{
    "MMBench_Columns": [
        {
            "title": {
                "en-US": "Method",
                "zh-CN": "方法"
            },
            "key": "Method",
            "fixed": "left",
            "customizeRender": {
                "type": "link"
            }
        },
        {
            "title": {
                "en-US": "Time",
                "zh-CN": "发布时间"
            },
            "key": "Time"
        },
        {
            "title": {
                "en-US": "Parameters",
                "zh-CN": "参数"
            },
            "key": "Parameters",
            "width": 110
        },
        {
            "title": {
                "en-US": "Language Model",
                "zh-CN": "语言模型"
            },
            "key": "Language Model",
            "width": 150
        },
        {
            "title": {
                "en-US": "Vision Model",
                "zh-CN": "视觉模型"
            },
            "key": "Vision Model",
            "width": 150
        },
        {
            "title": {
                "en-US": "Overall",
                "zh-CN": "均分"
            },
            "key": "Overall",
            "customizeRender": {
                "sorter": "ascend"
            },
            "width": 100
        },
        {
            "title": {
                "en-US": "LR",
                "zh-CN": "逻辑推理"
            },
            "key": "LR",
            "customizeRender": {
                "sorter": "ascend"
            },
            "width": 120
        },
        {
            "title": {
                "en-US": "AR",
                "zh-CN": "属性推理"
            },
            "key": "AR",
            "customizeRender": {
                "sorter": "ascend"
            },
            "width": 120
        },
        {
            "title": {
                "en-US": "RR",
                "zh-CN": "关系推理"
            },
            "key": "RR",
            "customizeRender": {
                "sorter": "ascend"
            },
            "width": 120
        },
        {
            "title": {
                "en-US": "FP-S",
                "zh-CN": "单对象感知"
            },
            "key": "FP-S",
            "customizeRender": {
                "sorter": "ascend"
            },
            "width": 120
        },
        {
            "title": {
                "en-US": "FP-C",
                "zh-CN": "多对象感知"
            },
            "key": "FP-C",
            "customizeRender": {
                "sorter": "ascend"
            },
            "width": 120
        },
        {
            "title": {
                "en-US": "CP",
                "zh-CN": "粗粒度感知"
            },
            "key": "CP",
            "customizeRender": {
                "sorter": "ascend"
            },
            "width": 120
        }
    ],
    "CCBench_Columns": [
        {
            "title": {
                "en-US": "Method",
                "zh-CN": "方法"
            },
            "key": "Method",
            "fixed": "left",
            "customizeRender": {
                "type": "link"
            }
        },
        {
            "title": {
                "en-US": "Time",
                "zh-CN": "发布时间"
            },
            "key": "Time"
        },
        {
            "title": {
                "en-US": "Parameters",
                "zh-CN": "参数"
            },
            "key": "Parameters",
            "width": 110
        },
        {
            "title": {
                "en-US": "Language Model",
                "zh-CN": "语言模型"
            },
            "key": "Language Model",
            "width": 150
        },
        {
            "title": {
                "en-US": "Vision Model",
                "zh-CN": "视觉模型"
            },
            "key": "Vision Model",
            "width": 150
        },
        {
            "title": {
                "en-US": "Overall",
                "zh-CN": "均分"
            },
            "key": "Overall",
            "customizeRender": {
                "sorter": "ascend"
            },
            "width": 100
        },
        {
            "title": {
                "en-US": "Calligraphy Painting",
                "zh-CN": "书画"
            },
            "key": "calligraphy_painting",
            "customizeRender": {
                "sorter": "ascend"
            },
            "width": 120
        },
        {
            "title": {
                "en-US": "Cultural Relic",
                "zh-CN": "文物"
            },
            "key": "cultural_relic",
            "customizeRender": {
                "sorter": "ascend"
            },
            "width": 120
        },
        {
            "title": {
                "en-US": "Food & Clothes",
                "zh-CN": "食物与服饰"
            },
            "key": "food_clothes",
            "customizeRender": {
                "sorter": "ascend"
            },
            "width": 120
        },
        {
            "title": {
                "en-US": "Historical Figures",
                "zh-CN": "历史人物"
            },
            "key": "historical_figure",
            "customizeRender": {
                "sorter": "ascend"
            },
            "width": 120
        },
        {
            "title": {
                "en-US": "Scenery & Building",
                "zh-CN": "风景与建筑"
            },
            "key": "scenery_building",
            "customizeRender": {
                "sorter": "ascend"
            },
            "width": 120
        },
        {
            "title": {
                "en-US": "Sketch Reasoning",
                "zh-CN": "图像推理"
            },
            "key": "sketch_reasoning",
            "customizeRender": {
                "sorter": "ascend"
            },
            "width": 120
        },
        {
            "title": {
                "en-US": "Traditional Show",
                "zh-CN": "传统戏剧"
            },
            "key": "traditional_show",
            "customizeRender": {
                "sorter": "ascend"
            },
            "width": 120
        }
    ],
    "CCBench_Data": [
        {
            "Method": [
                "Qwen-VL-Plus Base",
                "https://github.com/QwenLM/Qwen-VL?tab=readme-ov-file#qwen-vl-plus"
            ],
            "Parameters": "",
            "Language Model": "QwenLM",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2023/12/15",
            "key": 144,
            "Verified": "No",
            "OpenSource": "No",
            "cultural_relic": 73.2,
            "calligraphy_painting": 75.4,
            "historical_figure": 62.9,
            "scenery_building": 92.6,
            "traditional_show": 71.2,
            "sketch_reasoning": 86.7,
            "food_clothes": 74.8,
            "Overall": 77.6
        },
        {
            "Method": [
                "GPT-4o (0513, detail-high)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 336,
            "Overall": 71.2,
            "sketch_reasoning": 91.1,
            "historical_figure": 37.1,
            "calligraphy_painting": 70.2,
            "scenery_building": 89.5,
            "food_clothes": 62.6,
            "cultural_relic": 67.0,
            "traditional_show": 71.2
        },
        {
            "Method": [
                "GPT-4o (0513, detail-low)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "No",
            "key": 324,
            "Overall": 70.6,
            "food_clothes": 61.7,
            "calligraphy_painting": 68.4,
            "cultural_relic": 64.9,
            "scenery_building": 91.6,
            "sketch_reasoning": 86.7,
            "traditional_show": 71.2,
            "historical_figure": 40.0
        },
        {
            "Method": [
                "InternVL-Chat-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/04/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 311,
            "historical_figure": 28.6,
            "calligraphy_painting": 78.9,
            "scenery_building": 73.7,
            "traditional_show": 71.2,
            "food_clothes": 65.2,
            "cultural_relic": 69.1,
            "sketch_reasoning": 93.3,
            "Overall": 69.8
        },
        {
            "Method": [
                "TransCore-M",
                "https://github.com/PCIResearch/TransCore-M"
            ],
            "Parameters": "13.4B",
            "Language Model": "PCITransGPT-13B",
            "Vision Model": "CLIP ViT/L-14",
            "Org": "PCI Research",
            "Time": "2024/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 306,
            "historical_figure": 28.6,
            "calligraphy_painting": 78.9,
            "scenery_building": 73.7,
            "traditional_show": 71.2,
            "food_clothes": 65.2,
            "cultural_relic": 69.1,
            "sketch_reasoning": 93.3,
            "Overall": 69.8
        },
        {
            "Method": [
                "GLM-4v",
                "https://open.bigmodel.cn/dev/api#glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2024/05/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 329,
            "Overall": 63.9,
            "historical_figure": 5.7,
            "traditional_show": 71.2,
            "cultural_relic": 56.7,
            "food_clothes": 67.0,
            "scenery_building": 71.6,
            "sketch_reasoning": 82.2,
            "calligraphy_painting": 70.2
        },
        {
            "Method": [
                "Qwen-VL-Max",
                "https://huggingface.co/spaces/Qwen/Qwen-VL-Max"
            ],
            "Parameters": "",
            "Language Model": "QwenLM",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 222,
            "scenery_building": 87.4,
            "cultural_relic": 55.7,
            "traditional_show": 60.6,
            "food_clothes": 56.5,
            "sketch_reasoning": 80.0,
            "historical_figure": 28.6,
            "calligraphy_painting": 63.2,
            "Overall": 63.5
        },
        {
            "Method": [
                "InternVL-Chat-V1.2",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "40B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/02/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 272,
            "scenery_building": 55.8,
            "food_clothes": 56.5,
            "cultural_relic": 54.6,
            "sketch_reasoning": 91.1,
            "traditional_show": 65.2,
            "historical_figure": 31.4,
            "calligraphy_painting": 63.2,
            "Overall": 59.2
        },
        {
            "Method": [
                "GPT-4v (0409, detail-high)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 316,
            "sketch_reasoning": 82.2,
            "scenery_building": 72.6,
            "historical_figure": 28.6,
            "cultural_relic": 48.5,
            "food_clothes": 52.2,
            "calligraphy_painting": 59.6,
            "traditional_show": 53.0,
            "Overall": 57.3
        },
        {
            "Method": [
                "InternVL-Chat-V1.2-Plus",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "40B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/03/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 273,
            "scenery_building": 66.3,
            "food_clothes": 46.1,
            "cultural_relic": 52.6,
            "sketch_reasoning": 86.7,
            "traditional_show": 60.6,
            "historical_figure": 2.9,
            "calligraphy_painting": 64.9,
            "Overall": 55.7
        },
        {
            "Method": [
                "GPT-4v (0409, detail-low)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 314,
            "sketch_reasoning": 73.3,
            "scenery_building": 73.7,
            "historical_figure": 28.6,
            "cultural_relic": 44.3,
            "food_clothes": 49.6,
            "calligraphy_painting": 59.6,
            "traditional_show": 54.5,
            "Overall": 55.5
        },
        {
            "Method": [
                "Qwen-VL-Plus",
                "https://github.com/QwenLM/Qwen-VL?tab=readme-ov-file#qwen-vl-plus"
            ],
            "Parameters": "",
            "Language Model": "QwenLM",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/01/10",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 182,
            "sketch_reasoning": 77.8,
            "scenery_building": 80.0,
            "calligraphy_painting": 42.1,
            "food_clothes": 58.3,
            "historical_figure": 5.7,
            "cultural_relic": 40.2,
            "traditional_show": 57.6,
            "Overall": 55.1
        },
        {
            "Method": [
                "mPLUG-Owl2.1",
                ""
            ],
            "Parameters": "9.8B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-G/16",
            "Org": "Alibaba",
            "Time": "2024/01/26",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 212,
            "cultural_relic": 55.5,
            "scenery_building": 62,
            "sketch_reasoning": 77.8,
            "traditional_show": 50,
            "calligraphy_painting": 59.6,
            "food_clothes": 48.7,
            "historical_figure": 20.7,
            "Overall": 53.1
        },
        {
            "Method": [
                "Gemini-1.0-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2023/12/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 200,
            "traditional_show": 54.5,
            "calligraphy_painting": 50.9,
            "cultural_relic": 51.5,
            "scenery_building": 65.3,
            "historical_figure": 8.6,
            "sketch_reasoning": 77.8,
            "food_clothes": 46.1,
            "Overall": 52.5
        },
        {
            "Method": [
                "DeepSeek-VL-7B",
                "https://github.com/deepseek-ai/DeepSeek-VL"
            ],
            "Parameters": "7.3B",
            "Language Model": "DeekSeek-7B",
            "Vision Model": "SAM-B\nSigLIP-L",
            "Org": "DeepSeek",
            "Time": "2024/03/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 277,
            "historical_figure": 14.3,
            "traditional_show": 60.6,
            "calligraphy_painting": 59.6,
            "sketch_reasoning": 80.0,
            "scenery_building": 48.4,
            "food_clothes": 53.9,
            "cultural_relic": 45.4,
            "Overall": 52.4
        },
        {
            "Method": [
                "GPT-4v (1106, detail-high)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/04/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 313,
            "sketch_reasoning": 75.6,
            "scenery_building": 60.0,
            "historical_figure": 22.9,
            "cultural_relic": 42.3,
            "food_clothes": 48.7,
            "calligraphy_painting": 49.1,
            "traditional_show": 50.0,
            "Overall": 50.4
        },
        {
            "Method": [
                "CatVision",
                ""
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "4paradigm.Inc",
            "Time": "2024/01/23",
            "Verified": "No",
            "OpenSource": "No",
            "key": 202,
            "cultural_relic": 40.2,
            "scenery_building": 53.7,
            "sketch_reasoning": 66.7,
            "traditional_show": 54.5,
            "calligraphy_painting": 52.6,
            "food_clothes": 50.4,
            "historical_figure": 28.6,
            "Overall": 49.8
        },
        {
            "Method": [
                "InternLM-XComposer",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM-7B",
            "Vision Model": "EVA-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/9/26",
            "key": 146,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "cultural_relic": 52.6,
            "calligraphy_painting": 50.9,
            "historical_figure": 14.3,
            "scenery_building": 57.9,
            "traditional_show": 50.0,
            "sketch_reasoning": 73.3,
            "food_clothes": 40.9,
            "Overall": 49.6
        },
        {
            "Method": [
                "LLaVA-Next-Yi-34B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "34.8B",
            "Language Model": "Yi-34B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 285,
            "cultural_relic": 45.4,
            "calligraphy_painting": 57.9,
            "sketch_reasoning": 75.6,
            "food_clothes": 49.6,
            "scenery_building": 42.1,
            "historical_figure": 14.3,
            "traditional_show": 57.6,
            "Overall": 49.2
        },
        {
            "Method": [
                "InternLM-XComposer2",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 218,
            "traditional_show": 45.5,
            "food_clothes": 48.7,
            "historical_figure": 40.0,
            "calligraphy_painting": 63.2,
            "scenery_building": 38.9,
            "cultural_relic": 45.4,
            "sketch_reasoning": 64.4,
            "Overall": 48.2
        },
        {
            "Method": [
                "WeMM",
                "https://github.com/scenarios/WeMM/tree/main"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "SigLip-400M",
            "Org": "WechatCV",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 338,
            "Overall": 48.0,
            "scenery_building": 45.3,
            "calligraphy_painting": 59.6,
            "food_clothes": 52.2,
            "sketch_reasoning": 66.7,
            "traditional_show": 40.9,
            "cultural_relic": 45.4,
            "historical_figure": 20.0
        },
        {
            "Method": [
                "Monkey-Chat",
                "https://github.com/Yuliang-Liu/Monkey"
            ],
            "Parameters": "9.8B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-BigHuge",
            "Org": "Huazhong University of Science and Technology",
            "Time": "2024/01/16",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 196,
            "traditional_show": 48.5,
            "calligraphy_painting": 50.9,
            "cultural_relic": 44.3,
            "scenery_building": 66.3,
            "historical_figure": 2.9,
            "sketch_reasoning": 66.7,
            "food_clothes": 40.9,
            "Overall": 48.0
        },
        {
            "Method": [
                "InternLM-XComposer2-4KHD",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 341,
            "Overall": 47.1,
            "scenery_building": 48.4,
            "calligraphy_painting": 47.4,
            "food_clothes": 49.6,
            "sketch_reasoning": 75.6,
            "traditional_show": 45.5,
            "cultural_relic": 42.3,
            "historical_figure": 14.3
        },
        {
            "Method": [
                "XVERSE-V-13B",
                "https://github.com/xverse-ai/XVERSE-V-13B"
            ],
            "Parameters": "13B",
            "Language Model": "XVERSE-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "XVERSE",
            "Time": "2024/05/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 322,
            "Overall": 46.9,
            "food_clothes": 48.7,
            "traditional_show": 42.4,
            "calligraphy_painting": 54.4,
            "cultural_relic": 45.4,
            "scenery_building": 42.1,
            "sketch_reasoning": 71.1,
            "historical_figure": 22.9
        },
        {
            "Method": [
                "GPT-4v (1106, detail-low)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2023/12/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 312,
            "sketch_reasoning": 75.6,
            "scenery_building": 60.0,
            "historical_figure": 17.1,
            "cultural_relic": 41.2,
            "food_clothes": 43.5,
            "calligraphy_painting": 38.6,
            "traditional_show": 42.4,
            "Overall": 46.5
        },
        {
            "Method": [
                "LLaVA-InternLM2-20B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "20.2B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 191,
            "cultural_relic": 38.1,
            "scenery_building": 43.2,
            "traditional_show": 47.0,
            "food_clothes": 50.4,
            "historical_figure": 14.3,
            "sketch_reasoning": 71.1,
            "calligraphy_painting": 56.1,
            "Overall": 46.3
        },
        {
            "Method": [
                "Yi-VL-34B",
                "https://huggingface.co/01-ai/Yi-VL-34B"
            ],
            "Parameters": "34.6B",
            "Language Model": "Yi-34B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "01-AI",
            "Time": "2024/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 267,
            "scenery_building": 44.2,
            "food_clothes": 46.1,
            "cultural_relic": 44.3,
            "sketch_reasoning": 66.7,
            "traditional_show": 47.0,
            "historical_figure": 8.6,
            "calligraphy_painting": 57.9,
            "Overall": 46.1
        },
        {
            "Method": [
                "MiniCPM-Llama3-V2.5",
                "https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLip-400M",
            "Org": "OpenBMB",
            "Time": "2024/05/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 331,
            "Overall": 45.9,
            "cultural_relic": 38.1,
            "historical_figure": 22.9,
            "sketch_reasoning": 64.4,
            "food_clothes": 38.3,
            "scenery_building": 61.1,
            "calligraphy_painting": 47.4,
            "traditional_show": 47.0
        },
        {
            "Method": [
                "MiniCPM-V-2",
                "https://huggingface.co/openbmb/MiniCPM-V-2"
            ],
            "Parameters": "2.8B",
            "Vision Model": "SigLip-400M",
            "Language Model": "MiniCPM-2.4B",
            "Org": "OpenBMB",
            "Time": "2024/04/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 301,
            "scenery_building": 53.7,
            "sketch_reasoning": 64.4,
            "calligraphy_painting": 36.8,
            "historical_figure": 5.7,
            "traditional_show": 51.5,
            "cultural_relic": 39.2,
            "food_clothes": 48.7,
            "Overall": 45.3
        },
        {
            "Method": [
                "LLaVA-DINOv2",
                "https://huggingface.co/StarCycle/llava-dinov2-internlm2-7b-v1"
            ],
            "Parameters": "8.1B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "DINOv2 ViT-L/13",
            "Org": "Exponential Deep Space",
            "Time": "2024/02/13",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 232,
            "sketch_reasoning": 68.9,
            "traditional_show": 43.9,
            "food_clothes": 47.8,
            "calligraphy_painting": 61.4,
            "scenery_building": 33.7,
            "historical_figure": 28.6,
            "cultural_relic": 40.2,
            "Overall": 45.3
        },
        {
            "Method": [
                "360VL-70B",
                "https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5"
            ],
            "Parameters": "70B",
            "Language Model": "Llama-3-70B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "QiHoo360",
            "Time": "2024/05/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 330,
            "Overall": 44.9,
            "historical_figure": 37.1,
            "traditional_show": 45.5,
            "cultural_relic": 37.1,
            "food_clothes": 48.7,
            "scenery_building": 35.8,
            "sketch_reasoning": 73.3,
            "calligraphy_painting": 47.4
        },
        {
            "Method": [
                "InternVL-Chat-V1.1",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "19B",
            "Language Model": "LLaMA2-13B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/03/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 271,
            "scenery_building": 50.5,
            "food_clothes": 36.5,
            "cultural_relic": 35.1,
            "sketch_reasoning": 68.9,
            "traditional_show": 42.4,
            "historical_figure": 25.7,
            "calligraphy_painting": 52.6,
            "Overall": 43.5
        },
        {
            "Method": [
                "Yi-VL-6B",
                "https://huggingface.co/01-ai/Yi-VL-6B"
            ],
            "Parameters": "6.6B",
            "Language Model": "Yi-6B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "01-AI",
            "Time": "2024/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 266,
            "scenery_building": 45.3,
            "food_clothes": 40.9,
            "cultural_relic": 34.0,
            "sketch_reasoning": 66.7,
            "traditional_show": 53.0,
            "historical_figure": 11.4,
            "calligraphy_painting": 47.4,
            "Overall": 42.9
        },
        {
            "Method": [
                "LLaVA-InternLM2-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "8.1B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 190,
            "cultural_relic": 38.1,
            "scenery_building": 31.6,
            "traditional_show": 47.0,
            "food_clothes": 48.7,
            "historical_figure": 8.6,
            "sketch_reasoning": 71.1,
            "calligraphy_painting": 49.1,
            "Overall": 42.5
        },
        {
            "Method": [
                "MiniCPM-V",
                "https://huggingface.co/openbmb/MiniCPM-V"
            ],
            "Parameters": "3B",
            "Language Model": "MiniCPM-2.4B",
            "Vision Model": "SigLip-400M",
            "Org": "OpenBMB",
            "Time": "2024/02/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 229,
            "sketch_reasoning": 55.6,
            "traditional_show": 48.5,
            "food_clothes": 40.9,
            "calligraphy_painting": 35.1,
            "scenery_building": 54.7,
            "historical_figure": 5.7,
            "cultural_relic": 34.0,
            "Overall": 41.4
        },
        {
            "Method": [
                "Qwen-VL-Chat",
                "https://github.com/QwenLM/Qwen-VL"
            ],
            "Parameters": "9.6B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-G/16",
            "Org": "Alibaba",
            "Time": "2023/8/24",
            "key": 147,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "cultural_relic": 37.1,
            "calligraphy_painting": 42.1,
            "historical_figure": 5.7,
            "scenery_building": 56.8,
            "traditional_show": 47.0,
            "sketch_reasoning": 55.6,
            "food_clothes": 33.0,
            "Overall": 41.2
        },
        {
            "Method": [
                "InternLM-XComposer2-1.8B",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 340,
            "Overall": 40.4,
            "scenery_building": 43.2,
            "calligraphy_painting": 35.1,
            "food_clothes": 40.0,
            "sketch_reasoning": 53.3,
            "traditional_show": 47.0,
            "cultural_relic": 33.0,
            "historical_figure": 34.3
        },
        {
            "Method": [
                "ShareCaptioner",
                "https://huggingface.co/Lin-Chen/ShareCaptioner/"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM-7B",
            "Vision Model": "EVA-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 315,
            "sketch_reasoning": 62.2,
            "scenery_building": 50.5,
            "historical_figure": 22.9,
            "cultural_relic": 33.0,
            "food_clothes": 38.3,
            "calligraphy_painting": 36.8,
            "traditional_show": 37.9,
            "Overall": 40.4
        },
        {
            "Method": [
                "SharedCaptioner",
                "https://huggingface.co/Lin-Chen/ShareCaptioner/"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM-7B",
            "Vision Model": "EVA-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/03",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 179,
            "historical_figure": 22.9,
            "traditional_show": 37.9,
            "sketch_reasoning": 62.2,
            "food_clothes": 38.3,
            "cultural_relic": 33.0,
            "scenery_building": 50.5,
            "calligraphy_painting": 36.8,
            "Overall": 40.4
        },
        {
            "Method": [
                "CogVLM2-19B-Chat",
                "https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B"
            ],
            "Parameters": "19B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "EVA2-CLIP-E",
            "Org": "Zhipu AI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 335,
            "Overall": 38.8,
            "sketch_reasoning": 64.4,
            "historical_figure": 0.0,
            "calligraphy_painting": 24.6,
            "scenery_building": 52.6,
            "food_clothes": 46.1,
            "cultural_relic": 23.7,
            "traditional_show": 43.9
        },
        {
            "Method": [
                "IDEFICS2-8B",
                "https://huggingface.co/HuggingFaceM4/idefics2-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Mistral-7B",
            "Vision Model": "SigLip-400M",
            "Org": "Hugging Face",
            "Time": "2024/04/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 318,
            "food_clothes": 40.0,
            "traditional_show": 31.8,
            "scenery_building": 43.2,
            "cultural_relic": 30.9,
            "calligraphy_painting": 33.3,
            "historical_figure": 11.4,
            "sketch_reasoning": 68.9,
            "Overall": 37.6
        },
        {
            "Method": [
                "DeepSeek-VL-1.3B",
                "https://github.com/deepseek-ai/DeepSeek-VL"
            ],
            "Parameters": "2.0B",
            "Language Model": "DeekSeek-1B",
            "Vision Model": "SAM-B\nSigLIP-L",
            "Org": "DeepSeek",
            "Time": "2024/03/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 276,
            "historical_figure": 0.0,
            "traditional_show": 45.5,
            "calligraphy_painting": 33.3,
            "sketch_reasoning": 60.0,
            "scenery_building": 40.0,
            "food_clothes": 34.8,
            "cultural_relic": 39.2,
            "Overall": 37.6
        },
        {
            "Method": [
                "LLaVA-InternLM-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "7.6B",
            "Language Model": "InternLM-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 176,
            "traditional_show": 25.8,
            "sketch_reasoning": 71.1,
            "cultural_relic": 33.0,
            "calligraphy_painting": 45.6,
            "scenery_building": 38.9,
            "historical_figure": 5.7,
            "food_clothes": 38.3,
            "Overall": 37.3
        },
        {
            "Method": [
                "OmniLMM-12B",
                "https://huggingface.co/openbmb/OmniLMM-12B"
            ],
            "Parameters": "12B",
            "Language Model": "Zephyr-7B-β",
            "Vision Model": "EVA-02-5B",
            "Org": "OpenBMB",
            "Time": "2024/02/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 228,
            "sketch_reasoning": 73.3,
            "traditional_show": 39.4,
            "food_clothes": 35.7,
            "calligraphy_painting": 31.6,
            "scenery_building": 41.1,
            "historical_figure": 2.9,
            "cultural_relic": 32.0,
            "Overall": 37.1
        },
        {
            "Method": [
                "Monkey",
                "https://github.com/Yuliang-Liu/Monkey"
            ],
            "Parameters": "9.8B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-BigHuge",
            "Org": "Huazhong University of Science and Technology",
            "Time": "2024/01/11",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 184,
            "sketch_reasoning": 40.0,
            "scenery_building": 51.6,
            "calligraphy_painting": 42.1,
            "food_clothes": 33.0,
            "historical_figure": 5.7,
            "cultural_relic": 33.0,
            "traditional_show": 39.4,
            "Overall": 37.1
        },
        {
            "Method": [
                "LLaVA-InternLM2-1.8B",
                "https://huggingface.co/StarCycle/llava-siglip-internlm2-1_8b-v1"
            ],
            "Parameters": "2.2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "SigLIP-400M",
            "Org": "Exponential Deep Space",
            "Time": "2024/03/10",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 244,
            "historical_figure": 11.4,
            "cultural_relic": 30.9,
            "traditional_show": 31.8,
            "scenery_building": 28.4,
            "sketch_reasoning": 60.0,
            "food_clothes": 44.3,
            "calligraphy_painting": 43.9,
            "Overall": 36.3
        },
        {
            "Method": [
                "RekaFlash",
                "https://www.reka.ai"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Reka AI",
            "Time": "2024/05/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 328,
            "Overall": 33.7,
            "historical_figure": 17.1,
            "traditional_show": 39.4,
            "cultural_relic": 28.9,
            "food_clothes": 29.6,
            "scenery_building": 40.0,
            "sketch_reasoning": 55.6,
            "calligraphy_painting": 26.3
        },
        {
            "Method": [
                "LLaVA-v1.5-13B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 178,
            "traditional_show": 24.2,
            "sketch_reasoning": 73.3,
            "cultural_relic": 27.8,
            "calligraphy_painting": 40.4,
            "scenery_building": 25.3,
            "historical_figure": 8.6,
            "food_clothes": 36.5,
            "Overall": 32.9
        },
        {
            "Method": [
                "Sphinx",
                "https://github.com/Alpha-VLLM/LLaMA2-Accessory/tree/main/SPHINX"
            ],
            "Parameters": "16.5B",
            "Language Model": "LLaMA2 13B",
            "Vision Model": "CLIP ViT-L/14\nCLIP ConvNeXT\nConvNeXT-XXLarge\nDinov2-VIT-G/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/10/25",
            "key": 150,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "cultural_relic": 32.0,
            "calligraphy_painting": 31.6,
            "historical_figure": 0.0,
            "scenery_building": 36.8,
            "traditional_show": 24.2,
            "sketch_reasoning": 66.7,
            "food_clothes": 28.7,
            "Overall": 32.0
        },
        {
            "Method": [
                "mPLUG-Owl2",
                "https://github.com/X-PLUG/mPLUG-Owl/tree/main/mPLUG-Owl2"
            ],
            "Parameters": "8.2B",
            "Language Model": "LLaMA2 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "DAMO Academy",
            "Time": "2023/11/10",
            "key": 151,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "cultural_relic": 28.9,
            "calligraphy_painting": 35.1,
            "historical_figure": 5.7,
            "scenery_building": 31.6,
            "traditional_show": 31.8,
            "sketch_reasoning": 55.6,
            "food_clothes": 27.8,
            "Overall": 31.0
        },
        {
            "Method": [
                "ShareGPT4V-7B",
                "https://sharegpt4v.github.io"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 261,
            "scenery_building": 30.5,
            "food_clothes": 26.1,
            "cultural_relic": 26.8,
            "sketch_reasoning": 73.3,
            "traditional_show": 27.3,
            "historical_figure": 2.9,
            "calligraphy_painting": 35.1,
            "Overall": 30.8
        },
        {
            "Method": [
                "ShareGPT4V-13B",
                "https://sharegpt4v.github.io"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 262,
            "scenery_building": 32.6,
            "food_clothes": 18.3,
            "cultural_relic": 26.8,
            "sketch_reasoning": 73.3,
            "traditional_show": 27.3,
            "historical_figure": 11.4,
            "calligraphy_painting": 38.6,
            "Overall": 30.4
        },
        {
            "Method": [
                "LLaVA-Next-Mistral-7B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "7.6B",
            "Language Model": "Mistral-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 283,
            "cultural_relic": 28.9,
            "calligraphy_painting": 31.6,
            "sketch_reasoning": 62.2,
            "food_clothes": 27.8,
            "scenery_building": 27.4,
            "historical_figure": 5.7,
            "traditional_show": 28.8,
            "Overall": 30.0
        },
        {
            "Method": [
                "PaliGemma-3B-mix-448",
                "https://github.com/google-research/big_vision/blob/main/big_vision/configs/proj/paligemma/README.md"
            ],
            "Parameters": "3B",
            "Language Model": "Gemma-2B",
            "Vision Model": "SigLip-400M",
            "Org": "Google",
            "Time": "2024/05/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 327,
            "Overall": 29.6,
            "scenery_building": 27.4,
            "food_clothes": 37.4,
            "cultural_relic": 22.7,
            "sketch_reasoning": 51.1,
            "calligraphy_painting": 28.1,
            "traditional_show": 30.3,
            "historical_figure": 2.9
        },
        {
            "Method": [
                "LLaVA-Next-Vicuna-13B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 284,
            "cultural_relic": 23.7,
            "calligraphy_painting": 38.6,
            "sketch_reasoning": 68.9,
            "food_clothes": 21.7,
            "scenery_building": 29.5,
            "historical_figure": 11.4,
            "traditional_show": 21.2,
            "Overall": 28.8
        },
        {
            "Method": [
                "MMAlaya",
                "https://huggingface.co/DataCanvas/MMAlaya"
            ],
            "Parameters": "7.8B",
            "Language Model": "Alaya-7B-Chat",
            "Vision Model": "EVA-G",
            "Org": "DataCanvas",
            "Time": "2024/01/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 220,
            "historical_figure": 5.7,
            "traditional_show": 21.2,
            "calligraphy_painting": 29.8,
            "cultural_relic": 27.8,
            "sketch_reasoning": 51.1,
            "food_clothes": 32.2,
            "scenery_building": 27.4,
            "Overall": 28.6
        },
        {
            "Method": [
                "LLaVA-v1.5-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 177,
            "traditional_show": 19.7,
            "sketch_reasoning": 66.7,
            "cultural_relic": 27.8,
            "calligraphy_painting": 33.3,
            "scenery_building": 29.5,
            "historical_figure": 5.7,
            "food_clothes": 22.6,
            "Overall": 28.4
        },
        {
            "Method": [
                "LLaVA-LLaMA-3-8B",
                "https://huggingface.co/xtuner/llava-llama-3-8b-v1_1"
            ],
            "Parameters": "8B",
            "Language Model": "LLaMA-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/05/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 321,
            "sketch_reasoning": 57.8,
            "scenery_building": 27.4,
            "calligraphy_painting": 31.6,
            "food_clothes": 26.1,
            "traditional_show": 22.7,
            "cultural_relic": 22.7,
            "historical_figure": 14.3,
            "Overall": 27.8
        },
        {
            "Method": [
                "Claude3-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 290,
            "cultural_relic": 24.7,
            "calligraphy_painting": 28.1,
            "sketch_reasoning": 48.9,
            "food_clothes": 20.0,
            "scenery_building": 32.6,
            "historical_figure": 11.4,
            "traditional_show": 33.3,
            "Overall": 27.8
        },
        {
            "Method": [
                "Sphinx-V2",
                "https://github.com/Alpha-VLLM/LLaMA2-Accessory/tree/main/SPHINX"
            ],
            "Parameters": "16.5B",
            "Language Model": "LLaMA2 13B",
            "Vision Model": "CLIP ViT-L/14\nCLIP ConvNeXT\nConvNeXT-XXLarge\nDinov2-VIT-G/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/11/15",
            "key": 154,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "cultural_relic": 23.7,
            "calligraphy_painting": 36.8,
            "historical_figure": 8.6,
            "scenery_building": 29.5,
            "traditional_show": 22.7,
            "sketch_reasoning": 55.6,
            "food_clothes": 18.3,
            "Overall": 26.7
        },
        {
            "Method": [
                "Claude3-Opus",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 291,
            "cultural_relic": 22.7,
            "calligraphy_painting": 36.8,
            "sketch_reasoning": 35.6,
            "food_clothes": 18.3,
            "scenery_building": 35.8,
            "historical_figure": 2.9,
            "traditional_show": 28.8,
            "Overall": 26.3
        },
        {
            "Method": [
                "RekaEdge",
                "https://www.reka.ai"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Reka AI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 337,
            "Overall": 24.7,
            "sketch_reasoning": 24.4,
            "historical_figure": 2.9,
            "calligraphy_painting": 28.1,
            "scenery_building": 24.2,
            "food_clothes": 24.3,
            "cultural_relic": 25.8,
            "traditional_show": 33.3
        },
        {
            "Method": [
                "Claude3-Haiku",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 289,
            "cultural_relic": 20.6,
            "calligraphy_painting": 26.3,
            "sketch_reasoning": 40.0,
            "food_clothes": 20.9,
            "scenery_building": 32.6,
            "historical_figure": 11.4,
            "traditional_show": 19.7,
            "Overall": 24.5
        },
        {
            "Method": [
                "Phi-3-Vision",
                "https://huggingface.co/microsoft/Phi-3-vision-128k-instruct"
            ],
            "Parameters": "4.2B",
            "Language Model": "Phi-3",
            "Vision Model": "CLIP ViT/L-14",
            "Org": "Microsoft",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 334,
            "Overall": 24.1,
            "sketch_reasoning": 48.9,
            "historical_figure": 17.1,
            "calligraphy_painting": 26.3,
            "scenery_building": 18.9,
            "food_clothes": 22.6,
            "cultural_relic": 25.8,
            "traditional_show": 16.7
        },
        {
            "Method": [
                "CogVLM-17B-Chat",
                "https://huggingface.co/THUDM/cogvlm-chat-hf"
            ],
            "Parameters": "17B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "EVA2-CLIP-E",
            "Org": "Zhipu AI",
            "Time": "2024/01/03",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 180,
            "historical_figure": 11.4,
            "traditional_show": 27.3,
            "sketch_reasoning": 46.7,
            "food_clothes": 11.3,
            "cultural_relic": 17.5,
            "scenery_building": 15.8,
            "calligraphy_painting": 15.8,
            "Overall": 19.0
        },
        {
            "Method": [
                "Emu2_chat",
                "https://github.com/baaivision/Emu/tree/main/Emu2"
            ],
            "Parameters": "37B",
            "Language Model": "LLaMA-33B",
            "Vision Model": "EVA-02-CLIP-E-plus",
            "Org": "Beijing Academy of Artificial Intelligence",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 187,
            "traditional_show": 12.1,
            "scenery_building": 23.2,
            "historical_figure": 5.7,
            "cultural_relic": 15.5,
            "food_clothes": 15.7,
            "sketch_reasoning": 44.4,
            "calligraphy_painting": 19.3,
            "Overall": 18.8
        },
        {
            "Method": [
                "VisualGLM",
                "https://github.com/THUDM/VisualGLM-6B"
            ],
            "Parameters": "8B",
            "Language Model": "ChatGLM 6B",
            "Vision Model": "EVA-CLIP",
            "Org": "Tsinghua University",
            "Time": "2023/5/17",
            "key": 156,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "cultural_relic": 15.5,
            "calligraphy_painting": 19.3,
            "historical_figure": 0.0,
            "scenery_building": 27.4,
            "traditional_show": 13.6,
            "sketch_reasoning": 40.0,
            "food_clothes": 7.8,
            "Overall": 17.3
        },
        {
            "Method": [
                "LLaVA-v1-7B",
                "https://arxiv.org/abs/2304.08485"
            ],
            "Parameters": "7.2B",
            "Language Model": "LLaMA 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin-Madison",
            "Time": "2023/4/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 264,
            "scenery_building": 13.7,
            "food_clothes": 13.9,
            "cultural_relic": 16.5,
            "sketch_reasoning": 11.1,
            "traditional_show": 10.6,
            "historical_figure": 2.9,
            "calligraphy_painting": 12.3,
            "Overall": 12.7
        },
        {
            "Method": [
                "InstructBLIP-7B",
                "https://arxiv.org/abs/2305.06500"
            ],
            "Parameters": "8B",
            "Language Model": "Vicuna 7B",
            "Vision Model": "EVA-G",
            "Org": "Salesforce Research",
            "Time": "2023/5/11",
            "key": 157,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "cultural_relic": 9.3,
            "calligraphy_painting": 8.8,
            "historical_figure": 0.0,
            "scenery_building": 11.6,
            "traditional_show": 18.2,
            "sketch_reasoning": 6.7,
            "food_clothes": 21.7,
            "Overall": 12.7
        },
        {
            "Method": [
                "IDEFICS-80B-Instruct",
                "https://huggingface.co/HuggingFaceM4/idefics-80b-instruct"
            ],
            "Parameters": "80B",
            "Language Model": "LLaMA65B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "Hugging Face",
            "Time": "2023/7/25",
            "key": 158,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "cultural_relic": 8.2,
            "calligraphy_painting": 8.8,
            "historical_figure": 0.0,
            "scenery_building": 16.8,
            "traditional_show": 9.1,
            "sketch_reasoning": 22.2,
            "food_clothes": 7.8,
            "Overall": 10.6
        },
        {
            "Method": [
                "IDEFICS-9B-Instruct",
                "https://huggingface.co/HuggingFaceM4/idefics-9b-instruct"
            ],
            "Parameters": "9B",
            "Language Model": "LLaMA 7B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "Hugging Face",
            "Time": "2023/7/25",
            "key": 160,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "cultural_relic": 6.2,
            "calligraphy_painting": 12.3,
            "historical_figure": 5.7,
            "scenery_building": 7.4,
            "traditional_show": 9.1,
            "sketch_reasoning": 11.1,
            "food_clothes": 6.1,
            "Overall": 7.8
        },
        {
            "Method": [
                "PandaGPT-13B",
                "https://arxiv.org/abs/2305.16355"
            ],
            "Parameters": "14B",
            "Language Model": "Vicuna 13B",
            "Vision Model": "ImageBind ViT-H/14",
            "Org": "Tencent AI Lab",
            "Time": "2023/5/25",
            "key": 161,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "cultural_relic": 9.3,
            "calligraphy_painting": 8.8,
            "historical_figure": 2.9,
            "scenery_building": 5.3,
            "traditional_show": 7.6,
            "sketch_reasoning": 4.4,
            "food_clothes": 6.1,
            "Overall": 6.7
        },
        {
            "Method": [
                "OpenFlamingo v2",
                "https://github.com/mlfoundations/open_flamingo"
            ],
            "Parameters": "9B",
            "Language Model": "MPT 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "The University of Washington",
            "Time": "2023/6/28",
            "key": 162,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "cultural_relic": 6.2,
            "calligraphy_painting": 3.5,
            "historical_figure": 0.0,
            "scenery_building": 11.6,
            "traditional_show": 0.0,
            "sketch_reasoning": 6.7,
            "food_clothes": 8.7,
            "Overall": 6.3
        },
        {
            "Method": [
                "Qwen-VL",
                "https://github.com/QwenLM/Qwen-VL"
            ],
            "Parameters": "9.6B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-G/16",
            "Org": "Alibaba",
            "Time": "2023/8/24",
            "key": 163,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "cultural_relic": 8.2,
            "calligraphy_painting": 10.5,
            "historical_figure": 0.0,
            "scenery_building": 5.3,
            "traditional_show": 4.5,
            "sketch_reasoning": 6.7,
            "food_clothes": 5.2,
            "Overall": 6.1
        },
        {
            "Method": [
                "MiniGPT-4-v1-7B",
                "https://arxiv.org/abs/2304.10592"
            ],
            "Parameters": "8B",
            "Language Model": "Vicuna 7B",
            "Vision Model": "EVA-G",
            "Org": "King Abdullah University of Science and Technology",
            "Time": "2023/4/20",
            "key": 164,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "cultural_relic": 4.1,
            "calligraphy_painting": 7.0,
            "historical_figure": 0.0,
            "scenery_building": 1.1,
            "traditional_show": 0.0,
            "sketch_reasoning": 0.0,
            "food_clothes": 0.0,
            "Overall": 1.8
        },
        {
            "Method": [
                "MiniGPT-4-v2",
                "https://minigpt-v2.github.io"
            ],
            "Parameters": "8B",
            "Language Model": "LLaMA2 13B",
            "Vision Model": "EVA-G",
            "Org": "King Abdullah University of Science and Technology",
            "Time": "2023/10/27",
            "key": 165,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "cultural_relic": 2.1,
            "calligraphy_painting": 0.0,
            "historical_figure": 2.9,
            "scenery_building": 0.0,
            "traditional_show": 0.0,
            "sketch_reasoning": 4.4,
            "food_clothes": 1.7,
            "Overall": 1.4
        },
        {
            "Method": [
                "OpenFlamingo",
                "https://github.com/mlfoundations/open_flamingo"
            ],
            "Parameters": "9B",
            "Language Model": "LLaMA 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "The University of Washington",
            "Time": "2023/3/29",
            "key": 166,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "cultural_relic": 0.0,
            "calligraphy_painting": 1.8,
            "historical_figure": 0.0,
            "scenery_building": 0.0,
            "traditional_show": 1.5,
            "sketch_reasoning": 2.2,
            "food_clothes": 0.9,
            "Overall": 0.8
        },
        {
            "Overall": 62.9,
            "calligraphy_painting": 68.4,
            "cultural_relic": 62.9,
            "food_clothes": 63.5,
            "historical_figure": 31.4,
            "scenery_building": 63.2,
            "sketch_reasoning": 80.0,
            "traditional_show": 62.1,
            "Method": [
                "Mini-InternVL-Chat-2B-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 277
        },
        {
            "Overall": 59.4,
            "calligraphy_painting": 57.9,
            "cultural_relic": 58.8,
            "food_clothes": 60.9,
            "historical_figure": 17.1,
            "scenery_building": 62.1,
            "sketch_reasoning": 77.8,
            "traditional_show": 65.2,
            "Method": [
                "Mini-InternVL-Chat-4B-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 278
        },
        {
            "Overall": 28.4,
            "calligraphy_painting": 7.0,
            "cultural_relic": 37.1,
            "food_clothes": 27.8,
            "historical_figure": 11.4,
            "scenery_building": 53.7,
            "sketch_reasoning": 40.0,
            "traditional_show": 0.0,
            "Method": [
                "Gemini-1.5-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 279
        },
        {
            "Overall": 54.1,
            "calligraphy_painting": 54.4,
            "cultural_relic": 49.5,
            "food_clothes": 53.9,
            "historical_figure": 14.3,
            "scenery_building": 68.4,
            "sketch_reasoning": 73.3,
            "traditional_show": 48.5,
            "Method": [
                "Claude3.5-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/06/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 284
        },
        {
            "Overall": 69.6,
            "calligraphy_painting": 75.4,
            "cultural_relic": 64.9,
            "food_clothes": 73.9,
            "historical_figure": 14.3,
            "scenery_building": 74.7,
            "sketch_reasoning": 91.1,
            "traditional_show": 71.2,
            "Method": [
                "CongRong",
                "https://mllm.cloudwalk.com/web/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "CloudWalk",
            "Time": "2024/06/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 285
        },
        {
            "Overall": 38.4,
            "calligraphy_painting": 36.8,
            "cultural_relic": 37.1,
            "food_clothes": 37.4,
            "historical_figure": 2.9,
            "scenery_building": 40.0,
            "sketch_reasoning": 73.3,
            "traditional_show": 36.4,
            "Method": [
                "Llama-3-MixSense",
                "https://huggingface.co/Zero-Vision/Llama-3-MixSense"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "ZeroVision",
            "Time": "2024/07/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 288
        },
        {
            "Overall": 83.5,
            "calligraphy_painting": 86.0,
            "cultural_relic": 87.6,
            "food_clothes": 78.3,
            "historical_figure": 57.1,
            "scenery_building": 91.6,
            "sketch_reasoning": 93.3,
            "traditional_show": 80.3,
            "Method": [
                "InternVL-2.0-Pro",
                "https://huggingface.co/spaces/OpenGVLab/InternVL/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/08",
            "Verified": "Yes",
            "OpenSource": "No",
            "key": 290
        },
        {
            "Overall": 76.3,
            "calligraphy_painting": 91.2,
            "cultural_relic": 80.4,
            "food_clothes": 73.9,
            "historical_figure": 11.4,
            "scenery_building": 80.0,
            "sketch_reasoning": 86.7,
            "traditional_show": 83.3,
            "Method": [
                "InternVL2-1B",
                "https://huggingface.co/OpenGVLab/InternVL2-1B"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 292
        },
        {
            "Overall": 74.7,
            "calligraphy_painting": 82.5,
            "cultural_relic": 84.5,
            "food_clothes": 78.3,
            "historical_figure": 11.4,
            "scenery_building": 70.5,
            "sketch_reasoning": 93.3,
            "traditional_show": 74.2,
            "Method": [
                "InternVL2-2B",
                "https://huggingface.co/OpenGVLab/InternVL2-2B"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 293
        },
        {
            "Overall": 66.3,
            "calligraphy_painting": 71.9,
            "cultural_relic": 68.0,
            "food_clothes": 63.5,
            "historical_figure": 20.0,
            "scenery_building": 68.4,
            "sketch_reasoning": 86.7,
            "traditional_show": 71.2,
            "Method": [
                "InternVL2-4B",
                "https://huggingface.co/OpenGVLab/InternVL2-4B"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 294
        },
        {
            "Overall": 77.1,
            "calligraphy_painting": 89.5,
            "cultural_relic": 84.5,
            "food_clothes": 76.5,
            "historical_figure": 17.1,
            "scenery_building": 76.8,
            "sketch_reasoning": 91.1,
            "traditional_show": 78.8,
            "Method": [
                "InternVL2-8B",
                "https://huggingface.co/OpenGVLab/InternVL2-8B"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 295
        },
        {
            "Overall": 73.9,
            "calligraphy_painting": 87.7,
            "cultural_relic": 73.2,
            "food_clothes": 79.1,
            "historical_figure": 20.0,
            "scenery_building": 70.5,
            "sketch_reasoning": 93.3,
            "traditional_show": 74.2,
            "Method": [
                "InternVL2-26B",
                "https://huggingface.co/OpenGVLab/InternVL2-26B"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 296
        },
        {
            "Overall": 80.2,
            "calligraphy_painting": 87.7,
            "cultural_relic": 88.7,
            "food_clothes": 80.0,
            "historical_figure": 17.1,
            "scenery_building": 80.0,
            "sketch_reasoning": 95.6,
            "traditional_show": 84.8,
            "Method": [
                "InternVL2-40B",
                "https://huggingface.co/OpenGVLab/InternVL2-40B"
            ],
            "Parameters": "40B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 297
        },
        {
            "Overall": 23.7,
            "calligraphy_painting": 26.3,
            "cultural_relic": 27.8,
            "food_clothes": 20.0,
            "historical_figure": 0.0,
            "scenery_building": 26.3,
            "sketch_reasoning": 37.8,
            "traditional_show": 21.2,
            "Method": [
                "Cambrian-8B",
                "https://huggingface.co/nyu-visionx/cambrian-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "NYU",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 298
        },
        {
            "Overall": 49.6,
            "calligraphy_painting": 43.9,
            "cultural_relic": 44.3,
            "food_clothes": 50.4,
            "historical_figure": 11.4,
            "scenery_building": 53.7,
            "sketch_reasoning": 77.8,
            "traditional_show": 56.1,
            "Method": [
                "InternLM-XComposer2.5",
                "https://huggingface.co/internlm/internlm-xcomposer2d5-7b"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 299
        },
        {
            "Overall": 44.1,
            "calligraphy_painting": 47.4,
            "cultural_relic": 41.2,
            "food_clothes": 45.2,
            "historical_figure": 8.6,
            "scenery_building": 40.0,
            "sketch_reasoning": 77.8,
            "traditional_show": 45.5,
            "Method": [
                "Bunny-Llama3-8B",
                "https://huggingface.co/BAAI/Bunny-v1_1-Llama-3-8B-V"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "BAAI",
            "Time": "2024/07/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 303
        },
        {
            "Overall": 61.4,
            "calligraphy_painting": 57.9,
            "cultural_relic": 55.7,
            "food_clothes": 59.1,
            "historical_figure": 37.1,
            "scenery_building": 73.7,
            "sketch_reasoning": 77.8,
            "traditional_show": 60.6,
            "Method": [
                "GPT-4o-mini (0718, detail-high)",
                "https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/07/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 305
        },
        {
            "Overall": 36.7,
            "calligraphy_painting": 33.3,
            "cultural_relic": 26.8,
            "food_clothes": 40.9,
            "historical_figure": 14.3,
            "scenery_building": 33.7,
            "sketch_reasoning": 62.2,
            "traditional_show": 45.5,
            "Method": [
                "Ovis1.5-Llama3-8B",
                "https://huggingface.co/AIDC-AI/Ovis1.5-Llama3-8B"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 306
        },
        {
            "Overall": 1.4,
            "calligraphy_painting": 3.5,
            "cultural_relic": 2.1,
            "food_clothes": 0.9,
            "historical_figure": 0.0,
            "scenery_building": 2.1,
            "sketch_reasoning": 0.0,
            "traditional_show": 0.0,
            "Method": [
                "Chameleon-7B",
                "https://huggingface.co/facebook/chameleon-7b"
            ],
            "Parameters": "7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 309
        },
        {
            "Overall": 5.9,
            "calligraphy_painting": 5.3,
            "cultural_relic": 6.2,
            "food_clothes": 7.8,
            "historical_figure": 0.0,
            "scenery_building": 7.4,
            "sketch_reasoning": 2.2,
            "traditional_show": 6.1,
            "Method": [
                "Chameleon-30B",
                "https://huggingface.co/facebook/chameleon-30b"
            ],
            "Parameters": "30B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 310
        },
        {
            "Overall": 26.7,
            "calligraphy_painting": 29.8,
            "cultural_relic": 27.8,
            "food_clothes": 13.9,
            "historical_figure": 8.6,
            "scenery_building": 27.4,
            "sketch_reasoning": 68.9,
            "traditional_show": 24.2,
            "Method": [
                "Cambrian-13B",
                "https://huggingface.co/nyu-visionx/cambrian-13b"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "NYU",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 311
        },
        {
            "Overall": 50.6,
            "calligraphy_painting": 63.2,
            "cultural_relic": 49.5,
            "food_clothes": 40.9,
            "historical_figure": 17.1,
            "scenery_building": 48.4,
            "sketch_reasoning": 84.4,
            "traditional_show": 56.1,
            "Method": [
                "Yi-Vision",
                "https://platform.lingyiwanwu.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "01-AI",
            "Time": "2024/08/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 312
        },
        {
            "Overall": 44.1,
            "calligraphy_painting": 42.1,
            "cultural_relic": 26.8,
            "food_clothes": 52.2,
            "historical_figure": 25.7,
            "scenery_building": 44.2,
            "sketch_reasoning": 64.4,
            "traditional_show": 53.0,
            "Method": [
                "Ovis1.5-Gemma2-9B",
                "https://huggingface.co/AIDC-AI/Ovis1.5-Gemma2-9B"
            ],
            "Parameters": "11.4B",
            "Language Model": "Gemma2-9B-It",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/08/04",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 313
        },
        {
            "Overall": 32.7,
            "calligraphy_painting": 29.8,
            "cultural_relic": 26.8,
            "food_clothes": 32.2,
            "historical_figure": 20.0,
            "scenery_building": 32.6,
            "sketch_reasoning": 60.0,
            "traditional_show": 33.3,
            "Method": [
                "LLaVA-Next-Llama3",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "ByteDance",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 307
        },
        {
            "Overall": 42.4,
            "calligraphy_painting": 47.4,
            "cultural_relic": 40.2,
            "food_clothes": 37.4,
            "historical_figure": 5.7,
            "scenery_building": 43.2,
            "sketch_reasoning": 71.1,
            "traditional_show": 48.5,
            "Method": [
                "LLaVA-Next-Interleave-7B-DPO",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen1.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 308
        },
        {
            "Overall": 44.3,
            "calligraphy_painting": 50.9,
            "cultural_relic": 41.2,
            "food_clothes": 40.9,
            "historical_figure": 11.4,
            "scenery_building": 42.1,
            "sketch_reasoning": 68.9,
            "traditional_show": 53.0,
            "Method": [
                "LLaVA-Next-Interleave-7B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen1.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 314
        },
        {
            "Overall": 52.2,
            "calligraphy_painting": 59.6,
            "cultural_relic": 48.5,
            "food_clothes": 57.4,
            "historical_figure": 14.3,
            "scenery_building": 53.7,
            "sketch_reasoning": 68.9,
            "traditional_show": 48.5,
            "Method": [
                "LLaVA-Next-Qwen-32B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "33B",
            "Language Model": "Qwen1.5-32B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 315
        },
        {
            "Overall": 37.1,
            "calligraphy_painting": 38.6,
            "cultural_relic": 30.9,
            "food_clothes": 33.9,
            "historical_figure": 11.4,
            "scenery_building": 41.1,
            "sketch_reasoning": 73.3,
            "traditional_show": 33.3,
            "Method": [
                "Mantis-8B-clip-llama3",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-clip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 316
        },
        {
            "Overall": 37.3,
            "calligraphy_painting": 35.1,
            "cultural_relic": 32.0,
            "food_clothes": 38.3,
            "historical_figure": 2.9,
            "scenery_building": 38.9,
            "sketch_reasoning": 75.6,
            "traditional_show": 34.8,
            "Method": [
                "Mantis-8B-siglip-llama3",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-siglip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 317
        },
        {
            "Overall": 38.6,
            "calligraphy_painting": 36.8,
            "cultural_relic": 33.0,
            "food_clothes": 30.4,
            "historical_figure": 17.1,
            "scenery_building": 45.3,
            "sketch_reasoning": 75.6,
            "traditional_show": 39.4,
            "Method": [
                "Mantis-8B-Idefics2",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-Idefics2"
            ],
            "Parameters": "8B",
            "Language Model": "Mistral-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 318
        },
        {
            "Overall": 55.7,
            "calligraphy_painting": 47.4,
            "cultural_relic": 44.3,
            "food_clothes": 56.5,
            "historical_figure": 25.7,
            "scenery_building": 65.3,
            "sketch_reasoning": 84.4,
            "traditional_show": 60.6,
            "Method": [
                "MiniCPM-V-2.6",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-siglip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "OpenBMB",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 319
        },
        {
            "Overall": 66.5,
            "calligraphy_painting": 64.9,
            "cultural_relic": 60.8,
            "food_clothes": 53.9,
            "historical_figure": 40.0,
            "scenery_building": 87.4,
            "sketch_reasoning": 88.9,
            "traditional_show": 66.7,
            "Method": [
                "GPT-4o (0806, detail-high)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 320
        },
        {
            "Overall": 30.0,
            "calligraphy_painting": 35.1,
            "cultural_relic": 30.9,
            "food_clothes": 27.0,
            "historical_figure": 2.9,
            "scenery_building": 29.5,
            "sketch_reasoning": 60.0,
            "traditional_show": 24.2,
            "Method": [
                "Llama-3-MixSense-v1.1",
                "https://huggingface.co/Zero-Vision/Llama-3-MixSenseV1_1"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "Florence-2-Large-FT",
            "Org": "ZeroVision",
            "Time": "2024/08/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 321
        },
        {
            "Overall": 54.5,
            "calligraphy_painting": 47.4,
            "cultural_relic": 56.7,
            "food_clothes": 53.0,
            "historical_figure": 37.1,
            "scenery_building": 52.6,
            "sketch_reasoning": 68.9,
            "traditional_show": 62.1,
            "Method": [
                "OmChat-v2.0-13B",
                "https://huggingface.co/omlab/omchat-v2.0-13B-single-beta_hf"
            ],
            "Parameters": "13B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "InternViT-6B",
            "Org": "Om AI",
            "Time": "2024/08/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 323
        },
        {
            "Overall": 41.8,
            "calligraphy_painting": 50.9,
            "cultural_relic": 42.3,
            "food_clothes": 40.9,
            "historical_figure": 5.7,
            "scenery_building": 40.0,
            "sketch_reasoning": 75.6,
            "traditional_show": 33.3,
            "Method": [
                "Parrot-7B",
                "https://huggingface.co/AIDC-AI/Parrot-7B"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Alibaba",
            "Time": "2024/08/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 324
        },
        {
            "Overall": 24.1,
            "calligraphy_painting": 33.3,
            "cultural_relic": 27.8,
            "food_clothes": 13.0,
            "historical_figure": 5.7,
            "scenery_building": 18.9,
            "sketch_reasoning": 53.3,
            "traditional_show": 27.3,
            "Method": [
                "VILA1.5-3B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-3b"
            ],
            "Parameters": "3B",
            "Language Model": "Sheared-LLaMA-2.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 325
        },
        {
            "Overall": 23.7,
            "calligraphy_painting": 22.8,
            "cultural_relic": 18.6,
            "food_clothes": 21.7,
            "historical_figure": 2.9,
            "scenery_building": 25.3,
            "sketch_reasoning": 51.1,
            "traditional_show": 25.8,
            "Method": [
                "Llama-3-VILA1.5-8B",
                "https://huggingface.co/Efficient-Large-Model/Llama-3-VILA1.5-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 326
        },
        {
            "Overall": 24.3,
            "calligraphy_painting": 22.8,
            "cultural_relic": 24.7,
            "food_clothes": 18.3,
            "historical_figure": 0.0,
            "scenery_building": 30.5,
            "sketch_reasoning": 44.4,
            "traditional_show": 25.8,
            "Method": [
                "VILA1.5-13B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-13b"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 327
        },
        {
            "Overall": 50.8,
            "calligraphy_painting": 59.6,
            "cultural_relic": 46.4,
            "food_clothes": 47.0,
            "historical_figure": 14.3,
            "scenery_building": 49.5,
            "sketch_reasoning": 80.0,
            "traditional_show": 57.6,
            "Method": [
                "VILA1.5-40B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-40b"
            ],
            "Parameters": "40B",
            "Language Model": "Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 328
        },
        {
            "Overall": 70.0,
            "calligraphy_painting": 73.7,
            "cultural_relic": 68.0,
            "food_clothes": 73.0,
            "historical_figure": 22.9,
            "scenery_building": 72.6,
            "sketch_reasoning": 91.1,
            "traditional_show": 71.2,
            "Org": "DataCanvas",
            "Time": "2024/08/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "MMAlaya2",
                "https://huggingface.co/DataCanvas/MMAlaya2"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "key": 329
        },
        {
            "Overall": 38.8,
            "calligraphy_painting": 36.8,
            "cultural_relic": 28.9,
            "food_clothes": 39.1,
            "historical_figure": 17.1,
            "scenery_building": 36.8,
            "sketch_reasoning": 71.1,
            "traditional_show": 47.0,
            "Org": "HuggingFace",
            "Time": "2024/08/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "Idefics3-8B-Llama3",
                "https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "key": 330
        },
        {
            "Overall": 27.6,
            "calligraphy_painting": 22.8,
            "cultural_relic": 21.6,
            "food_clothes": 23.5,
            "historical_figure": 25.7,
            "scenery_building": 28.4,
            "sketch_reasoning": 51.1,
            "traditional_show": 31.8,
            "Org": "Microsoft",
            "Time": "2024/08/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "Phi-3.5-Vision",
                "https://huggingface.co/microsoft/Phi-3.5-vision-instruct"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3.5",
            "Vision Model": "CLIP ViT-L/14",
            "key": 331
        },
        {
            "Overall": 17.8,
            "calligraphy_painting": 12.3,
            "cultural_relic": 12.4,
            "food_clothes": 27.8,
            "historical_figure": 0.0,
            "scenery_building": 10.5,
            "sketch_reasoning": 44.4,
            "traditional_show": 15.2,
            "Method": [
                "LLaVA-v1.5-7B",
                "https://arxiv.org/abs/2310.03744"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2023/10/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 186
        },
        {
            "Overall": 20.8,
            "calligraphy_painting": 15.8,
            "cultural_relic": 14.4,
            "food_clothes": 19.1,
            "historical_figure": 5.7,
            "scenery_building": 21.1,
            "sketch_reasoning": 64.4,
            "traditional_show": 15.2,
            "Method": [
                "LLaVA-v1.5-13B",
                "https://arxiv.org/abs/2310.03744"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2023/10/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 188
        },
        {
            "Overall": 33.5,
            "calligraphy_painting": 35.1,
            "cultural_relic": 32.0,
            "food_clothes": 25.2,
            "historical_figure": 2.9,
            "scenery_building": 36.8,
            "sketch_reasoning": 68.9,
            "traditional_show": 36.4,
            "Method": [
                "XGen-MM-Instruct-Interleave-v1.5",
                "https://huggingface.co/Salesforce/xgen-mm-phi3-mini-instruct-interleave-r-v1.5"
            ],
            "Parameters": "4.4B",
            "Language Model": "Phi-3",
            "Vision Model": "SigLIP-400M",
            "Org": "Salesforce",
            "Time": "2024/09/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 333
        },
        {
            "Overall": 32.7,
            "calligraphy_painting": 35.1,
            "cultural_relic": 27.8,
            "food_clothes": 32.2,
            "historical_figure": 2.9,
            "scenery_building": 33.7,
            "sketch_reasoning": 64.4,
            "traditional_show": 31.8,
            "Method": [
                "XGen-MM-Instruct-DPO-v1.5",
                "https://huggingface.co/Salesforce/xgen-mm-phi3-mini-instruct-dpo-r-v1.5"
            ],
            "Parameters": "4.4B",
            "Language Model": "Phi-3",
            "Vision Model": "SigLIP-400M",
            "Org": "Salesforce",
            "Time": "2024/09/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 334
        },
        {
            "Overall": 65.7,
            "calligraphy_painting": 70.2,
            "cultural_relic": 58.8,
            "food_clothes": 63.5,
            "historical_figure": 28.6,
            "scenery_building": 77.9,
            "sketch_reasoning": 86.7,
            "traditional_show": 63.6,
            "Method": [
                "Qwen2-VL-7B",
                "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/09/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 336
        },
        {
            "Overall": 53.7,
            "calligraphy_painting": 56.1,
            "cultural_relic": 48.5,
            "food_clothes": 53.0,
            "historical_figure": 17.1,
            "scenery_building": 62.1,
            "sketch_reasoning": 75.6,
            "traditional_show": 53.0,
            "Method": [
                "Qwen2-VL-2B",
                "https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct"
            ],
            "Parameters": "2B",
            "Language Model": "Qwen2-1.5B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/09/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 337
        },
        {
            "Overall": 11.8,
            "calligraphy_painting": 8.8,
            "cultural_relic": 16.5,
            "food_clothes": 7.8,
            "historical_figure": 5.7,
            "scenery_building": 6.3,
            "sketch_reasoning": 26.7,
            "traditional_show": 15.2,
            "Method": [
                "Mantis-8B-Fuyu",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-Fuyu"
            ],
            "Parameters": "8B",
            "Language Model": "Fuyu-8B",
            "Vision Model": "",
            "Org": "TIGER Lab",
            "Time": "2024/09/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 339
        },
        {
            "Overall": 25.3,
            "calligraphy_painting": 31.6,
            "cultural_relic": 19.6,
            "food_clothes": 19.1,
            "historical_figure": 5.7,
            "scenery_building": 28.4,
            "sketch_reasoning": 53.3,
            "traditional_show": 25.8,
            "Method": [
                "Slime-7B",
                "https://huggingface.co/yifanzhang114/SliME-vicuna-7B"
            ],
            "Parameters": "7B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 340
        },
        {
            "Overall": 27.6,
            "calligraphy_painting": 33.3,
            "cultural_relic": 21.6,
            "food_clothes": 27.8,
            "historical_figure": 0.0,
            "scenery_building": 27.4,
            "sketch_reasoning": 51.1,
            "traditional_show": 30.3,
            "Method": [
                "Slime-8B",
                "https://huggingface.co/yifanzhang114/SliME-Llama3-8B"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 341
        },
        {
            "Overall": 20.0,
            "calligraphy_painting": 26.3,
            "cultural_relic": 14.4,
            "food_clothes": 15.7,
            "historical_figure": 0.0,
            "scenery_building": 26.3,
            "sketch_reasoning": 44.4,
            "traditional_show": 15.2,
            "Method": [
                "Slime-13B",
                "https://huggingface.co/yifanzhang114/SliME-vicuna-13B"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 342
        },
        {
            "Overall": 37.6,
            "calligraphy_painting": 50.9,
            "cultural_relic": 34.0,
            "food_clothes": 31.3,
            "historical_figure": 17.1,
            "scenery_building": 38.9,
            "sketch_reasoning": 57.8,
            "traditional_show": 37.9,
            "Method": [
                "Pixtral-12B",
                "https://huggingface.co/mistralai/Pixtral-12B-2409"
            ],
            "Parameters": "13B",
            "Language Model": "Nemo-12B",
            "Vision Model": "ViT-400M",
            "Org": "Mistral AI",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 343
        },
        {
            "Overall": 52.4,
            "calligraphy_painting": 57.9,
            "cultural_relic": 48.5,
            "food_clothes": 55.7,
            "historical_figure": 5.7,
            "scenery_building": 56.8,
            "sketch_reasoning": 68.9,
            "traditional_show": 54.5,
            "Method": [
                "Gemini-1.5-Flash",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 344
        },
        {
            "Overall": 28.0,
            "calligraphy_painting": 31.6,
            "cultural_relic": 20.6,
            "food_clothes": 23.5,
            "historical_figure": 5.7,
            "scenery_building": 28.4,
            "sketch_reasoning": 53.3,
            "traditional_show": 37.9,
            "Method": [
                "LLaVA-OneVision-0.5B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-0.5b-ov"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 345
        },
        {
            "Overall": 54.9,
            "calligraphy_painting": 57.9,
            "cultural_relic": 49.5,
            "food_clothes": 59.1,
            "historical_figure": 34.3,
            "scenery_building": 51.6,
            "sketch_reasoning": 71.1,
            "traditional_show": 57.6,
            "Method": [
                "LLaVA-OneVision-7B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-7b-ov"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 346
        },
        {
            "Overall": 25.7,
            "calligraphy_painting": 26.3,
            "cultural_relic": 18.6,
            "food_clothes": 20.9,
            "historical_figure": 5.7,
            "scenery_building": 27.4,
            "sketch_reasoning": 48.9,
            "traditional_show": 36.4,
            "Method": [
                "LLaVA-OneVision-0.5B (SI)",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-0.5b-si"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 347
        },
        {
            "Overall": 44.7,
            "calligraphy_painting": 45.6,
            "cultural_relic": 39.2,
            "food_clothes": 41.7,
            "historical_figure": 28.6,
            "scenery_building": 47.4,
            "sketch_reasoning": 60.0,
            "traditional_show": 51.5,
            "Method": [
                "LLaVA-OneVision-7B (SI)",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-7b-si"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 348
        },
        {
            "Overall": 64.1,
            "calligraphy_painting": 68.4,
            "cultural_relic": 58.8,
            "food_clothes": 59.1,
            "historical_figure": 28.6,
            "scenery_building": 77.9,
            "sketch_reasoning": 82.2,
            "traditional_show": 63.6,
            "Method": [
                "Qwen-VL-Plus-0809",
                "https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-qianwen-vl-plus-api"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 349
        },
        {
            "Overall": 63.9,
            "calligraphy_painting": 75.4,
            "cultural_relic": 53.6,
            "food_clothes": 62.6,
            "historical_figure": 54.3,
            "scenery_building": 63.2,
            "sketch_reasoning": 82.2,
            "traditional_show": 65.2,
            "Method": [
                "LLaVA-OneVision-72B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-72b-ov"
            ],
            "Parameters": "73B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 351
        },
        {
            "Overall": 51.8,
            "calligraphy_painting": 59.6,
            "cultural_relic": 36.1,
            "food_clothes": 58.3,
            "historical_figure": 45.7,
            "scenery_building": 45.3,
            "sketch_reasoning": 71.1,
            "traditional_show": 56.1,
            "Method": [
                "Ovis1.6-Gemma2-9B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B"
            ],
            "Parameters": "10.2B",
            "Language Model": "Gemma2-9B-It",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/09/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 352
        },
        {
            "Overall": 28.4,
            "calligraphy_painting": 40.4,
            "cultural_relic": 21.6,
            "food_clothes": 22.6,
            "historical_figure": 5.7,
            "scenery_building": 24.2,
            "sketch_reasoning": 62.2,
            "traditional_show": 33.3,
            "Method": [
                "Eagle-X5-7B",
                "https://huggingface.co/NVEagle/Eagle-X5-7B"
            ],
            "Parameters": "9B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 353
        },
        {
            "Overall": 30.0,
            "calligraphy_painting": 36.8,
            "cultural_relic": 22.7,
            "food_clothes": 20.0,
            "historical_figure": 14.3,
            "scenery_building": 32.6,
            "sketch_reasoning": 68.9,
            "traditional_show": 30.3,
            "Method": [
                "Eagle-X5-13B",
                "https://huggingface.co/NVEagle/Eagle-X5-13B"
            ],
            "Parameters": "15B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 354
        },
        {
            "Overall": 9.2,
            "calligraphy_painting": 15.8,
            "cultural_relic": 5.2,
            "food_clothes": 8.7,
            "historical_figure": 0.0,
            "scenery_building": 9.5,
            "sketch_reasoning": 13.3,
            "traditional_show": 12.1,
            "Method": [
                "Moondream1",
                "https://huggingface.co/vikhyatk/moondream1"
            ],
            "Parameters": "1.9B",
            "Language Model": "SigLIP-400M",
            "Vision Model": "Phi-1.5",
            "Org": "Moondream",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 355
        },
        {
            "Overall": 77.3,
            "calligraphy_painting": 84.2,
            "cultural_relic": 86.6,
            "food_clothes": 78.3,
            "historical_figure": 11.4,
            "scenery_building": 81.1,
            "sketch_reasoning": 93.3,
            "traditional_show": 74.2,
            "Method": [
                "MiniMonkey",
                "https://huggingface.co/mx262/MiniMonkey"
            ],
            "Parameters": "2.2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "HUST",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 357
        },
        {
            "Overall": 54.7,
            "calligraphy_painting": 47.4,
            "cultural_relic": 54.6,
            "food_clothes": 49.6,
            "historical_figure": 25.7,
            "scenery_building": 66.3,
            "sketch_reasoning": 80.0,
            "traditional_show": 51.5,
            "Method": [
                "XinYuan-VL-2B-Instruct",
                "https://huggingface.co/Cylingo/Xinyuan-VL-2B"
            ],
            "Parameters": "2B",
            "Language Model": "Qwen2-1.5B",
            "Vision Model": "QwenViT",
            "Org": "Cylingo",
            "Time": "2024/09/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 359
        },
        {
            "Overall": 30.2,
            "calligraphy_painting": 26.3,
            "cultural_relic": 29.9,
            "food_clothes": 32.2,
            "historical_figure": 2.9,
            "scenery_building": 30.5,
            "sketch_reasoning": 46.7,
            "traditional_show": 33.3,
            "Method": [
                "Llama-3.2-11B-Vision-Instruct",
                "https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct"
            ],
            "Parameters": "11B",
            "Language Model": "Llama-3.1-8B",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/10/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 360
        },
        {
            "Overall": 74.3,
            "calligraphy_painting": 75.4,
            "cultural_relic": 69.1,
            "food_clothes": 67.0,
            "historical_figure": 51.4,
            "scenery_building": 95.8,
            "sketch_reasoning": 91.1,
            "traditional_show": 63.6,
            "Method": [
                "Step-1.5V",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "Step-1.5",
            "Vision Model": "stepencoder",
            "Org": "StepFun",
            "Time": "2024/10/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 322
        },
        {
            "Overall": 48.6,
            "calligraphy_painting": 56.1,
            "cultural_relic": 39.2,
            "food_clothes": 46.1,
            "historical_figure": 22.9,
            "scenery_building": 49.5,
            "sketch_reasoning": 75.6,
            "traditional_show": 54.5,
            "Method": [
                "POINTS-Yi-1.5-9B",
                "https://huggingface.co/WePOINTS/POINTS-Yi-1-5-9B-Chat"
            ],
            "Parameters": "9.5B",
            "Language Model": "Yi-1.5-9B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "WeChat",
            "Time": "2024/10/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTS-Yi-1.5-9B-Chat",
            "key": 362
        },
        {
            "Overall": 52.2,
            "calligraphy_painting": 61.4,
            "cultural_relic": 41.2,
            "food_clothes": 47.0,
            "historical_figure": 42.9,
            "scenery_building": 49.5,
            "sketch_reasoning": 77.8,
            "traditional_show": 60.6,
            "Method": [
                "POINTS-Qwen2.5-7B",
                "https://huggingface.co/WePOINTS/POINTS-Qwen-2-5-7B-Chat"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen-2.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "WeChat",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTS-Qwen-2.5-7B-Chat",
            "key": 363
        },
        {
            "Overall": 1.4,
            "calligraphy_painting": 3.5,
            "cultural_relic": 0.0,
            "food_clothes": 0.9,
            "historical_figure": 2.9,
            "scenery_building": 0.0,
            "sketch_reasoning": 2.2,
            "traditional_show": 3.0,
            "Method": [
                "Kosmos2",
                "https://huggingface.co/microsoft/kosmos-2-patch14-224"
            ],
            "Parameters": "1.7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Microsoft",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kosmos2",
            "key": 364
        },
        {
            "Overall": 54.1,
            "calligraphy_painting": 54.4,
            "cultural_relic": 49.5,
            "food_clothes": 44.3,
            "historical_figure": 20.0,
            "scenery_building": 70.5,
            "sketch_reasoning": 77.8,
            "traditional_show": 56.1,
            "Method": [
                "Llama-3.2-90B-Vision-Instruct",
                "https://huggingface.co/meta-llama/Llama-3.2-90B-Vision-Instruct"
            ],
            "Parameters": "88.6B",
            "Language Model": "Llama-3.1-70B",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Llama-3.2-90B-Vision-Instruct",
            "key": 365
        },
        {
            "Overall": 59.0,
            "calligraphy_painting": 59.6,
            "cultural_relic": 53.6,
            "food_clothes": 55.7,
            "historical_figure": 51.4,
            "scenery_building": 61.1,
            "sketch_reasoning": 82.2,
            "traditional_show": 57.6,
            "Method": [
                "NVLM-D-72B",
                "https://huggingface.co/nvidia/NVLM-D-72B"
            ],
            "Parameters": "79.4B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "InternViT-6B",
            "Org": "Nvidia",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "NVLM",
            "key": 366
        },
        {
            "Overall": 15.5,
            "calligraphy_painting": 22.8,
            "cultural_relic": 10.3,
            "food_clothes": 15.7,
            "historical_figure": 5.7,
            "scenery_building": 13.7,
            "sketch_reasoning": 26.7,
            "traditional_show": 16.7,
            "Method": [
                "Moondream2",
                "https://huggingface.co/vikhyatk/moondream2"
            ],
            "Parameters": "1.9B",
            "Language Model": "SigLIP-400M",
            "Vision Model": "Phi-1.5",
            "Org": "Moondream",
            "Time": "2024/10/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Moondream2",
            "key": 356
        },
        {
            "Overall": 36.7,
            "calligraphy_painting": 47.4,
            "cultural_relic": 29.9,
            "food_clothes": 29.6,
            "historical_figure": 20.0,
            "scenery_building": 29.5,
            "sketch_reasoning": 73.3,
            "traditional_show": 43.9,
            "Method": [
                "Molmo-7B-D",
                "https://huggingface.co/allenai/Molmo-7B-D-0924"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 361,
            "dir_name": "molmo-7B-D-0924"
        },
        {
            "Overall": 20.6,
            "calligraphy_painting": 24.6,
            "cultural_relic": 14.4,
            "food_clothes": 14.8,
            "historical_figure": 2.9,
            "scenery_building": 23.2,
            "sketch_reasoning": 53.3,
            "traditional_show": 19.7,
            "Method": [
                "Molmo-7B-O",
                "https://huggingface.co/allenai/Molmo-7B-O-0924"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 367,
            "dir_name": "molmo-7B-O-0924"
        },
        {
            "Overall": 17.5,
            "calligraphy_painting": 19.3,
            "cultural_relic": 15.5,
            "food_clothes": 16.5,
            "historical_figure": 2.9,
            "scenery_building": 10.5,
            "sketch_reasoning": 53.3,
            "traditional_show": 13.6,
            "Method": [
                "MolmoE-1B",
                "https://huggingface.co/allenai/MolmoE-1B-0924"
            ],
            "Parameters": "7.2B",
            "Language Model": "OLMoE-1B-7B-0924",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "molmoE-1B-0924",
            "key": 368
        },
        {
            "Overall": 22.2,
            "calligraphy_painting": 17.5,
            "cultural_relic": 26.8,
            "food_clothes": 13.0,
            "historical_figure": 0.0,
            "scenery_building": 22.1,
            "sketch_reasoning": 48.9,
            "traditional_show": 28.8,
            "Method": [
                "Janus-1.3B",
                "https://huggingface.co/deepseek-ai/Janus-1.3B"
            ],
            "Parameters": "2.1B",
            "Language Model": "DeepSeek-1B",
            "Vision Model": "SigLIP-400M",
            "Org": "deepseek",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Janus-1.3B",
            "key": 370
        },
        {
            "Overall": 39.2,
            "calligraphy_painting": 56.1,
            "cultural_relic": 33.0,
            "food_clothes": 24.3,
            "historical_figure": 25.7,
            "scenery_building": 35.8,
            "sketch_reasoning": 62.2,
            "traditional_show": 56.1,
            "Method": [
                "Vintern-3B-beta",
                "https://huggingface.co/5CD-AI/Vintern-3B-beta"
            ],
            "Parameters": "3.7B",
            "Language Model": "Qwen-2.5-3B",
            "Vision Model": "InternViT-300M",
            "Org": "Fifth Civil Defender",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Vintern-3B-beta",
            "key": 371
        },
        {
            "Overall": 36.3,
            "calligraphy_painting": 28.1,
            "cultural_relic": 33.0,
            "food_clothes": 41.7,
            "historical_figure": 8.6,
            "scenery_building": 28.4,
            "sketch_reasoning": 68.9,
            "traditional_show": 42.4,
            "Method": [
                "Ovis1.6-Llama3.2-3B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Llama3.2-3B"
            ],
            "Parameters": "4.1B",
            "Language Model": "Llama-3.2-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis1.6-Llama3.2-3B",
            "key": 372
        },
        {
            "Overall": 43.5,
            "calligraphy_painting": 43.9,
            "cultural_relic": 41.2,
            "food_clothes": 47.8,
            "historical_figure": 17.1,
            "scenery_building": 38.9,
            "sketch_reasoning": 68.9,
            "traditional_show": 42.4,
            "Method": [
                "Aquila-VL-2B",
                "https://huggingface.co/BAAI/Aquila-VL-2B-llava-qwen"
            ],
            "Parameters": "2.2B",
            "Language Model": "Qwen-2.5-1.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "BAAI",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Aquila-VL-2B",
            "key": 373
        },
        {
            "Overall": 69.8,
            "calligraphy_painting": 70.2,
            "cultural_relic": 61.9,
            "food_clothes": 57.4,
            "historical_figure": 60.0,
            "scenery_building": 88.4,
            "sketch_reasoning": 86.7,
            "traditional_show": 69.7,
            "Method": [
                "Qwen2-VL-72B",
                "https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct"
            ],
            "Parameters": "73.4B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/10/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2-VL-72B-Instruct",
            "key": 378
        },
        {
            "Overall": 74.3,
            "calligraphy_painting": 73.7,
            "cultural_relic": 72.2,
            "food_clothes": 73.0,
            "historical_figure": 34.3,
            "scenery_building": 89.5,
            "sketch_reasoning": 91.1,
            "traditional_show": 68.2,
            "Method": [
                "BlueLM-V-3B",
                "https://developers.vivo.com/product/ai/bluelm"
            ],
            "Parameters": "3B",
            "Language Model": "BlueLM-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "vivo",
            "Time": "2024/10/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 358,
            "dir_name": "BlueLM_V"
        },
        {
            "Overall": 30.2,
            "calligraphy_painting": 33.3,
            "cultural_relic": 24.7,
            "food_clothes": 26.1,
            "historical_figure": 0.0,
            "scenery_building": 29.5,
            "sketch_reasoning": 68.9,
            "traditional_show": 33.3,
            "Method": [
                "Falcon2-VLM-11B",
                "https://huggingface.co/tiiuae/falcon-11B-vlm"
            ],
            "Parameters": "11.4B",
            "Language Model": "Falcon2-11B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Technology Innovation Institute",
            "Time": "2024/10/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Falcon2-VLM-11B",
            "key": 380
        },
        {
            "Overall": 21.4,
            "calligraphy_painting": 17.5,
            "cultural_relic": 17.5,
            "food_clothes": 22.6,
            "historical_figure": 2.9,
            "scenery_building": 25.3,
            "sketch_reasoning": 24.4,
            "traditional_show": 30.3,
            "Method": [
                "H2OVL-800M",
                "https://huggingface.co/h2oai/h2ovl-mississippi-800m"
            ],
            "Parameters": "0.83B",
            "Language Model": "H2O-DANUBE3-500M",
            "Vision Model": "InternViT-300M",
            "Org": "H2O.ai",
            "Time": "2024/10/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "h2ovl-mississippi-1b",
            "key": 381
        },
        {
            "Overall": 23.7,
            "calligraphy_painting": 17.5,
            "cultural_relic": 21.6,
            "food_clothes": 20.0,
            "historical_figure": 0.0,
            "scenery_building": 28.4,
            "sketch_reasoning": 51.1,
            "traditional_show": 25.8,
            "Method": [
                "H2OVL-2B",
                "https://huggingface.co/h2oai/h2ovl-mississippi-2b"
            ],
            "Parameters": "2.2B",
            "Language Model": "H2O-DANUBE2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "H2O.ai",
            "Time": "2024/10/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "h2ovl-mississippi-2b",
            "key": 382
        },
        {
            "Overall": 70.6,
            "calligraphy_painting": 70.2,
            "cultural_relic": 62.9,
            "food_clothes": 57.4,
            "historical_figure": 54.3,
            "scenery_building": 91.6,
            "sketch_reasoning": 88.9,
            "traditional_show": 71.2,
            "Method": [
                "Qwen-VL-Max-0809",
                "https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-qianwen-vl-plus-api"
            ],
            "Parameters": "72B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/09/12",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "Qwen-VL-Max-0809",
            "key": 384
        },
        {
            "Overall": 56.1,
            "calligraphy_painting": 70.2,
            "cultural_relic": 44.3,
            "food_clothes": 48.7,
            "historical_figure": 22.9,
            "scenery_building": 74.7,
            "sketch_reasoning": 73.3,
            "traditional_show": 53.0,
            "Method": [
                "Claude3.5-Sonnet-20241022",
                "https://docs.anthropic.com/en/docs/build-with-claude/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/11/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Claude3-5V_Sonnet_20241022",
            "key": 376
        },
        {
            "Overall": 55.7,
            "calligraphy_painting": 63.2,
            "cultural_relic": 50.5,
            "food_clothes": 53.0,
            "historical_figure": 34.3,
            "scenery_building": 49.5,
            "sketch_reasoning": 84.4,
            "traditional_show": 62.1,
            "Method": [
                "RBDash-v1.5",
                "https://huggingface.co/RBDash-Team/RBDash-v1.5"
            ],
            "Parameters": "79B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "CLIP ViT-L/14\nInternViT-6B",
            "Org": "DLUT",
            "Time": "2024/11/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "RBDash_72b",
            "key": 388
        },
        {
            "Overall": 74.7,
            "calligraphy_painting": 87.7,
            "cultural_relic": 80.4,
            "food_clothes": 74.8,
            "historical_figure": 11.4,
            "scenery_building": 76.8,
            "sketch_reasoning": 84.4,
            "traditional_show": 78.8,
            "Method": [
                "InternVL2-8B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/11/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2-8B-MPO",
            "key": 390
        },
        {
            "Overall": 74.3,
            "calligraphy_painting": 87.7,
            "cultural_relic": 79.4,
            "food_clothes": 73.0,
            "historical_figure": 14.3,
            "scenery_building": 76.8,
            "sketch_reasoning": 86.7,
            "traditional_show": 77.3,
            "Method": [
                "InternVL2-8B-MPO-CoT",
                "https://huggingface.co/OpenGVLab/InternVL2-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/11/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2-8B-MPO-CoT",
            "key": 391
        },
        {
            "Overall": 42.7,
            "calligraphy_painting": 52.6,
            "cultural_relic": 34.0,
            "food_clothes": 51.3,
            "historical_figure": 11.4,
            "scenery_building": 33.7,
            "sketch_reasoning": 64.4,
            "traditional_show": 47.0,
            "Method": [
                "Eagle-X5-34B-Chat",
                "https://huggingface.co/NVEagle/Eagle-X5-34B-Chat"
            ],
            "Parameters": "36.8B",
            "Language Model": "Yi-34B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/11/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Eagle-X5-34B-Chat",
            "key": 395
        },
        {
            "Overall": 53.1,
            "calligraphy_painting": 63.2,
            "cultural_relic": 44.3,
            "food_clothes": 47.8,
            "historical_figure": 40.0,
            "scenery_building": 52.6,
            "sketch_reasoning": 75.6,
            "traditional_show": 59.1,
            "Method": [
                "Ovis1.6-Gemma2-27B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-27B"
            ],
            "Parameters": "28.9B",
            "Language Model": "Gemma2-27B",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/11/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis1.6-Gemma2-27B",
            "key": 396
        },
        {
            "Overall": 48.4,
            "calligraphy_painting": 50.9,
            "cultural_relic": 35.1,
            "food_clothes": 44.3,
            "historical_figure": 37.1,
            "scenery_building": 53.7,
            "sketch_reasoning": 73.3,
            "traditional_show": 54.5,
            "Method": [
                "Aria",
                "https://huggingface.co/rhymes-ai/Aria"
            ],
            "Parameters": "25.3B",
            "Language Model": "Aria-MoE",
            "Vision Model": "SigLIP-400M",
            "Org": "Rhymes AI",
            "Time": "2024/12/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Aria",
            "key": 401
        },
        {
            "Overall": 59.0,
            "calligraphy_painting": 64.9,
            "cultural_relic": 50.5,
            "food_clothes": 55.7,
            "historical_figure": 31.4,
            "scenery_building": 64.2,
            "sketch_reasoning": 84.4,
            "traditional_show": 62.1,
            "Method": [
                "POINTS1.5-Qwen2.5-7B",
                "https://huggingface.co/WePOINTS/POINTS-1-5-Qwen-2-5-7B-Chat"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen-2.5-7B",
            "Vision Model": "NaViT",
            "Org": "WeChat",
            "Time": "2024/12/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTSV15-Qwen-2.5-7B-Chat",
            "key": 403
        },
        {
            "Overall": 49.0,
            "calligraphy_painting": 52.6,
            "cultural_relic": 41.2,
            "food_clothes": 40.0,
            "historical_figure": 31.4,
            "scenery_building": 55.8,
            "sketch_reasoning": 75.6,
            "traditional_show": 54.5,
            "Method": [
                "BailingMM-Lite-1203",
                "https://zxb.alipay.com/llm/landing"
            ],
            "Parameters": "21B",
            "Language Model": "Bailing-20B",
            "Vision Model": "SigLIP-400M",
            "Org": "Ant Group",
            "Time": "2024/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "bailingMM-Lite",
            "key": 404
        },
        {
            "Overall": 62.5,
            "calligraphy_painting": 61.4,
            "cultural_relic": 48.5,
            "food_clothes": 54.8,
            "historical_figure": 34.3,
            "scenery_building": 86.3,
            "sketch_reasoning": 80.0,
            "traditional_show": 66.7,
            "Method": [
                "GLM-4v-Plus",
                "https://open.bigmodel.cn/dev/api/normal-model/glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GLM4V_PLUS",
            "key": 412
        },
        {
            "Overall": 72.7,
            "calligraphy_painting": 75.4,
            "cultural_relic": 68.0,
            "food_clothes": 71.3,
            "historical_figure": 45.7,
            "scenery_building": 90.5,
            "sketch_reasoning": 82.2,
            "traditional_show": 62.1,
            "Method": [
                "Step-1.5V-mini",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "StepFun",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Step1.5V-mini",
            "key": 413
        },
        {
            "Overall": 37.5,
            "calligraphy_painting": 24.6,
            "cultural_relic": 35.1,
            "food_clothes": 42.6,
            "historical_figure": 14.3,
            "scenery_building": 31.6,
            "sketch_reasoning": 48.9,
            "traditional_show": 56.1,
            "Method": [
                "abab6.5s",
                "https://www.minimaxi.com/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "MiniMax",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "abab6.5s",
            "key": 414
        },
        {
            "Overall": 59.8,
            "calligraphy_painting": 70.2,
            "cultural_relic": 59.8,
            "food_clothes": 55.7,
            "historical_figure": 40.0,
            "scenery_building": 54.7,
            "sketch_reasoning": 77.8,
            "traditional_show": 63.6,
            "Method": [
                "abab7-preview",
                "https://www.minimaxi.com/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "MiniMax",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "abab7-preview",
            "key": 415
        },
        {
            "Overall": 58.0,
            "calligraphy_painting": 61.4,
            "cultural_relic": 54.6,
            "food_clothes": 54.8,
            "historical_figure": 31.4,
            "scenery_building": 65.3,
            "sketch_reasoning": 71.1,
            "traditional_show": 60.6,
            "Method": [
                "Taiyi",
                "https://taiyi.megvii.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Megvii & StepFun",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Taiyi",
            "key": 383
        },
        {
            "Overall": 42.2,
            "calligraphy_painting": 40.4,
            "cultural_relic": 33.0,
            "food_clothes": 42.6,
            "historical_figure": 20.0,
            "scenery_building": 43.2,
            "sketch_reasoning": 68.9,
            "traditional_show": 48.5,
            "Method": [
                "SAIL-VL-2B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL-2B"
            ],
            "Parameters": "2.1B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "InternViT-300M",
            "Org": "ByteDance",
            "Time": "2024/12/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL-2B",
            "key": 424
        },
        {
            "Overall": 78.2,
            "calligraphy_painting": 84.2,
            "cultural_relic": 78.4,
            "food_clothes": 84.3,
            "historical_figure": 34.3,
            "scenery_building": 73.7,
            "sketch_reasoning": 91.1,
            "traditional_show": 83.3,
            "Method": [
                "InternVL2.5-1B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-1B-MPO"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen-2.5-0.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-1B-MPO",
            "key": 425
        },
        {
            "Overall": 86.1,
            "calligraphy_painting": 91.2,
            "cultural_relic": 92.8,
            "food_clothes": 90.4,
            "historical_figure": 8.6,
            "scenery_building": 92.6,
            "sketch_reasoning": 95.6,
            "traditional_show": 89.4,
            "Method": [
                "InternVL2.5-2B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-2B-MPO"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2.5-1.8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-2B-MPO",
            "key": 426
        },
        {
            "Overall": 82.2,
            "calligraphy_painting": 87.7,
            "cultural_relic": 87.6,
            "food_clothes": 87.0,
            "historical_figure": 11.4,
            "scenery_building": 87.4,
            "sketch_reasoning": 93.3,
            "traditional_show": 83.3,
            "Method": [
                "InternVL2.5-4B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-4B-MPO"
            ],
            "Parameters": "4B",
            "Language Model": "Qwen-2.5-3B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-4B-MPO",
            "key": 427
        },
        {
            "Overall": 82.9,
            "calligraphy_painting": 86.0,
            "cultural_relic": 87.6,
            "food_clothes": 88.7,
            "historical_figure": 34.3,
            "scenery_building": 87.4,
            "sketch_reasoning": 84.4,
            "traditional_show": 81.8,
            "Method": [
                "InternVL2.5-8B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-8B-MPO",
            "key": 428
        },
        {
            "Overall": 79.8,
            "calligraphy_painting": 89.5,
            "cultural_relic": 84.5,
            "food_clothes": 77.4,
            "historical_figure": 22.9,
            "scenery_building": 87.4,
            "sketch_reasoning": 95.6,
            "traditional_show": 77.3,
            "Method": [
                "InternVL2.5-26B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-26B-MPO"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2.5-20B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-26B-MPO",
            "key": 429
        },
        {
            "Overall": 75.9,
            "calligraphy_painting": 80.7,
            "cultural_relic": 81.4,
            "food_clothes": 78.3,
            "historical_figure": 20.0,
            "scenery_building": 74.7,
            "sketch_reasoning": 95.6,
            "traditional_show": 77.3,
            "Method": [
                "InternVL2.5-38B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-38B-MPO"
            ],
            "Parameters": "38B",
            "Language Model": "Qwen-2.5-32B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-38B-MPO",
            "key": 430
        },
        {
            "Overall": 86.9,
            "calligraphy_painting": 86.0,
            "cultural_relic": 89.7,
            "food_clothes": 87.8,
            "historical_figure": 40.0,
            "scenery_building": 94.7,
            "sketch_reasoning": 97.8,
            "traditional_show": 87.9,
            "Method": [
                "InternVL2.5-78B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-78B-MPO"
            ],
            "Parameters": "78B",
            "Language Model": "Qwen-2.5-72B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-78B-MPO",
            "key": 432
        },
        {
            "Overall": 40.0,
            "calligraphy_painting": 45.6,
            "cultural_relic": 39.2,
            "food_clothes": 33.0,
            "historical_figure": 2.9,
            "scenery_building": 40.0,
            "sketch_reasoning": 62.2,
            "traditional_show": 53.0,
            "Method": [
                "DeepSeek-VL2-Tiny",
                "https://huggingface.co/deepseek-ai/deepseek-vl2-tiny"
            ],
            "Parameters": "3.4B",
            "Language Model": "DeepSeekMoE-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2_tiny",
            "key": 433
        },
        {
            "Overall": 56.7,
            "calligraphy_painting": 68.4,
            "cultural_relic": 52.6,
            "food_clothes": 60.0,
            "historical_figure": 17.1,
            "scenery_building": 49.5,
            "sketch_reasoning": 80.0,
            "traditional_show": 62.1,
            "Method": [
                "DeepSeek-VL2-Small",
                "https://huggingface.co/deepseek-ai/deepseek-vl2-small"
            ],
            "Parameters": "16.1B",
            "Language Model": "DeepSeekMoE-16B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2_small",
            "key": 434
        },
        {
            "Overall": 53.1,
            "calligraphy_painting": 61.4,
            "cultural_relic": 48.5,
            "food_clothes": 53.0,
            "historical_figure": 37.1,
            "scenery_building": 48.4,
            "sketch_reasoning": 75.6,
            "traditional_show": 53.0,
            "Method": [
                "VARCO-VISION-14B",
                "https://huggingface.co/NCSOFT/VARCO-VISION-14B-HF"
            ],
            "Parameters": "15.2B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "SigLIP-400M",
            "Org": "NC Research",
            "Time": "2025/01/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "varco-vision-hf",
            "key": 437
        },
        {
            "Overall": 81.4,
            "calligraphy_painting": 80.7,
            "cultural_relic": 79.4,
            "food_clothes": 79.1,
            "historical_figure": 57.1,
            "scenery_building": 98.9,
            "sketch_reasoning": 88.9,
            "traditional_show": 71.2,
            "Method": [
                "Step-1o",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "StepFun",
            "Time": "2025/01/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Step1o",
            "key": 439
        },
        {
            "Overall": 72.0,
            "calligraphy_painting": 71.9,
            "cultural_relic": 68.0,
            "food_clothes": 62.6,
            "historical_figure": 51.4,
            "scenery_building": 96.8,
            "sketch_reasoning": 80.0,
            "traditional_show": 63.6,
            "Method": [
                "HunYuan-Standard-Vision",
                "https://cloud.tencent.com/document/product/1729/104753"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Tencent",
            "Time": "2025/01/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "HunYuan-Standard-Vision",
            "key": 440
        },
        {
            "Overall": 48.4,
            "calligraphy_painting": 61.4,
            "cultural_relic": 36.1,
            "food_clothes": 47.8,
            "historical_figure": 34.3,
            "scenery_building": 50.5,
            "sketch_reasoning": 71.1,
            "traditional_show": 45.5,
            "Method": [
                "Ross-Qwen2-7B",
                "https://huggingface.co/HaochenWang/ross-qwen2-7b"
            ],
            "Parameters": "8.2B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "CASIA",
            "Time": "2025/01/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "ross-qwen2-7b",
            "key": 441
        },
        {
            "Overall": 48.2,
            "calligraphy_painting": 56.1,
            "cultural_relic": 45.4,
            "food_clothes": 41.7,
            "historical_figure": 14.3,
            "scenery_building": 49.5,
            "sketch_reasoning": 71.1,
            "traditional_show": 57.6,
            "Method": [
                "VITA-1.5",
                "https://huggingface.co/VITA-MLLM/VITA-1.5"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "InternViT-300M",
            "Org": "NJU",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "vita_qwen2",
            "key": 442
        },
        {
            "Overall": 53.3,
            "calligraphy_painting": 52.6,
            "cultural_relic": 41.2,
            "food_clothes": 54.8,
            "historical_figure": 40.0,
            "scenery_building": 57.9,
            "sketch_reasoning": 80.0,
            "traditional_show": 51.5,
            "Method": [
                "MiniCPM-o-2.6",
                "https://huggingface.co/openbmb/MiniCPM-o-2_6"
            ],
            "Parameters": "8.67B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "OpenBMB",
            "Time": "2025/01/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MiniCPM-o-2_6",
            "key": 444
        },
        {
            "Overall": 52.2,
            "calligraphy_painting": 70.2,
            "cultural_relic": 40.2,
            "food_clothes": 40.9,
            "historical_figure": 37.1,
            "scenery_building": 58.9,
            "sketch_reasoning": 84.4,
            "traditional_show": 50.0,
            "Method": [
                "BailingMM-Pro-0120",
                "https://zxb.alipay.com/llm/landing"
            ],
            "Parameters": "81B",
            "Language Model": "Bailing-80B",
            "Vision Model": "SigLIP-400M",
            "Org": "Ant Group",
            "Time": "2025/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "BailingMM-Pro-0120",
            "key": 445
        },
        {
            "Overall": 71.0,
            "calligraphy_painting": 77.2,
            "cultural_relic": 69.1,
            "food_clothes": 64.3,
            "historical_figure": 37.1,
            "scenery_building": 81.1,
            "sketch_reasoning": 88.9,
            "traditional_show": 71.2,
            "Method": [
                "GLM-4v-Plus-20250111",
                "https://open.bigmodel.cn/dev/api/normal-model/glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2025/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GLM4V_PLUS_20250111",
            "key": 447
        },
        {
            "Overall": 19.0,
            "calligraphy_painting": 26.3,
            "cultural_relic": 20.6,
            "food_clothes": 13.0,
            "historical_figure": 0.0,
            "scenery_building": 17.9,
            "sketch_reasoning": 31.1,
            "traditional_show": 24.2,
            "Method": [
                "Emu3_chat",
                "https://huggingface.co/BAAI/Emu3-Chat"
            ],
            "Parameters": "8.49B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Beijing Academy of Artificial Intelligence",
            "Time": "2025/01/26",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "dir_name": "emu3_chat",
            "key": 448
        },
        {
            "Overall": 20.8,
            "calligraphy_painting": 21.1,
            "cultural_relic": 21.6,
            "food_clothes": 13.0,
            "historical_figure": 2.9,
            "scenery_building": 20.0,
            "sketch_reasoning": 53.3,
            "traditional_show": 21.2,
            "Method": [
                "SmolVLM-Instruct",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM",
            "key": 392
        },
        {
            "Overall": 19.6,
            "calligraphy_painting": 22.8,
            "cultural_relic": 18.6,
            "food_clothes": 12.2,
            "historical_figure": 0.0,
            "scenery_building": 21.1,
            "sketch_reasoning": 48.9,
            "traditional_show": 19.7,
            "Method": [
                "SmolVLM-Instruct-DPO",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct-DPO"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-DPO",
            "key": 393
        },
        {
            "Overall": 10.6,
            "calligraphy_painting": 12.3,
            "cultural_relic": 5.2,
            "food_clothes": 4.3,
            "historical_figure": 0.0,
            "scenery_building": 14.7,
            "sketch_reasoning": 35.6,
            "traditional_show": 10.6,
            "Method": [
                "SmolVLM-Synthetic",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Synthetic"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-Synthetic",
            "key": 394
        },
        {
            "Overall": 5.1,
            "calligraphy_painting": 3.5,
            "cultural_relic": 8.2,
            "food_clothes": 1.7,
            "historical_figure": 2.9,
            "scenery_building": 5.3,
            "sketch_reasoning": 8.9,
            "traditional_show": 6.1,
            "Method": [
                "SmolVLM-256M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct"
            ],
            "Parameters": "0.26B",
            "Language Model": "SmolLM2-135M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-256M",
            "key": 449
        },
        {
            "Overall": 10.6,
            "calligraphy_painting": 7.0,
            "cultural_relic": 11.3,
            "food_clothes": 9.6,
            "historical_figure": 2.9,
            "scenery_building": 4.2,
            "sketch_reasoning": 24.4,
            "traditional_show": 18.2,
            "Method": [
                "SmolVLM-500M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-500M-Instruct"
            ],
            "Parameters": "0.51B",
            "Language Model": "SmolLM2-360M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-500M",
            "key": 450
        },
        {
            "Overall": 33.3,
            "calligraphy_painting": 31.6,
            "cultural_relic": 28.9,
            "food_clothes": 34.8,
            "historical_figure": 8.6,
            "scenery_building": 28.4,
            "sketch_reasoning": 51.1,
            "traditional_show": 47.0,
            "Method": [
                "Janus-Pro-7B",
                "https://huggingface.co/deepseek-ai/Janus-Pro-7B"
            ],
            "Parameters": "7.42B",
            "Language Model": "DeepSeek-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "deepseek",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Janus-Pro-7B",
            "key": 454
        },
        {
            "Overall": 60.2,
            "calligraphy_painting": 66.7,
            "cultural_relic": 46.4,
            "food_clothes": 61.7,
            "historical_figure": 45.7,
            "scenery_building": 65.3,
            "sketch_reasoning": 84.4,
            "traditional_show": 56.1,
            "Method": [
                "Ola-7b",
                "https://huggingface.co/THUdyh/Ola-7b"
            ],
            "Parameters": "8.88B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "Oryx-ViT",
            "Org": "THU",
            "Time": "2025/02/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "ola",
            "key": 455
        },
        {
            "Overall": 37.5,
            "calligraphy_painting": 35.1,
            "cultural_relic": 34.0,
            "food_clothes": 33.9,
            "historical_figure": 11.4,
            "scenery_building": 30.5,
            "sketch_reasoning": 77.8,
            "traditional_show": 47.0,
            "Method": [
                "Ovis2-1B",
                "https://huggingface.co/AIDC-AI/Ovis2-1B"
            ],
            "Parameters": "1.27B",
            "Language Model": "Qwen2.5-0.5B",
            "Vision Model": "AIMv2 Large",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-1B",
            "key": 456
        },
        {
            "Overall": 44.7,
            "calligraphy_painting": 40.4,
            "cultural_relic": 37.1,
            "food_clothes": 42.6,
            "historical_figure": 14.3,
            "scenery_building": 45.3,
            "sketch_reasoning": 82.2,
            "traditional_show": 53.0,
            "Method": [
                "Ovis2-2B",
                "https://huggingface.co/AIDC-AI/Ovis2-2B"
            ],
            "Parameters": "2.46B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "AIMv2 Large",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-2B",
            "key": 457
        },
        {
            "Overall": 53.1,
            "calligraphy_painting": 45.6,
            "cultural_relic": 47.4,
            "food_clothes": 48.7,
            "historical_figure": 37.1,
            "scenery_building": 54.7,
            "sketch_reasoning": 86.7,
            "traditional_show": 59.1,
            "Method": [
                "Ovis2-4B",
                "https://huggingface.co/AIDC-AI/Ovis2-4B"
            ],
            "Parameters": "4.62B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-4B",
            "key": 458
        },
        {
            "Overall": 59.6,
            "calligraphy_painting": 63.2,
            "cultural_relic": 49.5,
            "food_clothes": 53.0,
            "historical_figure": 51.4,
            "scenery_building": 60.0,
            "sketch_reasoning": 93.3,
            "traditional_show": 63.6,
            "Method": [
                "Ovis2-8B",
                "https://huggingface.co/AIDC-AI/Ovis2-8B"
            ],
            "Parameters": "8.94B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-8B",
            "key": 459
        },
        {
            "Overall": 62.4,
            "calligraphy_painting": 66.7,
            "cultural_relic": 57.7,
            "food_clothes": 59.1,
            "historical_figure": 45.7,
            "scenery_building": 62.1,
            "sketch_reasoning": 91.1,
            "traditional_show": 60.6,
            "Method": [
                "Ovis2-16B",
                "https://huggingface.co/AIDC-AI/Ovis2-16B"
            ],
            "Parameters": "16.2B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-16B",
            "key": 460
        },
        {
            "Overall": 64.1,
            "calligraphy_painting": 66.7,
            "cultural_relic": 59.8,
            "food_clothes": 55.7,
            "historical_figure": 51.4,
            "scenery_building": 66.3,
            "sketch_reasoning": 93.3,
            "traditional_show": 66.7,
            "Method": [
                "Ovis2-34B",
                "https://huggingface.co/AIDC-AI/Ovis2-34B"
            ],
            "Parameters": "34.9B",
            "Language Model": "Qwen2.5-32B",
            "Vision Model": "AIMv2-1B",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-34B",
            "key": 461
        },
        {
            "Overall": 62.0,
            "calligraphy_painting": 63.2,
            "cultural_relic": 61.9,
            "food_clothes": 53.0,
            "historical_figure": 28.6,
            "scenery_building": 83.2,
            "sketch_reasoning": 73.3,
            "traditional_show": 56.1,
            "Method": [
                "Qwen2.5-VL-3B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct"
            ],
            "Parameters": "3.75B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-3B-Instruct",
            "key": 462
        },
        {
            "Overall": 59.2,
            "calligraphy_painting": 57.9,
            "cultural_relic": 56.7,
            "food_clothes": 54.8,
            "historical_figure": 25.7,
            "scenery_building": 83.2,
            "sketch_reasoning": 62.2,
            "traditional_show": 53.0,
            "Method": [
                "Qwen2.5-VL-7B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct"
            ],
            "Parameters": "8.29B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-7B-Instruct",
            "key": 463
        },
        {
            "Overall": 73.9,
            "calligraphy_painting": 71.9,
            "cultural_relic": 73.2,
            "food_clothes": 60.0,
            "historical_figure": 57.1,
            "scenery_building": 94.7,
            "sketch_reasoning": 86.7,
            "traditional_show": 71.2,
            "Method": [
                "Qwen2.5-VL-72B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct"
            ],
            "Parameters": "73.4B",
            "Language Model": "Qwen2.5-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-72B-Instruct",
            "key": 464
        },
        {
            "Overall": 55.1,
            "calligraphy_painting": 56.1,
            "cultural_relic": 49.5,
            "food_clothes": 56.5,
            "historical_figure": 2.9,
            "scenery_building": 67.4,
            "sketch_reasoning": 80.0,
            "traditional_show": 53.0,
            "Method": [
                "Claude3.7-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2025/02/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Claude3-7V_Sonnet",
            "key": 466
        },
        {
            "Overall": 60.2,
            "calligraphy_painting": 66.7,
            "cultural_relic": 52.6,
            "food_clothes": 55.7,
            "historical_figure": 20.0,
            "scenery_building": 72.6,
            "sketch_reasoning": 80.0,
            "traditional_show": 63.6,
            "Method": [
                "moonshot-v1-8k",
                "https://platform.moonshot.cn/docs/api/chat"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Moonshot AI",
            "Time": "2025/03/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "moonshot-v1-8k",
            "key": 467
        },
        {
            "Overall": 57.3,
            "calligraphy_painting": 70.2,
            "cultural_relic": 49.5,
            "food_clothes": 47.0,
            "historical_figure": 20.0,
            "scenery_building": 69.5,
            "sketch_reasoning": 80.0,
            "traditional_show": 62.1,
            "Method": [
                "grok-2-vision-1212",
                "https://docs.x.ai/docs/overview"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "xAI",
            "Time": "2025/03/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "grok-2-vision-1212",
            "key": 468
        },
        {
            "Overall": 55.7,
            "calligraphy_painting": 66.7,
            "cultural_relic": 49.5,
            "food_clothes": 47.0,
            "historical_figure": 31.4,
            "scenery_building": 57.9,
            "sketch_reasoning": 84.4,
            "traditional_show": 60.6,
            "Method": [
                "DeepSeek-VL2",
                "https://huggingface.co/deepseek-ai/deepseek-vl2"
            ],
            "Parameters": "27.5B",
            "Language Model": "DeepSeekMoE-27B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2",
            "key": 469
        },
        {
            "Overall": 23.1,
            "calligraphy_painting": 28.1,
            "cultural_relic": 18.6,
            "food_clothes": 17.4,
            "historical_figure": 0.0,
            "scenery_building": 20.0,
            "sketch_reasoning": 57.8,
            "traditional_show": 28.8,
            "Method": [
                "SmolVLM2",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct"
            ],
            "Parameters": "2.25B",
            "Language Model": "SmolLM2-1.7M",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2",
            "key": 470
        },
        {
            "Overall": 0.0,
            "calligraphy_painting": 0.0,
            "cultural_relic": 0.0,
            "food_clothes": 0.0,
            "historical_figure": 0.0,
            "scenery_building": 0.0,
            "sketch_reasoning": 0.0,
            "traditional_show": 0.0,
            "Method": [
                "SmolVLM2-256M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-256M-Video-Instruct"
            ],
            "Parameters": "0.26B",
            "Language Model": "SmolLM2-135M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2-256M",
            "key": 471
        },
        {
            "Overall": 13.3,
            "calligraphy_painting": 12.3,
            "cultural_relic": 17.5,
            "food_clothes": 10.4,
            "historical_figure": 5.7,
            "scenery_building": 6.3,
            "sketch_reasoning": 28.9,
            "traditional_show": 16.7,
            "Method": [
                "SmolVLM2-500M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
            ],
            "Parameters": "0.51B",
            "Language Model": "SmolLM2-360M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2-500M",
            "key": 472
        },
        {
            "Overall": 55.5,
            "calligraphy_painting": 54.4,
            "cultural_relic": 47.4,
            "food_clothes": 49.6,
            "historical_figure": 28.6,
            "scenery_building": 74.7,
            "sketch_reasoning": 77.8,
            "traditional_show": 50.0,
            "Method": [
                "Phi-4-MultiModal",
                "https://huggingface.co/microsoft/Phi-4-multimodal-instruct"
            ],
            "Parameters": "5.57B",
            "Language Model": "Phi-4-Mini",
            "Vision Model": "SigLIP-400M",
            "Org": "Microsoft",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Phi-4-Vision",
            "key": 473
        },
        {
            "Overall": 52.7,
            "calligraphy_painting": 57.9,
            "cultural_relic": 43.3,
            "food_clothes": 51.3,
            "historical_figure": 34.3,
            "scenery_building": 50.5,
            "sketch_reasoning": 73.3,
            "traditional_show": 63.6,
            "Method": [
                "MUG-U-7B",
                "https://github.com/Shopee-MUG/MUG-U"
            ],
            "Parameters": "7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Shopee",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MUG-U-7B",
            "key": 474
        },
        {
            "Overall": 36.9,
            "calligraphy_painting": 43.9,
            "cultural_relic": 29.9,
            "food_clothes": 37.4,
            "historical_figure": 8.6,
            "scenery_building": 38.9,
            "sketch_reasoning": 57.8,
            "traditional_show": 37.9,
            "Method": [
                "Gemma3-4B",
                "https://huggingface.co/google/gemma-3-4b-it"
            ],
            "Parameters": "4.3B",
            "Language Model": "Gemma3-4B",
            "Vision Model": "SigLIP-400M",
            "Org": "Google",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Gemma3-4B",
            "key": 475
        },
        {
            "Overall": 49.0,
            "calligraphy_painting": 57.9,
            "cultural_relic": 44.3,
            "food_clothes": 47.8,
            "historical_figure": 20.0,
            "scenery_building": 52.6,
            "sketch_reasoning": 64.4,
            "traditional_show": 50.0,
            "Method": [
                "Gemma3-12B",
                "https://huggingface.co/google/gemma-3-12b-it"
            ],
            "Parameters": "12.2B",
            "Language Model": "Gemma3-12B",
            "Vision Model": "SigLIP-400M",
            "Org": "Google",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Gemma3-12B",
            "key": 476
        },
        {
            "Overall": 25.7,
            "calligraphy_painting": 31.6,
            "cultural_relic": 27.8,
            "food_clothes": 20.9,
            "historical_figure": 11.4,
            "scenery_building": 29.5,
            "sketch_reasoning": 42.2,
            "traditional_show": 16.7,
            "Method": [
                "AKI-4B",
                "https://huggingface.co/Sony/AKI-4B-phi-3.5-mini"
            ],
            "Parameters": "4.33B",
            "Language Model": "Phi-3.5",
            "Vision Model": "SigLIP-400M",
            "Org": "Sony",
            "Time": "2025/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "AKI",
            "key": 478
        },
        {
            "Overall": 72.0,
            "calligraphy_painting": 71.9,
            "cultural_relic": 72.2,
            "food_clothes": 65.2,
            "historical_figure": 48.6,
            "scenery_building": 90.5,
            "sketch_reasoning": 82.2,
            "traditional_show": 62.1,
            "Method": [
                "Kimi-VL-A3B-Instruct",
                "https://huggingface.co/moonshotai/Kimi-VL-A3B-Instruct"
            ],
            "Parameters": "16.4B",
            "Language Model": "Moonlight-16B-A3B",
            "Vision Model": "MoonViT",
            "Org": "moonshot.ai",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kimi-VL-A3B-Instruct",
            "key": 483
        },
        {
            "Overall": 78.4,
            "calligraphy_painting": 87.7,
            "cultural_relic": 84.5,
            "food_clothes": 76.5,
            "historical_figure": 14.3,
            "scenery_building": 87.4,
            "sketch_reasoning": 91.1,
            "traditional_show": 77.3,
            "Method": [
                "InternVL3-1B",
                "https://huggingface.co/OpenGVLab/InternVL3-1B"
            ],
            "Parameters": "0.94B",
            "Language Model": "Qwen2.5-0.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-1B",
            "key": 484
        },
        {
            "Overall": 75.3,
            "calligraphy_painting": 89.5,
            "cultural_relic": 82.5,
            "food_clothes": 67.8,
            "historical_figure": 20.0,
            "scenery_building": 83.2,
            "sketch_reasoning": 86.7,
            "traditional_show": 75.8,
            "Method": [
                "InternVL3-2B",
                "https://huggingface.co/OpenGVLab/InternVL3-2B"
            ],
            "Parameters": "2.09B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-2B",
            "key": 485
        },
        {
            "Overall": 77.8,
            "calligraphy_painting": 91.2,
            "cultural_relic": 87.6,
            "food_clothes": 69.6,
            "historical_figure": 14.3,
            "scenery_building": 76.8,
            "sketch_reasoning": 93.3,
            "traditional_show": 90.9,
            "Method": [
                "InternVL3-8B",
                "https://huggingface.co/OpenGVLab/InternVL3-8B"
            ],
            "Parameters": "7.94B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-8B",
            "key": 486
        },
        {
            "Overall": 78.0,
            "calligraphy_painting": 89.5,
            "cultural_relic": 93.8,
            "food_clothes": 67.8,
            "historical_figure": 34.3,
            "scenery_building": 75.8,
            "sketch_reasoning": 91.1,
            "traditional_show": 80.3,
            "Method": [
                "InternVL3-9B",
                "https://huggingface.co/OpenGVLab/InternVL3-9B"
            ],
            "Parameters": "9.14B",
            "Language Model": "InternLM3-8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-9B",
            "key": 487
        },
        {
            "Overall": 77.1,
            "calligraphy_painting": 89.5,
            "cultural_relic": 85.6,
            "food_clothes": 68.7,
            "historical_figure": 37.1,
            "scenery_building": 70.5,
            "sketch_reasoning": 93.3,
            "traditional_show": 87.9,
            "Method": [
                "InternVL3-14B",
                "https://huggingface.co/OpenGVLab/InternVL3-14B"
            ],
            "Parameters": "15.1B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-14B",
            "key": 488
        },
        {
            "Overall": 80.6,
            "calligraphy_painting": 91.2,
            "cultural_relic": 91.8,
            "food_clothes": 76.5,
            "historical_figure": 25.7,
            "scenery_building": 76.8,
            "sketch_reasoning": 93.3,
            "traditional_show": 87.9,
            "Method": [
                "InternVL3-38B",
                "https://huggingface.co/OpenGVLab/InternVL3-38B"
            ],
            "Parameters": "38.4B",
            "Language Model": "Qwen2.5-32B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-38B",
            "key": 489
        },
        {
            "Overall": 83.5,
            "calligraphy_painting": 87.7,
            "cultural_relic": 95.9,
            "food_clothes": 72.2,
            "historical_figure": 54.3,
            "scenery_building": 84.2,
            "sketch_reasoning": 95.6,
            "traditional_show": 87.9,
            "Method": [
                "InternVL3-78B",
                "https://huggingface.co/OpenGVLab/InternVL3-78B"
            ],
            "Parameters": "78.4B",
            "Language Model": "Qwen2.5-72B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-78B",
            "key": 490
        },
        {
            "Overall": 73.5,
            "calligraphy_painting": 75.4,
            "cultural_relic": 71.1,
            "food_clothes": 64.3,
            "historical_figure": 45.7,
            "scenery_building": 94.7,
            "sketch_reasoning": 84.4,
            "traditional_show": 68.2,
            "Method": [
                "GPT-4.1-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-2025-04-14",
            "key": 491
        },
        {
            "Overall": 64.3,
            "calligraphy_painting": 66.7,
            "cultural_relic": 53.6,
            "food_clothes": 55.7,
            "historical_figure": 42.9,
            "scenery_building": 82.1,
            "sketch_reasoning": 84.4,
            "traditional_show": 65.2,
            "Method": [
                "GPT-4.1-mini-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-mini-2025-04-14",
            "key": 492
        },
        {
            "Overall": 31.2,
            "calligraphy_painting": 42.1,
            "cultural_relic": 29.9,
            "food_clothes": 21.7,
            "historical_figure": 11.4,
            "scenery_building": 32.6,
            "sketch_reasoning": 55.6,
            "traditional_show": 31.8,
            "Method": [
                "GPT-4.1-nano-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-nano-2025-04-14",
            "key": 493
        },
        {
            "Overall": 27.8,
            "calligraphy_painting": 28.1,
            "cultural_relic": 23.7,
            "food_clothes": 23.5,
            "historical_figure": 2.9,
            "scenery_building": 22.1,
            "sketch_reasoning": 64.4,
            "traditional_show": 37.9,
            "Method": [
                "granite-vision-3.2-2b",
                "https://huggingface.co/ibm-granite/granite-vision-3.2-2b"
            ],
            "Parameters": "2.98B",
            "Language Model": "granite-3.1-2b-instruct",
            "Vision Model": "SigLip",
            "Org": "IBM",
            "Time": "2025/06/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "granite_vision_3.2_2b",
            "key": 509
        },
        {
            "Overall": 24.9,
            "calligraphy_painting": 26.3,
            "cultural_relic": 24.7,
            "food_clothes": 20.0,
            "historical_figure": 0.0,
            "scenery_building": 24.2,
            "sketch_reasoning": 60.0,
            "traditional_show": 22.7,
            "Method": [
                "granite-vision-3.3-2b",
                "https://huggingface.co/ibm-granite/granite-vision-3.3-2b"
            ],
            "Parameters": "2.98B",
            "Language Model": "granite-3.1-2b-instruct",
            "Vision Model": "SigLIP2-400M",
            "Org": "IBM",
            "Time": "2025/06/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "granite_vision_3.3_2b",
            "key": 510
        }
    ],
    "MMBench_TEST_CN_Data": [
        {
            "Method": [
                "Qwen-VL-Plus Base",
                "https://github.com/QwenLM/Qwen-VL?tab=readme-ov-file#qwen-vl-plus"
            ],
            "Parameters": "",
            "Language Model": "QwenLM",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2023/12/15",
            "OpenSource": "No",
            "Verified": "No",
            "key": 36,
            "Overall": 82.7,
            "CP": 86.5,
            "FP-S": 85.9,
            "FP-C": 69.6,
            "AR": 86.1,
            "LR": 76.9,
            "RR": 83.4
        },
        {
            "Method": [
                "yuntiantianshu-3.0V",
                "https://www.intellif.com/"
            ],
            "Parameters": "",
            "Language Model": "tianshu-v3",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "yuntianlifei",
            "Time": "2024/05/13",
            "Verified": "No",
            "OpenSource": "No",
            "key": 226,
            "Overall": 82.4,
            "CP": 87.4,
            "FP-S": 89.2,
            "FP-C": 77.7,
            "AR": 78.1,
            "LR": 68.8,
            "RR": 81.0
        },
        {
            "Method": [
                "InternVL-Chat-V1.2-Plus",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "40B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/03/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 170,
            "Overall": 82.2,
            "CP": 85.0,
            "FP-S": 89.9,
            "FP-C": 79.8,
            "AR": 80.9,
            "LR": 69.9,
            "RR": 75.8
        },
        {
            "Method": [
                "GPT-4o (0513, detail-high)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 235,
            "Overall": 82.1,
            "CP": 87.6,
            "FP-S": 76.6,
            "FP-C": 83.4,
            "AR": 83.7,
            "LR": 78.0,
            "RR": 80.1
        },
        {
            "Method": [
                "GPT-4o (0513, detail-low)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 227,
            "Overall": 82.1,
            "CP": 87.6,
            "FP-S": 78.1,
            "FP-C": 83.8,
            "AR": 83.0,
            "LR": 75.1,
            "RR": 80.1
        },
        {
            "Method": [
                "InternVL-Chat-V1.2",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "40B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/02/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 169,
            "Overall": 81.2,
            "CP": 85.2,
            "FP-S": 86.7,
            "FP-C": 76.1,
            "AR": 83.7,
            "LR": 65.3,
            "RR": 77.3
        },
        {
            "Method": [
                "Skywork-VL",
                "https://github.com/SkyworkAI/Skywork"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Skywork AI",
            "Time": "2024/05/31",
            "Verified": "No",
            "OpenSource": "No",
            "key": 237,
            "Overall": 80.7,
            "CP": 85.0,
            "FP-S": 85.2,
            "FP-C": 76.5,
            "AR": 83.0,
            "LR": 64.7,
            "RR": 77.3
        },
        {
            "Method": [
                "InternVL-Chat-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/04/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 209,
            "Overall": 80.7,
            "CP": 85.7,
            "FP-S": 86.7,
            "FP-C": 72.5,
            "AR": 81.2,
            "LR": 68.2,
            "RR": 77.7
        },
        {
            "Method": [
                "TransCore-M",
                "https://github.com/PCIResearch/TransCore-M"
            ],
            "Parameters": "13.4B",
            "Language Model": "PCITransGPT-13B",
            "Vision Model": "CLIP ViT/L-14",
            "Org": "PCI Research",
            "Time": "2024/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 204,
            "Overall": 80.7,
            "CP": 85.7,
            "FP-S": 86.7,
            "FP-C": 72.5,
            "AR": 81.2,
            "LR": 68.2,
            "RR": 77.7
        },
        {
            "Method": [
                "GPT-4v (0409, detail-high)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 214,
            "Overall": 80.2,
            "CP": 84.4,
            "FP-S": 85.4,
            "FP-C": 72.1,
            "AR": 80.6,
            "LR": 72.8,
            "RR": 75.8
        },
        {
            "Method": [
                "GLM-4v",
                "https://open.bigmodel.cn/dev/api#glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2024/05/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 230,
            "Overall": 79.4,
            "CP": 85.9,
            "FP-S": 82.9,
            "FP-C": 71.3,
            "AR": 81.2,
            "LR": 65.3,
            "RR": 76.8
        },
        {
            "Method": [
                "InternLM-XComposer2",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 109,
            "Overall": 79.4,
            "CP": 86.3,
            "FP-S": 85.2,
            "FP-C": 71.7,
            "AR": 85.4,
            "LR": 58.4,
            "RR": 71.1
        },
        {
            "Method": [
                "GPT-4v (0409, detail-low)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 212,
            "Overall": 79.1,
            "CP": 83.1,
            "FP-S": 82.7,
            "FP-C": 72.5,
            "AR": 81.2,
            "LR": 71.7,
            "RR": 74.4
        },
        {
            "Method": [
                "LLaVA-Next-Yi-34B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "34.8B",
            "Language Model": "Yi-34B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 182,
            "Overall": 79.0,
            "CP": 84.4,
            "FP-S": 83.2,
            "FP-C": 72.1,
            "AR": 83.0,
            "LR": 66.5,
            "RR": 72.5
        },
        {
            "Method": [
                "InternLM-XComposer2-4KHD",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 241,
            "Overall": 78.1,
            "CP": 84.6,
            "FP-S": 82.4,
            "FP-C": 66.4,
            "AR": 83.3,
            "LR": 65.9,
            "RR": 72.0
        },
        {
            "Method": [
                "Marco-VL-Plus",
                ""
            ],
            "Parameters": "",
            "Vision Model": "CLIP ViT-L/14",
            "Language Model": "Marco-Chat",
            "Org": "Alibaba",
            "Time": "2024/04/09",
            "Verified": "No",
            "OpenSource": "No",
            "key": 192,
            "Overall": 77.9,
            "CP": 83.3,
            "FP-S": 81.7,
            "FP-C": 70.4,
            "AR": 81.9,
            "LR": 60.7,
            "RR": 76.3
        },
        {
            "Method": [
                "360VL-70B",
                "https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5"
            ],
            "Parameters": "70B",
            "Language Model": "Llama-3-70B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "QiHoo360",
            "Time": "2024/05/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 231,
            "Overall": 77.2,
            "CP": 80.5,
            "FP-S": 83.9,
            "FP-C": 70.0,
            "AR": 83.0,
            "LR": 55.5,
            "RR": 75.8
        },
        {
            "Method": [
                "WeMM",
                "https://github.com/scenarios/WeMM/tree/main"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "SigLip-400M",
            "Org": "WechatCV",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 238,
            "Overall": 76.8,
            "CP": 86.1,
            "FP-S": 80.7,
            "FP-C": 66.4,
            "AR": 79.9,
            "LR": 61.3,
            "RR": 69.7
        },
        {
            "Method": [
                "EmbodiedGPT",
                "https://github.com/OpenGVLab/EmbodiedGPT"
            ],
            "Parameters": "8B",
            "Language Model": "LLaMA-7B",
            "Vision Model": "EVA-G",
            "Org": "The University of Hong Kong",
            "Time": "2024/02/06",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 116,
            "Overall": 76.8,
            "CP": 84.2,
            "FP-S": 77.4,
            "FP-C": 72.5,
            "AR": 81.6,
            "LR": 52.0,
            "RR": 78.7
        },
        {
            "Method": [
                "Marco-VL-34B",
                ""
            ],
            "Parameters": "34.2B",
            "Language Model": "Marco-Chat-34B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Alibaba",
            "Time": "2023/12/14",
            "OpenSource": "No",
            "Verified": "No",
            "key": 31,
            "Overall": 76.8,
            "CP": 82.0,
            "FP-S": 82.9,
            "FP-C": 68.8,
            "AR": 80.6,
            "LR": 56.6,
            "RR": 74.4
        },
        {
            "Method": [
                "Bumblebee-14B",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "14B",
            "Language Model": "Qwen2-14B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Monolith Foundation",
            "Time": "2024/04/26",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 217,
            "Overall": 75.9,
            "CP": 84.8,
            "FP-S": 76.6,
            "FP-C": 66.4,
            "AR": 83.3,
            "LR": 55.5,
            "RR": 72.5
        },
        {
            "Method": [
                "Qwen-VL-Max",
                "https://huggingface.co/spaces/Qwen/Qwen-VL-Max"
            ],
            "Parameters": "",
            "Language Model": "QwenLM",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 113,
            "Overall": 75.7,
            "CP": 80.5,
            "FP-S": 82.2,
            "FP-C": 68.0,
            "AR": 77.8,
            "LR": 61.3,
            "RR": 70.6
        },
        {
            "Method": [
                "XVERSE-V-13B",
                "https://github.com/xverse-ai/XVERSE-V-13B"
            ],
            "Parameters": "13B",
            "Language Model": "XVERSE-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "XVERSE",
            "Time": "2024/05/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 223,
            "Overall": 74.6,
            "CP": 86.5,
            "FP-S": 76.6,
            "FP-C": 65.6,
            "AR": 79.9,
            "LR": 49.7,
            "RR": 68.2
        },
        {
            "Method": [
                "GPT-4v (1106, detail-low)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2023/12/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 210,
            "Overall": 74.4,
            "CP": 82.4,
            "FP-S": 69.8,
            "FP-C": 70.4,
            "AR": 78.8,
            "LR": 65.9,
            "RR": 71.1
        },
        {
            "Method": [
                "Gemini-1.0-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2023/12/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 78,
            "Overall": 74.3,
            "CP": 76.7,
            "FP-S": 78.4,
            "FP-C": 64.4,
            "AR": 79.5,
            "LR": 59.5,
            "RR": 77.7
        },
        {
            "Method": [
                "RekaFlash",
                "https://www.reka.ai"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Reka AI",
            "Time": "2024/05/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 229,
            "Overall": 74.1,
            "CP": 80.9,
            "FP-S": 75.4,
            "FP-C": 66.8,
            "AR": 78.5,
            "LR": 59.0,
            "RR": 71.6
        },
        {
            "Method": [
                "MiniCPM-Llama3-V2.5",
                "https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLip-400M",
            "Org": "OpenBMB",
            "Time": "2024/05/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 232,
            "Overall": 73.8,
            "CP": 81.6,
            "FP-S": 78.9,
            "FP-C": 62.3,
            "AR": 79.2,
            "LR": 62.4,
            "RR": 62.6
        },
        {
            "Method": [
                "LLaVA-InternLM2-20B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "20.2B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 69,
            "Overall": 73.7,
            "CP": 82.0,
            "FP-S": 75.9,
            "FP-C": 68.4,
            "AR": 75.7,
            "LR": 52.0,
            "RR": 72.0
        },
        {
            "Method": [
                "PureMM",
                "https://github.com/Q-MM/PureMM"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Tencent",
            "Time": "2024/01/16",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 93,
            "Overall": 72.6,
            "CP": 81.4,
            "FP-S": 75.9,
            "FP-C": 64.0,
            "AR": 79.5,
            "LR": 48.6,
            "RR": 67.8
        },
        {
            "key": 8,
            "Method": [
                "InternLM-XComposer",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM-7B",
            "Vision Model": "EVA-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/9/26",
            "Overall": 72.4,
            "AR": 79.5,
            "CP": 82.4,
            "FP-C": 56.3,
            "FP-S": 71.6,
            "LR": 44.5,
            "RR": 83.4,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Method": [
                "LLaVA-InternLM2-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "8.1B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 68,
            "Overall": 71.7,
            "CP": 79.2,
            "FP-S": 72.9,
            "FP-C": 63.2,
            "AR": 81.2,
            "LR": 46.2,
            "RR": 71.1
        },
        {
            "Method": [
                "DeepSeek-VL-7B",
                "https://github.com/deepseek-ai/DeepSeek-VL"
            ],
            "Parameters": "7.3B",
            "Language Model": "DeekSeek-7B",
            "Vision Model": "SAM-B\nSigLIP-L",
            "Org": "DeepSeek",
            "Time": "2024/03/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 174,
            "Overall": 71.4,
            "CP": 80.1,
            "FP-S": 73.9,
            "FP-C": 60.7,
            "AR": 78.1,
            "LR": 46.8,
            "RR": 70.6
        },
        {
            "Method": [
                "Marco-VL-6B",
                ""
            ],
            "Parameters": "6.2B",
            "Language Model": "Marco-Chat-6B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Alibaba",
            "Time": "2023/12/14",
            "OpenSource": "No",
            "Verified": "No",
            "key": 29,
            "Overall": 71.4,
            "CP": 79.4,
            "FP-S": 76.9,
            "FP-C": 62.3,
            "AR": 77.1,
            "LR": 48.0,
            "RR": 65.4
        },
        {
            "Method": [
                "Yi-VL-34B",
                "https://huggingface.co/01-ai/Yi-VL-34B"
            ],
            "Parameters": "34.6B",
            "Language Model": "Yi-34B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "01-AI",
            "Time": "2024/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 164,
            "Overall": 70.7,
            "CP": 78.6,
            "FP-S": 75.1,
            "FP-C": 62.3,
            "AR": 78.1,
            "LR": 48.6,
            "RR": 63.0
        },
        {
            "Method": [
                "Qwen-VL-Plus",
                "https://github.com/QwenLM/Qwen-VL?tab=readme-ov-file#qwen-vl-plus"
            ],
            "Parameters": "",
            "Language Model": "QwenLM",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/01/10",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 58,
            "Overall": 70.7,
            "CP": 76.9,
            "FP-S": 78.6,
            "FP-C": 57.5,
            "AR": 73.3,
            "LR": 54.3,
            "RR": 67.3
        },
        {
            "Method": [
                "Bumblebee-7B",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen-1.5-7B",
            "Vision Model": "SigLip-400M",
            "Org": "Monolith Foundation",
            "Time": "2024/05/07",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 218,
            "Overall": 70.5,
            "CP": 79.0,
            "FP-S": 71.6,
            "FP-C": 61.1,
            "AR": 79.9,
            "LR": 45.1,
            "RR": 68.7
        },
        {
            "Method": [
                "CatVision",
                ""
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "4paradigm.Inc",
            "Time": "2024/01/23",
            "Verified": "No",
            "OpenSource": "No",
            "key": 80,
            "Overall": 70.2,
            "CP": 77.5,
            "FP-S": 78.6,
            "FP-C": 63.2,
            "AR": 72.9,
            "LR": 45.7,
            "RR": 62.6
        },
        {
            "Method": [
                "InternVL-Chat-V1.1",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "19B",
            "Language Model": "LLaMA2-13B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/03/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 168,
            "Overall": 70.0,
            "CP": 80.5,
            "FP-S": 73.9,
            "FP-C": 61.5,
            "AR": 74.7,
            "LR": 45.1,
            "RR": 63.5
        },
        {
            "Method": [
                "CogVLM2-19B-Chat",
                "https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B"
            ],
            "Parameters": "19B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "EVA2-CLIP-E",
            "Org": "Zhipu AI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 234,
            "Overall": 69.8,
            "CP": 78.6,
            "FP-S": 71.9,
            "FP-C": 59.9,
            "AR": 73.6,
            "LR": 45.7,
            "RR": 73.0
        },
        {
            "Method": [
                "mPLUG-Owl2.1",
                ""
            ],
            "Parameters": "9.8B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-G/16",
            "Org": "Alibaba",
            "Time": "2024/01/26",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 90,
            "Overall": 69.7,
            "CP": 77.7,
            "FP-S": 76.1,
            "FP-C": 55.5,
            "AR": 74,
            "LR": 45.1,
            "RR": 71.1
        },
        {
            "Method": [
                "Marco-VL-13B",
                ""
            ],
            "Parameters": "13.2B",
            "Language Model": "Marco-Chat-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Alibaba",
            "Time": "2023/12/14",
            "OpenSource": "No",
            "Verified": "No",
            "key": 30,
            "Overall": 69.3,
            "CP": 81.2,
            "FP-S": 68.8,
            "FP-C": 60.7,
            "AR": 73.6,
            "LR": 48.0,
            "RR": 65.4
        },
        {
            "Method": [
                "IDEFICS2-8B",
                "https://huggingface.co/HuggingFaceM4/idefics2-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Mistral-7B",
            "Vision Model": "SigLip-400M",
            "Org": "Hugging Face",
            "Time": "2024/04/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 216,
            "Overall": 68.6,
            "CP": 77.9,
            "FP-S": 67.6,
            "FP-C": 62.3,
            "AR": 78.8,
            "LR": 46.8,
            "RR": 60.7
        },
        {
            "Method": [
                "LLaVA-Next-Vicuna-13B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 181,
            "Overall": 68.5,
            "CP": 79.2,
            "FP-S": 66.3,
            "FP-C": 60.3,
            "AR": 77.1,
            "LR": 46.2,
            "RR": 64.9
        },
        {
            "Method": [
                "InternLM-XComposer2-1.8B",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 240,
            "Overall": 68.4,
            "CP": 78.8,
            "FP-S": 68.6,
            "FP-C": 60.3,
            "AR": 75.3,
            "LR": 43.4,
            "RR": 65.9
        },
        {
            "Method": [
                "Monkey-Chat",
                "https://github.com/Yuliang-Liu/Monkey"
            ],
            "Parameters": "9.8B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-BigHuge",
            "Org": "Huazhong University of Science and Technology",
            "Time": "2024/01/16",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 74,
            "Overall": 67.5,
            "CP": 77.5,
            "FP-S": 69.1,
            "FP-C": 50.6,
            "AR": 78.8,
            "LR": 52.6,
            "RR": 58.8
        },
        {
            "Method": [
                "CodeFuse-VLM",
                "https://huggingface.co/codefuse-ai/CodeFuse-VLM-14B"
            ],
            "Parameters": "14B",
            "Language Model": "Qwen-14B",
            "Vision Model": "Qwen-VL Vision Encoder",
            "Org": "Ant Group",
            "Time": "2024/01/29",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 106,
            "Overall": 66.7,
            "CP": 74.7,
            "FP-S": 70.6,
            "FP-C": 51.4,
            "AR": 77.8,
            "LR": 43.9,
            "RR": 63.0
        },
        {
            "Method": [
                "LLaVA-InternLM-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "7.6B",
            "Language Model": "InternLM-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 51,
            "Overall": 66.7,
            "CP": 76.2,
            "FP-S": 65.1,
            "FP-C": 53.8,
            "AR": 76.4,
            "LR": 47.4,
            "RR": 66.4
        },
        {
            "Method": [
                "Yi-VL-6B",
                "https://huggingface.co/01-ai/Yi-VL-6B"
            ],
            "Parameters": "6.6B",
            "Language Model": "Yi-6B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "01-AI",
            "Time": "2024/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 163,
            "Overall": 66.6,
            "CP": 74.5,
            "FP-S": 71.6,
            "FP-C": 56.3,
            "AR": 75.3,
            "LR": 44.5,
            "RR": 57.8
        },
        {
            "Method": [
                "MiniCPM-V-2",
                "https://huggingface.co/openbmb/MiniCPM-V-2"
            ],
            "Parameters": "2.8B",
            "Vision Model": "SigLip-400M",
            "Language Model": "MiniCPM-2.4B",
            "Org": "OpenBMB",
            "Time": "2024/04/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 199,
            "Overall": 66.5,
            "CP": 73.0,
            "FP-S": 69.6,
            "FP-C": 55.1,
            "AR": 76.7,
            "LR": 43.4,
            "RR": 64.5
        },
        {
            "Method": [
                "ShareGPT4V-13B",
                "https://sharegpt4v.github.io"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 159,
            "Overall": 65.1,
            "CP": 76.9,
            "FP-S": 63.1,
            "FP-C": 57.5,
            "AR": 75.3,
            "LR": 42.2,
            "RR": 56.9
        },
        {
            "Method": [
                "RBDash-v1-13B",
                "https://huggingface.co/RBDash-Team/rbdash-v1-13b/tree/main"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "RBDash Team",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "No",
            "key": 54,
            "Overall": 65.0,
            "CP": 76.0,
            "FP-S": 64.6,
            "FP-C": 55.5,
            "AR": 76.4,
            "LR": 45.7,
            "RR": 52.6
        },
        {
            "Method": [
                "LLaVA-v1.5-13B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 53,
            "Overall": 64.7,
            "CP": 75.6,
            "FP-S": 64.3,
            "FP-C": 57.1,
            "AR": 74.3,
            "LR": 41.6,
            "RR": 56.4
        },
        {
            "Method": [
                "LLaVA-InternLM2-1.8B",
                "https://huggingface.co/StarCycle/llava-siglip-internlm2-1_8b-v1"
            ],
            "Parameters": "2.2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "SigLIP-400M",
            "Org": "Exponential Deep Space",
            "Time": "2024/03/10",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 141,
            "Overall": 64.5,
            "CP": 73.4,
            "FP-S": 61.8,
            "FP-C": 57.5,
            "AR": 77.8,
            "LR": 40.5,
            "RR": 59.2
        },
        {
            "Method": [
                "Claude3-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 187,
            "Overall": 64.2,
            "CP": 71.9,
            "FP-S": 63.8,
            "FP-C": 56.3,
            "AR": 71.5,
            "LR": 57.2,
            "RR": 52.6
        },
        {
            "Method": [
                "PaliGemma-3B-mix-448",
                "https://github.com/google-research/big_vision/blob/main/big_vision/configs/proj/paligemma/README.md"
            ],
            "Parameters": "3B",
            "Language Model": "Gemma-2B",
            "Vision Model": "SigLip-400M",
            "Org": "Google",
            "Time": "2024/05/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 228,
            "Overall": 63.6,
            "CP": 76.9,
            "FP-S": 64.3,
            "FP-C": 48.2,
            "AR": 73.6,
            "LR": 33.5,
            "RR": 62.1
        },
        {
            "Method": [
                "GPT-4v (1106, detail-high)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/04/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 211,
            "Overall": 63.3,
            "CP": 71.5,
            "FP-S": 60.1,
            "FP-C": 53.8,
            "AR": 71.2,
            "LR": 58.4,
            "RR": 55.9
        },
        {
            "Method": [
                "LLaVA-Next-Mistral-7B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "7.6B",
            "Language Model": "Mistral-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 180,
            "Overall": 63.3,
            "CP": 74.7,
            "FP-S": 60.6,
            "FP-C": 51.8,
            "AR": 75.7,
            "LR": 42.8,
            "RR": 56.4
        },
        {
            "Method": [
                "LLaVA-LLaMA-3-8B",
                "https://huggingface.co/xtuner/llava-llama-3-8b-v1_1"
            ],
            "Parameters": "8B",
            "Language Model": "LLaMA-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/05/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 221,
            "Overall": 63.2,
            "CP": 74.7,
            "FP-S": 61.8,
            "FP-C": 61.1,
            "AR": 74.0,
            "LR": 42.8,
            "RR": 45.0
        },
        {
            "Method": [
                "DeepSeek-VL-1.3B",
                "https://github.com/deepseek-ai/DeepSeek-VL"
            ],
            "Parameters": "2.0B",
            "Language Model": "DeekSeek-1B",
            "Vision Model": "SAM-B\nSigLIP-L",
            "Org": "DeepSeek",
            "Time": "2024/03/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 173,
            "Overall": 62.9,
            "CP": 76.9,
            "FP-S": 65.1,
            "FP-C": 51.0,
            "AR": 77.1,
            "LR": 30.1,
            "RR": 49.8
        },
        {
            "Method": [
                "LLaVA-DINOv2",
                "https://huggingface.co/StarCycle/llava-dinov2-internlm2-7b-v1"
            ],
            "Parameters": "8.1B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "DINOv2 ViT-L/13",
            "Org": "Exponential Deep Space",
            "Time": "2024/02/13",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 128,
            "Overall": 62.9,
            "CP": 75.6,
            "FP-S": 53.5,
            "FP-C": 57.9,
            "AR": 74.7,
            "LR": 40.5,
            "RR": 60.7
        },
        {
            "Method": [
                "MiniCPM-V",
                "https://huggingface.co/openbmb/MiniCPM-V"
            ],
            "Parameters": "3B",
            "Language Model": "MiniCPM-2.4B",
            "Vision Model": "SigLip-400M",
            "Org": "OpenBMB",
            "Time": "2024/02/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 123,
            "Overall": 62.6,
            "CP": 70.2,
            "FP-S": 67.6,
            "FP-C": 51.8,
            "AR": 69.8,
            "LR": 38.2,
            "RR": 58.8
        },
        {
            "Method": [
                "Phi-3-Vision",
                "https://huggingface.co/microsoft/Phi-3-vision-128k-instruct"
            ],
            "Parameters": "4.2B",
            "Language Model": "Phi-3",
            "Vision Model": "CLIP ViT/L-14",
            "Org": "Microsoft",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 233,
            "Overall": 62.4,
            "CP": 75.4,
            "FP-S": 57.5,
            "FP-C": 53.4,
            "AR": 72.9,
            "LR": 48.0,
            "RR": 50.7
        },
        {
            "Method": [
                "LLaVA-Next-Vicuna-7B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "7.1B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 179,
            "Overall": 62.3,
            "CP": 77.5,
            "FP-S": 59.3,
            "FP-C": 53.4,
            "AR": 75.7,
            "LR": 27.7,
            "RR": 54.5
        },
        {
            "Method": [
                "OmniLMM-12B",
                "https://huggingface.co/openbmb/OmniLMM-12B"
            ],
            "Parameters": "12B",
            "Language Model": "Zephyr-7B-β",
            "Vision Model": "EVA-02-5B",
            "Org": "OpenBMB",
            "Time": "2024/02/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 122,
            "Overall": 62.0,
            "CP": 70.7,
            "FP-S": 65.1,
            "FP-C": 51.4,
            "AR": 73.3,
            "LR": 37.6,
            "RR": 54.0
        },
        {
            "Method": [
                "LLaVA-v1.5-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 52,
            "Overall": 61.0,
            "CP": 73.2,
            "FP-S": 57.3,
            "FP-C": 59.1,
            "AR": 74.0,
            "LR": 30.6,
            "RR": 50.7
        },
        {
            "Method": [
                "ShareCaptioner",
                "https://huggingface.co/Lin-Chen/ShareCaptioner/"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM-7B",
            "Vision Model": "EVA-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 213,
            "Overall": 60.9,
            "CP": 65.5,
            "FP-S": 68.6,
            "FP-C": 53.0,
            "AR": 67.4,
            "LR": 31.8,
            "RR": 60.7
        },
        {
            "Method": [
                "SharedCaptioner",
                "https://huggingface.co/Lin-Chen/ShareCaptioner/"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM-7B",
            "Vision Model": "EVA-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/03",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 55,
            "Overall": 60.9,
            "CP": 65.5,
            "FP-S": 68.6,
            "FP-C": 53.0,
            "AR": 67.4,
            "LR": 31.8,
            "RR": 60.7
        },
        {
            "Method": [
                "ShareGPT4V-7B",
                "https://sharegpt4v.github.io"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 158,
            "Overall": 60.7,
            "CP": 74.3,
            "FP-S": 59.0,
            "FP-C": 50.6,
            "AR": 72.9,
            "LR": 30.6,
            "RR": 53.1
        },
        {
            "Method": [
                "mPLUG-Owl2",
                "https://github.com/X-PLUG/mPLUG-Owl/tree/main/mPLUG-Owl2"
            ],
            "Parameters": "8.2B",
            "Language Model": "LLaMA2 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "DAMO Academy",
            "Time": "2023/11/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 18,
            "Overall": 60.3,
            "CP": 70.4,
            "FP-S": 57.5,
            "FP-C": 51.0,
            "AR": 74.3,
            "LR": 36.4,
            "RR": 54.5
        },
        {
            "Method": [
                "RekaEdge",
                "https://www.reka.ai"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Reka AI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 236,
            "Overall": 59.9,
            "CP": 72.4,
            "FP-S": 59.0,
            "FP-C": 42.1,
            "AR": 69.1,
            "LR": 30.6,
            "RR": 66.4
        },
        {
            "Method": [
                "Claude3-Opus",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 188,
            "Overall": 59.2,
            "CP": 66.6,
            "FP-S": 55.8,
            "FP-C": 53.0,
            "AR": 68.4,
            "LR": 55.5,
            "RR": 47.4
        },
        {
            "Method": [
                "Sphinx",
                "https://github.com/Alpha-VLLM/LLaMA2-Accessory/tree/main/SPHINX"
            ],
            "Parameters": "16.5B",
            "Language Model": "LLaMA2 13B",
            "Vision Model": "CLIP ViT-L/14\nCLIP ConvNeXT\nConvNeXT-XXLarge\nDinov2-VIT-G/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/10/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 19,
            "Overall": 59.1,
            "CP": 71.9,
            "FP-S": 59.0,
            "FP-C": 53.8,
            "AR": 67.4,
            "LR": 30.6,
            "RR": 48.8
        },
        {
            "Method": [
                "MMAlaya",
                "https://huggingface.co/DataCanvas/MMAlaya"
            ],
            "Parameters": "7.8B",
            "Language Model": "Alaya-7B-Chat",
            "Vision Model": "EVA-G",
            "Org": "DataCanvas",
            "Time": "2024/01/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 111,
            "Overall": 58.6,
            "CP": 70.0,
            "FP-S": 54.0,
            "FP-C": 51.8,
            "AR": 72.6,
            "LR": 30.6,
            "RR": 53.6
        },
        {
            "Method": [
                "Claude3-Haiku",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 186,
            "Overall": 57.2,
            "CP": 69.2,
            "FP-S": 51.0,
            "FP-C": 44.9,
            "AR": 70.5,
            "LR": 48.0,
            "RR": 46.4
        },
        {
            "Method": [
                "Sphinx-V2",
                "https://github.com/Alpha-VLLM/LLaMA2-Accessory/tree/main/SPHINX"
            ],
            "Parameters": "16.5B",
            "Language Model": "LLaMA2 13B",
            "Vision Model": "CLIP ViT-L/14\nCLIP ConvNeXT\nConvNeXT-XXLarge\nDinov2-VIT-G/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/11/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 20,
            "Overall": 57.2,
            "CP": 71.5,
            "FP-S": 59.0,
            "FP-C": 48.2,
            "AR": 63.5,
            "LR": 39.9,
            "RR": 38.4
        },
        {
            "key": 7,
            "Method": [
                "Qwen-VL-Chat",
                "https://github.com/QwenLM/Qwen-VL"
            ],
            "Parameters": "9.6B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-G/16",
            "Org": "Alibaba",
            "Time": "2023/8/24",
            "Overall": 56.3,
            "CP": 64.7,
            "FP-S": 63.6,
            "FP-C": 43.7,
            "AR": 63.5,
            "LR": 35.3,
            "RR": 46.0,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Method": [
                "CogVLM-17B-Chat",
                "https://huggingface.co/THUDM/cogvlm-chat-hf"
            ],
            "Parameters": "17B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "EVA2-CLIP-E",
            "Org": "Zhipu AI",
            "Time": "2024/01/03",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 56,
            "Overall": 55.9,
            "CP": 72.6,
            "FP-S": 50.5,
            "FP-C": 45.3,
            "AR": 66.0,
            "LR": 31.2,
            "RR": 47.9
        },
        {
            "Method": [
                "Monkey",
                "https://github.com/Yuliang-Liu/Monkey"
            ],
            "Parameters": "9.8B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-BigHuge",
            "Org": "Huazhong University of Science and Technology",
            "Time": "2024/01/11",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 60,
            "Overall": 54.7,
            "CP": 65.7,
            "FP-S": 58.8,
            "FP-C": 33.2,
            "AR": 71.2,
            "LR": 31.8,
            "RR": 44.1
        },
        {
            "Method": [
                "Emu2_chat",
                "https://github.com/baaivision/Emu/tree/main/Emu2"
            ],
            "Parameters": "37B",
            "Language Model": "LLaMA-33B",
            "Vision Model": "EVA-02-CLIP-E-plus",
            "Org": "Beijing Academy of Artificial Intelligence",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 63,
            "Overall": 45.9,
            "CP": 61.0,
            "FP-S": 38.9,
            "FP-C": 37.7,
            "AR": 52.1,
            "LR": 22.5,
            "RR": 45.5
        },
        {
            "Method": [
                "LLaVA-v1-7B",
                "https://arxiv.org/abs/2304.08485"
            ],
            "Parameters": "7.2B",
            "Language Model": "LLaMA 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin-Madison",
            "Time": "2023/4/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 161,
            "Overall": 38.7,
            "CP": 55.0,
            "FP-S": 39.2,
            "FP-C": 23.9,
            "AR": 52.1,
            "LR": 9.8,
            "RR": 24.6
        },
        {
            "Method": [
                "IDEFICS-80B-Instruct",
                "https://huggingface.co/HuggingFaceM4/idefics-80b-instruct"
            ],
            "Parameters": "80B",
            "Language Model": "LLaMA65B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "Hugging Face",
            "Time": "2023/7/25",
            "key": 13,
            "Overall": 38.1,
            "CP": 51.2,
            "FP-S": 29.1,
            "FP-C": 36.0,
            "AR": 49.0,
            "LR": 20.8,
            "RR": 27.5,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Method": [
                "VisualGLM",
                "https://github.com/THUDM/VisualGLM-6B"
            ],
            "Parameters": "8B",
            "Language Model": "ChatGLM 6B",
            "Vision Model": "EVA-CLIP",
            "Org": "Tsinghua University",
            "Time": "2023/5/17",
            "key": 24,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Overall": 35.5,
            "CP": 47.5,
            "FP-S": 34.4,
            "FP-C": 19.0,
            "AR": 42.7,
            "LR": 24.3,
            "RR": 29.9
        },
        {
            "Method": [
                "PandaGPT-13B",
                "https://arxiv.org/abs/2305.16355"
            ],
            "Parameters": "14B",
            "Language Model": "Vicuna 13B",
            "Vision Model": "ImageBind ViT-H/14",
            "Org": "Tencent AI Lab",
            "Time": "2023/5/25",
            "key": 10,
            "Overall": 32.0,
            "CP": 47.1,
            "FP-S": 20.4,
            "FP-C": 11.3,
            "AR": 50.3,
            "LR": 15.0,
            "RR": 33.2,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Method": [
                "IDEFICS-9B-Instruct",
                "https://huggingface.co/HuggingFaceM4/idefics-9b-instruct"
            ],
            "Parameters": "9B",
            "Language Model": "LLaMA 7B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "Hugging Face",
            "Time": "2023/7/25",
            "key": 12,
            "Overall": 25.2,
            "CP": 39.4,
            "FP-S": 18.3,
            "FP-C": 17.0,
            "AR": 35.4,
            "LR": 6.4,
            "RR": 17.5,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "key": 3,
            "Method": [
                "InstructBLIP-7B",
                "https://arxiv.org/abs/2305.06500"
            ],
            "Parameters": "8B",
            "Language Model": "Vicuna 7B",
            "Vision Model": "EVA-G",
            "Org": "Salesforce Research",
            "Time": "2023/5/11",
            "Overall": 23.9,
            "CP": 30.8,
            "FP-S": 20.9,
            "FP-C": 15.0,
            "AR": 38.5,
            "LR": 9.2,
            "RR": 16.6,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Method": [
                "OpenFlamingo v2",
                "https://github.com/mlfoundations/open_flamingo"
            ],
            "Parameters": "9B",
            "Language Model": "MPT 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "The University of Washington",
            "Time": "2023/6/28",
            "key": 11,
            "Overall": 14.4,
            "CP": 18.8,
            "FP-S": 10.6,
            "FP-C": 8.5,
            "AR": 23.6,
            "LR": 13.3,
            "RR": 7.1,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "key": 2,
            "Method": [
                "MiniGPT-4-v1-7B",
                "https://arxiv.org/abs/2304.10592"
            ],
            "Parameters": "8B",
            "Language Model": "Vicuna 7B",
            "Vision Model": "EVA-G",
            "Org": "King Abdullah University of Science and Technology",
            "Time": "2023/4/20",
            "Overall": 11.9,
            "CP": 10.9,
            "FP-S": 14.6,
            "FP-C": 6.5,
            "AR": 19.4,
            "LR": 11.6,
            "RR": 5.7,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "key": 9,
            "Method": [
                "Qwen-VL",
                "https://github.com/QwenLM/Qwen-VL"
            ],
            "Parameters": "9.6B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-G/16",
            "Org": "Alibaba",
            "Time": "2023/8/24",
            "Overall": 7.8,
            "AR": 14.2,
            "CP": 7.5,
            "FP-C": 7.3,
            "FP-S": 8.0,
            "LR": 3.5,
            "RR": 3.8,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Method": [
                "MiniGPT-4-v2",
                "https://minigpt-v2.github.io"
            ],
            "Parameters": "8B",
            "Language Model": "LLaMA2 13B",
            "Vision Model": "EVA-G",
            "Org": "King Abdullah University of Science and Technology",
            "Time": "2023/10/27",
            "key": 17,
            "Overall": 4.7,
            "CP": 2.4,
            "FP-S": 3.0,
            "FP-C": 2.0,
            "AR": 14.6,
            "LR": 2.9,
            "RR": 3.8,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "key": 1,
            "Method": [
                "OpenFlamingo",
                "https://github.com/mlfoundations/open_flamingo"
            ],
            "Parameters": "9B",
            "Language Model": "LLaMA 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "The University of Washington",
            "Time": "2023/3/29",
            "Overall": 1.7,
            "CP": 1.3,
            "FP-S": 1.5,
            "FP-C": 0.8,
            "AR": 4.5,
            "LR": 1.7,
            "RR": 0.0,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 66.0,
            "AR": 75.3,
            "CP": 76.9,
            "FP-C": 55.1,
            "FP-S": 67.6,
            "LR": 41.0,
            "RR": 59.2,
            "action_recognition": 94.3,
            "attribute_comparison": 43.6,
            "attribute_recognition": 76.8,
            "celebrity_recognition": 66.1,
            "function_reasoning": 75.5,
            "future_prediction": 56.9,
            "identity_reasoning": 92.7,
            "image_emotion": 73.5,
            "image_quality": 48.2,
            "image_scene": 89.9,
            "image_style": 69.4,
            "image_topic": 96.5,
            "nature_relation": 55.6,
            "object_localization": 42.3,
            "ocr": 92.2,
            "physical_property_reasoning": 61.0,
            "physical_relation": 32.7,
            "social_relation": 80.8,
            "spatial_relationship": 23.5,
            "structuralized_imagetext_understanding": 29.7,
            "Method": [
                "Mini-InternVL-Chat-2B-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 277
        },
        {
            "Overall": 70.0,
            "AR": 75.7,
            "CP": 78.4,
            "FP-C": 63.6,
            "FP-S": 68.8,
            "LR": 54.9,
            "RR": 65.4,
            "action_recognition": 90.9,
            "attribute_comparison": 69.2,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 53.4,
            "function_reasoning": 79.2,
            "future_prediction": 68.1,
            "identity_reasoning": 95.1,
            "image_emotion": 74.7,
            "image_quality": 61.2,
            "image_scene": 89.1,
            "image_style": 65.9,
            "image_topic": 95.3,
            "nature_relation": 58.0,
            "object_localization": 58.7,
            "ocr": 92.2,
            "physical_property_reasoning": 56.0,
            "physical_relation": 46.2,
            "social_relation": 85.9,
            "spatial_relationship": 28.4,
            "structuralized_imagetext_understanding": 45.5,
            "Method": [
                "Mini-InternVL-Chat-4B-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 278
        },
        {
            "Overall": 73.8,
            "AR": 69.4,
            "CP": 80.5,
            "FP-C": 68.8,
            "FP-S": 79.9,
            "LR": 60.7,
            "RR": 69.7,
            "action_recognition": 80.7,
            "attribute_comparison": 71.8,
            "attribute_recognition": 80.8,
            "celebrity_recognition": 90.7,
            "function_reasoning": 75.5,
            "future_prediction": 63.9,
            "identity_reasoning": 84.1,
            "image_emotion": 72.3,
            "image_quality": 69.4,
            "image_scene": 87.6,
            "image_style": 78.8,
            "image_topic": 90.6,
            "nature_relation": 82.7,
            "object_localization": 58.7,
            "ocr": 90.9,
            "physical_property_reasoning": 51.0,
            "physical_relation": 46.2,
            "social_relation": 71.8,
            "spatial_relationship": 53.1,
            "structuralized_imagetext_understanding": 58.4,
            "Method": [
                "Gemini-1.5-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 279
        },
        {
            "Overall": 76.5,
            "AR": 83.0,
            "CP": 83.9,
            "FP-C": 62.8,
            "FP-S": 79.4,
            "LR": 59.0,
            "RR": 76.3,
            "action_recognition": 94.3,
            "attribute_comparison": 61.5,
            "attribute_recognition": 83.8,
            "celebrity_recognition": 79.7,
            "function_reasoning": 87.7,
            "future_prediction": 75.0,
            "identity_reasoning": 100.0,
            "image_emotion": 74.7,
            "image_quality": 67.1,
            "image_scene": 96.9,
            "image_style": 78.8,
            "image_topic": 95.3,
            "nature_relation": 81.5,
            "object_localization": 65.4,
            "ocr": 92.2,
            "physical_property_reasoning": 64.0,
            "physical_relation": 51.9,
            "social_relation": 87.2,
            "spatial_relationship": 29.6,
            "structuralized_imagetext_understanding": 47.5,
            "Method": [
                "Bumblebee-7B-v1.5",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLip-400M",
            "Org": "Monolith Foundation",
            "Time": "2024/06/12",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 280
        },
        {
            "Overall": 70.4,
            "AR": 74.7,
            "CP": 72.4,
            "FP-C": 68.4,
            "FP-S": 79.9,
            "LR": 60.7,
            "RR": 52.6,
            "action_recognition": 93.2,
            "attribute_comparison": 65.4,
            "attribute_recognition": 81.8,
            "celebrity_recognition": 89.8,
            "function_reasoning": 81.1,
            "future_prediction": 65.3,
            "identity_reasoning": 89.0,
            "image_emotion": 65.1,
            "image_quality": 68.2,
            "image_scene": 76.0,
            "image_style": 63.5,
            "image_topic": 87.1,
            "nature_relation": 43.2,
            "object_localization": 59.6,
            "ocr": 89.6,
            "physical_property_reasoning": 56.0,
            "physical_relation": 57.7,
            "social_relation": 59.0,
            "spatial_relationship": 44.4,
            "structuralized_imagetext_understanding": 57.4,
            "Method": [
                "GLM-4v-9B",
                "https://huggingface.co/THUDM/glm-4v-9b"
            ],
            "Parameters": "9B",
            "Language Model": "GLM-4-9B",
            "Vision Model": "EVA-02-5B",
            "Org": "Zhipu AI",
            "Time": "2024/06/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 281
        },
        {
            "Overall": 72.6,
            "AR": 80.2,
            "CP": 82.0,
            "FP-C": 60.7,
            "FP-S": 75.6,
            "LR": 46.8,
            "RR": 71.1,
            "action_recognition": 94.3,
            "attribute_comparison": 60.3,
            "attribute_recognition": 80.8,
            "celebrity_recognition": 78.8,
            "function_reasoning": 85.8,
            "future_prediction": 65.3,
            "identity_reasoning": 96.3,
            "image_emotion": 78.3,
            "image_quality": 63.5,
            "image_scene": 94.6,
            "image_style": 70.6,
            "image_topic": 96.5,
            "nature_relation": 76.5,
            "object_localization": 57.7,
            "ocr": 88.3,
            "physical_property_reasoning": 61.0,
            "physical_relation": 48.1,
            "social_relation": 80.8,
            "spatial_relationship": 24.7,
            "structuralized_imagetext_understanding": 33.7,
            "Method": [
                "LLaVA-InternLM2-7B (QMoSLoRA)",
                "https://arxiv.org/abs/2406.11909"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "HKU",
            "Time": "2024/06/23",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 283
        },
        {
            "Overall": 80.7,
            "AR": 82.6,
            "CP": 85.4,
            "FP-C": 77.3,
            "FP-S": 81.9,
            "LR": 74.0,
            "RR": 74.4,
            "action_recognition": 87.5,
            "attribute_comparison": 76.9,
            "attribute_recognition": 85.9,
            "celebrity_recognition": 76.3,
            "function_reasoning": 90.6,
            "future_prediction": 63.9,
            "identity_reasoning": 97.6,
            "image_emotion": 68.7,
            "image_quality": 80.0,
            "image_scene": 93.0,
            "image_style": 84.7,
            "image_topic": 96.5,
            "nature_relation": 88.9,
            "object_localization": 76.0,
            "ocr": 93.5,
            "physical_property_reasoning": 62.0,
            "physical_relation": 46.2,
            "social_relation": 78.2,
            "spatial_relationship": 66.7,
            "structuralized_imagetext_understanding": 81.2,
            "Method": [
                "Claude3.5-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/06/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 284
        },
        {
            "Overall": 81.9,
            "AR": 84.0,
            "CP": 87.2,
            "FP-C": 72.5,
            "FP-S": 87.7,
            "LR": 69.4,
            "RR": 77.7,
            "action_recognition": 95.5,
            "attribute_comparison": 76.9,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 85.6,
            "function_reasoning": 85.8,
            "future_prediction": 77.8,
            "identity_reasoning": 96.3,
            "image_emotion": 79.5,
            "image_quality": 84.7,
            "image_scene": 94.6,
            "image_style": 76.5,
            "image_topic": 96.5,
            "nature_relation": 80.2,
            "object_localization": 76.9,
            "ocr": 94.8,
            "physical_property_reasoning": 72.0,
            "physical_relation": 67.3,
            "social_relation": 82.1,
            "spatial_relationship": 43.2,
            "structuralized_imagetext_understanding": 63.4,
            "Method": [
                "CongRong",
                "https://mllm.cloudwalk.com/web/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "CloudWalk",
            "Time": "2024/06/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 285
        },
        {
            "Overall": 76.8,
            "AR": 81.6,
            "CP": 85.4,
            "FP-C": 64.8,
            "FP-S": 78.1,
            "LR": 61.3,
            "RR": 75.4,
            "action_recognition": 94.3,
            "attribute_comparison": 61.5,
            "attribute_recognition": 83.8,
            "celebrity_recognition": 80.5,
            "function_reasoning": 88.7,
            "future_prediction": 76.4,
            "identity_reasoning": 98.8,
            "image_emotion": 81.9,
            "image_quality": 75.3,
            "image_scene": 93.8,
            "image_style": 77.6,
            "image_topic": 94.1,
            "nature_relation": 82.7,
            "object_localization": 59.6,
            "ocr": 92.2,
            "physical_property_reasoning": 60.0,
            "physical_relation": 51.9,
            "social_relation": 83.3,
            "spatial_relationship": 35.8,
            "structuralized_imagetext_understanding": 50.5,
            "Method": [
                "Bumblebee-7B-v1.6",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Monolith Foundation",
            "Time": "2024/06/27",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 286
        },
        {
            "Overall": 82.3,
            "AR": 81.6,
            "CP": 85.0,
            "FP-C": 77.7,
            "FP-S": 85.2,
            "LR": 68.8,
            "RR": 88.6,
            "action_recognition": 96.6,
            "attribute_comparison": 83.3,
            "attribute_recognition": 91.9,
            "celebrity_recognition": 90.7,
            "function_reasoning": 86.8,
            "future_prediction": 81.9,
            "identity_reasoning": 97.6,
            "image_emotion": 71.1,
            "image_quality": 82.4,
            "image_scene": 92.2,
            "image_style": 80.0,
            "image_topic": 95.3,
            "nature_relation": 88.9,
            "object_localization": 63.5,
            "ocr": 97.4,
            "physical_property_reasoning": 63.0,
            "physical_relation": 76.9,
            "social_relation": 96.2,
            "spatial_relationship": 51.9,
            "structuralized_imagetext_understanding": 59.4,
            "Method": [
                "bailingMM-Chat",
                "https://github.com/JKBox/bailingMM-Chat"
            ],
            "Parameters": "11B",
            "Language Model": "bailing-10B",
            "Vision Model": "bailingMM-Encoder-1B",
            "Org": "Ant Group",
            "Time": "2024/06/28",
            "Verified": "No",
            "OpenSource": "No",
            "key": 287
        },
        {
            "Overall": 70.7,
            "AR": 82.3,
            "CP": 79.9,
            "FP-C": 61.1,
            "FP-S": 73.1,
            "LR": 46.2,
            "RR": 61.1,
            "action_recognition": 93.2,
            "attribute_comparison": 60.3,
            "attribute_recognition": 81.8,
            "celebrity_recognition": 77.1,
            "function_reasoning": 86.8,
            "future_prediction": 61.1,
            "identity_reasoning": 96.3,
            "image_emotion": 74.7,
            "image_quality": 65.9,
            "image_scene": 91.5,
            "image_style": 65.9,
            "image_topic": 95.3,
            "nature_relation": 51.9,
            "object_localization": 49.0,
            "ocr": 88.3,
            "physical_property_reasoning": 66.0,
            "physical_relation": 32.7,
            "social_relation": 89.7,
            "spatial_relationship": 27.2,
            "structuralized_imagetext_understanding": 35.6,
            "Method": [
                "Llama-3-MixSense",
                "https://huggingface.co/Zero-Vision/Llama-3-MixSense"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "ZeroVision",
            "Time": "2024/07/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 288
        },
        {
            "Overall": 86.8,
            "AR": 88.5,
            "CP": 88.2,
            "FP-C": 83.0,
            "FP-S": 92.0,
            "LR": 78.0,
            "RR": 83.4,
            "action_recognition": 95.5,
            "attribute_comparison": 80.8,
            "attribute_recognition": 99.0,
            "celebrity_recognition": 92.4,
            "function_reasoning": 90.6,
            "future_prediction": 77.8,
            "identity_reasoning": 98.8,
            "image_emotion": 78.3,
            "image_quality": 80.0,
            "image_scene": 95.3,
            "image_style": 85.9,
            "image_topic": 97.6,
            "nature_relation": 86.4,
            "object_localization": 79.8,
            "ocr": 98.7,
            "physical_property_reasoning": 78.0,
            "physical_relation": 73.1,
            "social_relation": 87.2,
            "spatial_relationship": 71.6,
            "structuralized_imagetext_understanding": 78.2,
            "Method": [
                "InternVL-2.0-Pro",
                "https://huggingface.co/spaces/OpenGVLab/InternVL/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/08",
            "Verified": "Yes",
            "OpenSource": "No",
            "key": 290
        },
        {
            "Overall": 61.0,
            "AR": 76.0,
            "CP": 72.4,
            "FP-C": 42.9,
            "FP-S": 64.3,
            "LR": 28.3,
            "RR": 57.3,
            "action_recognition": 94.3,
            "attribute_comparison": 10.3,
            "attribute_recognition": 73.7,
            "celebrity_recognition": 63.6,
            "function_reasoning": 78.3,
            "future_prediction": 45.8,
            "identity_reasoning": 87.8,
            "image_emotion": 68.7,
            "image_quality": 32.9,
            "image_scene": 87.6,
            "image_style": 70.6,
            "image_topic": 94.1,
            "nature_relation": 48.1,
            "object_localization": 38.5,
            "ocr": 88.3,
            "physical_property_reasoning": 64.0,
            "physical_relation": 44.2,
            "social_relation": 75.6,
            "spatial_relationship": 18.5,
            "structuralized_imagetext_understanding": 15.8,
            "Method": [
                "InternVL2-1B",
                "https://huggingface.co/OpenGVLab/InternVL2-1B"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 292
        },
        {
            "Overall": 71.2,
            "AR": 80.6,
            "CP": 81.4,
            "FP-C": 59.9,
            "FP-S": 71.9,
            "LR": 50.9,
            "RR": 64.9,
            "action_recognition": 95.5,
            "attribute_comparison": 56.4,
            "attribute_recognition": 81.8,
            "celebrity_recognition": 69.5,
            "function_reasoning": 79.2,
            "future_prediction": 59.7,
            "identity_reasoning": 97.6,
            "image_emotion": 75.9,
            "image_quality": 60.0,
            "image_scene": 92.2,
            "image_style": 76.5,
            "image_topic": 96.5,
            "nature_relation": 65.4,
            "object_localization": 51.0,
            "ocr": 90.9,
            "physical_property_reasoning": 68.0,
            "physical_relation": 34.6,
            "social_relation": 84.6,
            "spatial_relationship": 24.7,
            "structuralized_imagetext_understanding": 44.6,
            "Method": [
                "InternVL2-2B",
                "https://huggingface.co/OpenGVLab/InternVL2-2B"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 293
        },
        {
            "Overall": 73.9,
            "AR": 77.8,
            "CP": 86.1,
            "FP-C": 65.2,
            "FP-S": 72.4,
            "LR": 56.6,
            "RR": 69.2,
            "action_recognition": 93.2,
            "attribute_comparison": 67.9,
            "attribute_recognition": 86.9,
            "celebrity_recognition": 59.3,
            "function_reasoning": 80.2,
            "future_prediction": 62.5,
            "identity_reasoning": 92.7,
            "image_emotion": 77.1,
            "image_quality": 81.2,
            "image_scene": 93.8,
            "image_style": 77.6,
            "image_topic": 96.5,
            "nature_relation": 71.6,
            "object_localization": 57.7,
            "ocr": 93.5,
            "physical_property_reasoning": 63.0,
            "physical_relation": 46.2,
            "social_relation": 82.1,
            "spatial_relationship": 32.1,
            "structuralized_imagetext_understanding": 52.5,
            "Method": [
                "InternVL2-4B",
                "https://huggingface.co/OpenGVLab/InternVL2-4B"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 294
        },
        {
            "Overall": 80.9,
            "AR": 81.9,
            "CP": 86.9,
            "FP-C": 74.9,
            "FP-S": 85.7,
            "LR": 67.1,
            "RR": 75.8,
            "action_recognition": 95.5,
            "attribute_comparison": 76.9,
            "attribute_recognition": 94.9,
            "celebrity_recognition": 83.1,
            "function_reasoning": 89.6,
            "future_prediction": 72.2,
            "identity_reasoning": 97.6,
            "image_emotion": 75.9,
            "image_quality": 82.4,
            "image_scene": 93.8,
            "image_style": 82.4,
            "image_topic": 96.5,
            "nature_relation": 82.7,
            "object_localization": 72.1,
            "ocr": 96.1,
            "physical_property_reasoning": 61.0,
            "physical_relation": 50.0,
            "social_relation": 85.9,
            "spatial_relationship": 50.6,
            "structuralized_imagetext_understanding": 63.4,
            "Method": [
                "InternVL2-8B",
                "https://huggingface.co/OpenGVLab/InternVL2-8B"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 295
        },
        {
            "Overall": 82.1,
            "AR": 81.2,
            "CP": 87.8,
            "FP-C": 72.9,
            "FP-S": 87.7,
            "LR": 72.3,
            "RR": 78.7,
            "action_recognition": 94.3,
            "attribute_comparison": 75.6,
            "attribute_recognition": 94.9,
            "celebrity_recognition": 87.3,
            "function_reasoning": 85.8,
            "future_prediction": 80.6,
            "identity_reasoning": 97.6,
            "image_emotion": 79.5,
            "image_quality": 87.1,
            "image_scene": 93.0,
            "image_style": 81.2,
            "image_topic": 95.3,
            "nature_relation": 82.7,
            "object_localization": 76.9,
            "ocr": 93.5,
            "physical_property_reasoning": 63.0,
            "physical_relation": 65.4,
            "social_relation": 83.3,
            "spatial_relationship": 46.9,
            "structuralized_imagetext_understanding": 66.3,
            "Method": [
                "InternVL2-26B",
                "https://huggingface.co/OpenGVLab/InternVL2-26B"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 296
        },
        {
            "Overall": 86.4,
            "AR": 87.5,
            "CP": 89.3,
            "FP-C": 77.7,
            "FP-S": 92.2,
            "LR": 76.9,
            "RR": 85.3,
            "action_recognition": 92.0,
            "attribute_comparison": 76.9,
            "attribute_recognition": 98.0,
            "celebrity_recognition": 94.1,
            "function_reasoning": 90.6,
            "future_prediction": 80.6,
            "identity_reasoning": 98.8,
            "image_emotion": 80.7,
            "image_quality": 85.9,
            "image_scene": 94.6,
            "image_style": 84.7,
            "image_topic": 97.6,
            "nature_relation": 90.1,
            "object_localization": 81.7,
            "ocr": 96.1,
            "physical_property_reasoning": 75.0,
            "physical_relation": 76.9,
            "social_relation": 85.9,
            "spatial_relationship": 63.0,
            "structuralized_imagetext_understanding": 74.3,
            "Method": [
                "InternVL2-40B",
                "https://huggingface.co/OpenGVLab/InternVL2-40B"
            ],
            "Parameters": "40B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 297
        },
        {
            "Overall": 67.9,
            "AR": 75.0,
            "CP": 79.9,
            "FP-C": 62.3,
            "FP-S": 63.1,
            "LR": 49.7,
            "RR": 62.6,
            "action_recognition": 93.2,
            "attribute_comparison": 57.7,
            "attribute_recognition": 74.7,
            "celebrity_recognition": 39.0,
            "function_reasoning": 83.0,
            "future_prediction": 59.7,
            "identity_reasoning": 93.9,
            "image_emotion": 75.9,
            "image_quality": 71.8,
            "image_scene": 90.7,
            "image_style": 61.2,
            "image_topic": 94.1,
            "nature_relation": 65.4,
            "object_localization": 58.7,
            "ocr": 90.9,
            "physical_property_reasoning": 51.0,
            "physical_relation": 36.5,
            "social_relation": 76.9,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 42.6,
            "Method": [
                "Cambrian-8B",
                "https://huggingface.co/nyu-visionx/cambrian-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "NYU",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 298
        },
        {
            "Overall": 80.9,
            "AR": 85.8,
            "CP": 85.4,
            "FP-C": 73.7,
            "FP-S": 86.2,
            "LR": 66.5,
            "RR": 74.4,
            "action_recognition": 94.3,
            "attribute_comparison": 80.8,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 84.7,
            "function_reasoning": 87.7,
            "future_prediction": 72.2,
            "identity_reasoning": 98.8,
            "image_emotion": 75.9,
            "image_quality": 80.0,
            "image_scene": 96.1,
            "image_style": 72.9,
            "image_topic": 96.5,
            "nature_relation": 80.2,
            "object_localization": 73.1,
            "ocr": 93.5,
            "physical_property_reasoning": 73.0,
            "physical_relation": 50.0,
            "social_relation": 84.6,
            "spatial_relationship": 44.4,
            "structuralized_imagetext_understanding": 62.4,
            "Method": [
                "InternLM-XComposer2.5",
                "https://huggingface.co/internlm/internlm-xcomposer2d5-7b"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 299
        },
        {
            "Overall": 79.6,
            "AR": 85.1,
            "CP": 87.6,
            "FP-C": 69.2,
            "FP-S": 79.4,
            "LR": 67.6,
            "RR": 76.8,
            "action_recognition": 93.2,
            "attribute_comparison": 73.1,
            "attribute_recognition": 85.9,
            "celebrity_recognition": 78.0,
            "function_reasoning": 88.7,
            "future_prediction": 81.9,
            "identity_reasoning": 97.6,
            "image_emotion": 79.5,
            "image_quality": 81.2,
            "image_scene": 94.6,
            "image_style": 83.5,
            "image_topic": 95.3,
            "nature_relation": 81.5,
            "object_localization": 64.4,
            "ocr": 93.5,
            "physical_property_reasoning": 71.0,
            "physical_relation": 57.7,
            "social_relation": 84.6,
            "spatial_relationship": 39.5,
            "structuralized_imagetext_understanding": 57.4,
            "Method": [
                "Bumblebee-7B-v2.0",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Monolith Foundation",
            "Time": "2024/07/11",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 300
        },
        {
            "Overall": 77.5,
            "AR": 85.8,
            "CP": 83.1,
            "FP-C": 67.2,
            "FP-S": 79.1,
            "LR": 54.3,
            "RR": 82.0,
            "action_recognition": 93.2,
            "attribute_comparison": 73.1,
            "attribute_recognition": 88.9,
            "celebrity_recognition": 75.4,
            "function_reasoning": 89.6,
            "future_prediction": 68.1,
            "identity_reasoning": 97.6,
            "image_emotion": 77.1,
            "image_quality": 74.1,
            "image_scene": 92.2,
            "image_style": 71.8,
            "image_topic": 95.3,
            "nature_relation": 88.9,
            "object_localization": 65.4,
            "ocr": 90.9,
            "physical_property_reasoning": 72.0,
            "physical_relation": 55.8,
            "social_relation": 92.3,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 44.6,
            "Method": [
                "XinYuan-VL",
                "https://cece.com"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Cylingo Group",
            "Time": "2024/07/18",
            "Verified": "No",
            "OpenSource": "No",
            "key": 301
        },
        {
            "Overall": 79.2,
            "AR": 81.9,
            "CP": 85.9,
            "FP-C": 75.3,
            "FP-S": 81.7,
            "LR": 61.8,
            "RR": 74.9,
            "action_recognition": 92.0,
            "attribute_comparison": 78.2,
            "attribute_recognition": 87.9,
            "celebrity_recognition": 78.0,
            "function_reasoning": 91.5,
            "future_prediction": 66.7,
            "identity_reasoning": 100.0,
            "image_emotion": 79.5,
            "image_quality": 76.5,
            "image_scene": 94.6,
            "image_style": 76.5,
            "image_topic": 97.6,
            "nature_relation": 85.2,
            "object_localization": 71.2,
            "ocr": 93.5,
            "physical_property_reasoning": 57.0,
            "physical_relation": 46.2,
            "social_relation": 83.3,
            "spatial_relationship": 54.3,
            "structuralized_imagetext_understanding": 58.4,
            "Method": [
                "Cambrian-34B",
                "https://huggingface.co/nyu-visionx/cambrian-34b"
            ],
            "Parameters": "34B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "NYU",
            "Time": "2024/07/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 302
        },
        {
            "Overall": 74.4,
            "AR": 80.6,
            "CP": 83.7,
            "FP-C": 63.2,
            "FP-S": 77.1,
            "LR": 52.6,
            "RR": 71.1,
            "action_recognition": 93.2,
            "attribute_comparison": 61.5,
            "attribute_recognition": 82.8,
            "celebrity_recognition": 78.8,
            "function_reasoning": 84.9,
            "future_prediction": 70.8,
            "identity_reasoning": 98.8,
            "image_emotion": 80.7,
            "image_quality": 68.2,
            "image_scene": 96.1,
            "image_style": 72.9,
            "image_topic": 94.1,
            "nature_relation": 70.4,
            "object_localization": 57.7,
            "ocr": 93.5,
            "physical_property_reasoning": 61.0,
            "physical_relation": 42.3,
            "social_relation": 91.0,
            "spatial_relationship": 32.1,
            "structuralized_imagetext_understanding": 39.6,
            "Method": [
                "Bunny-Llama3-8B",
                "https://huggingface.co/BAAI/Bunny-v1_1-Llama-3-8B-V"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "BAAI",
            "Time": "2024/07/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 303
        },
        {
            "Overall": 77.6,
            "AR": 80.9,
            "CP": 84.4,
            "FP-C": 73.7,
            "FP-S": 78.1,
            "LR": 65.9,
            "RR": 71.1,
            "action_recognition": 93.2,
            "attribute_comparison": 79.5,
            "attribute_recognition": 84.8,
            "celebrity_recognition": 77.1,
            "function_reasoning": 86.8,
            "future_prediction": 69.4,
            "identity_reasoning": 97.6,
            "image_emotion": 74.7,
            "image_quality": 80.0,
            "image_scene": 96.9,
            "image_style": 69.4,
            "image_topic": 94.1,
            "nature_relation": 70.4,
            "object_localization": 60.6,
            "ocr": 94.8,
            "physical_property_reasoning": 61.0,
            "physical_relation": 51.9,
            "social_relation": 84.6,
            "spatial_relationship": 46.9,
            "structuralized_imagetext_understanding": 63.4,
            "Method": [
                "Ovis1.5-Llama3-8B",
                "https://huggingface.co/AIDC-AI/Ovis1.5-Llama3-8B"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 306
        },
        {
            "Overall": 7.1,
            "AR": 14.6,
            "CP": 4.9,
            "FP-C": 8.5,
            "FP-S": 4.8,
            "LR": 3.5,
            "RR": 7.6,
            "action_recognition": 15.9,
            "attribute_comparison": 5.1,
            "attribute_recognition": 7.1,
            "celebrity_recognition": 6.8,
            "function_reasoning": 20.8,
            "future_prediction": 2.8,
            "identity_reasoning": 8.5,
            "image_emotion": 2.4,
            "image_quality": 0.0,
            "image_scene": 9.3,
            "image_style": 0.0,
            "image_topic": 10.6,
            "nature_relation": 13.6,
            "object_localization": 1.9,
            "ocr": 2.6,
            "physical_property_reasoning": 13.0,
            "physical_relation": 7.7,
            "social_relation": 1.3,
            "spatial_relationship": 3.7,
            "structuralized_imagetext_understanding": 4.0,
            "Method": [
                "Chameleon-7B",
                "https://huggingface.co/facebook/chameleon-7b"
            ],
            "Parameters": "7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 309
        },
        {
            "Overall": 17.5,
            "AR": 30.9,
            "CP": 24.6,
            "FP-C": 9.7,
            "FP-S": 14.1,
            "LR": 1.2,
            "RR": 12.3,
            "action_recognition": 21.6,
            "attribute_comparison": 3.8,
            "attribute_recognition": 29.3,
            "celebrity_recognition": 12.7,
            "function_reasoning": 32.1,
            "future_prediction": 0.0,
            "identity_reasoning": 28.0,
            "image_emotion": 21.7,
            "image_quality": 0.0,
            "image_scene": 36.4,
            "image_style": 20.0,
            "image_topic": 38.8,
            "nature_relation": 11.1,
            "object_localization": 4.8,
            "ocr": 9.1,
            "physical_property_reasoning": 32.0,
            "physical_relation": 3.8,
            "social_relation": 19.2,
            "spatial_relationship": 2.5,
            "structuralized_imagetext_understanding": 2.0,
            "Method": [
                "Chameleon-30B",
                "https://huggingface.co/facebook/chameleon-30b"
            ],
            "Parameters": "30B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 310
        },
        {
            "Overall": 65.0,
            "AR": 69.4,
            "CP": 79.2,
            "FP-C": 61.5,
            "FP-S": 61.6,
            "LR": 41.6,
            "RR": 57.3,
            "action_recognition": 94.3,
            "attribute_comparison": 62.8,
            "attribute_recognition": 70.7,
            "celebrity_recognition": 45.8,
            "function_reasoning": 82.1,
            "future_prediction": 52.8,
            "identity_reasoning": 92.7,
            "image_emotion": 75.9,
            "image_quality": 64.7,
            "image_scene": 91.5,
            "image_style": 63.5,
            "image_topic": 94.1,
            "nature_relation": 53.1,
            "object_localization": 48.1,
            "ocr": 92.2,
            "physical_property_reasoning": 37.0,
            "physical_relation": 38.5,
            "social_relation": 74.4,
            "spatial_relationship": 24.7,
            "structuralized_imagetext_understanding": 33.7,
            "Method": [
                "Cambrian-13B",
                "https://huggingface.co/nyu-visionx/cambrian-13b"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "NYU",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 311
        },
        {
            "Overall": 78.6,
            "AR": 82.3,
            "CP": 84.8,
            "FP-C": 68.4,
            "FP-S": 82.4,
            "LR": 64.7,
            "RR": 76.3,
            "action_recognition": 92.0,
            "attribute_comparison": 70.5,
            "attribute_recognition": 91.9,
            "celebrity_recognition": 78.0,
            "function_reasoning": 86.8,
            "future_prediction": 72.2,
            "identity_reasoning": 96.3,
            "image_emotion": 79.5,
            "image_quality": 69.4,
            "image_scene": 91.5,
            "image_style": 82.4,
            "image_topic": 97.6,
            "nature_relation": 88.9,
            "object_localization": 69.2,
            "ocr": 94.8,
            "physical_property_reasoning": 66.0,
            "physical_relation": 48.1,
            "social_relation": 82.1,
            "spatial_relationship": 40.7,
            "structuralized_imagetext_understanding": 59.4,
            "Method": [
                "Yi-Vision",
                "https://platform.lingyiwanwu.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "01-AI",
            "Time": "2024/08/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 312
        },
        {
            "Overall": 78.8,
            "AR": 80.9,
            "CP": 84.8,
            "FP-C": 72.5,
            "FP-S": 81.4,
            "LR": 67.6,
            "RR": 73.9,
            "action_recognition": 90.9,
            "attribute_comparison": 71.8,
            "attribute_recognition": 91.9,
            "celebrity_recognition": 76.3,
            "function_reasoning": 85.8,
            "future_prediction": 75.0,
            "identity_reasoning": 97.6,
            "image_emotion": 75.9,
            "image_quality": 81.2,
            "image_scene": 92.2,
            "image_style": 75.3,
            "image_topic": 95.3,
            "nature_relation": 75.3,
            "object_localization": 67.3,
            "ocr": 94.8,
            "physical_property_reasoning": 62.0,
            "physical_relation": 63.5,
            "social_relation": 79.5,
            "spatial_relationship": 53.1,
            "structuralized_imagetext_understanding": 62.4,
            "Method": [
                "Ovis1.5-Gemma2-9B",
                "https://huggingface.co/AIDC-AI/Ovis1.5-Gemma2-9B"
            ],
            "Parameters": "11.4B",
            "Language Model": "Gemma2-9B-It",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/08/04",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 313
        },
        {
            "Overall": 70.1,
            "AR": 79.9,
            "CP": 80.3,
            "FP-C": 64.4,
            "FP-S": 71.1,
            "LR": 47.4,
            "RR": 57.3,
            "action_recognition": 93.2,
            "attribute_comparison": 61.5,
            "attribute_recognition": 75.8,
            "celebrity_recognition": 69.5,
            "function_reasoning": 82.1,
            "future_prediction": 63.9,
            "identity_reasoning": 93.9,
            "image_emotion": 78.3,
            "image_quality": 57.6,
            "image_scene": 93.8,
            "image_style": 69.4,
            "image_topic": 95.3,
            "nature_relation": 46.9,
            "object_localization": 53.8,
            "ocr": 90.9,
            "physical_property_reasoning": 66.0,
            "physical_relation": 42.3,
            "social_relation": 78.2,
            "spatial_relationship": 35.8,
            "structuralized_imagetext_understanding": 35.6,
            "Method": [
                "LLaVA-Next-Llama3",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "ByteDance",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 307
        },
        {
            "Overall": 73.7,
            "AR": 83.0,
            "CP": 82.9,
            "FP-C": 68.8,
            "FP-S": 72.6,
            "LR": 49.7,
            "RR": 67.8,
            "action_recognition": 95.5,
            "attribute_comparison": 75.6,
            "attribute_recognition": 80.8,
            "celebrity_recognition": 74.6,
            "function_reasoning": 83.0,
            "future_prediction": 61.1,
            "identity_reasoning": 97.6,
            "image_emotion": 77.1,
            "image_quality": 72.9,
            "image_scene": 94.6,
            "image_style": 68.2,
            "image_topic": 95.3,
            "nature_relation": 79.0,
            "object_localization": 46.2,
            "ocr": 94.8,
            "physical_property_reasoning": 71.0,
            "physical_relation": 34.6,
            "social_relation": 78.2,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 41.6,
            "Method": [
                "LLaVA-Next-Interleave-7B-DPO",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen1.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 308
        },
        {
            "Overall": 72.5,
            "AR": 80.6,
            "CP": 80.5,
            "FP-C": 66.0,
            "FP-S": 71.6,
            "LR": 52.6,
            "RR": 69.7,
            "action_recognition": 94.3,
            "attribute_comparison": 71.8,
            "attribute_recognition": 82.8,
            "celebrity_recognition": 78.8,
            "function_reasoning": 82.1,
            "future_prediction": 66.7,
            "identity_reasoning": 95.1,
            "image_emotion": 67.5,
            "image_quality": 64.7,
            "image_scene": 92.2,
            "image_style": 75.3,
            "image_topic": 96.5,
            "nature_relation": 72.8,
            "object_localization": 36.5,
            "ocr": 93.5,
            "physical_property_reasoning": 67.0,
            "physical_relation": 40.4,
            "social_relation": 85.9,
            "spatial_relationship": 29.6,
            "structuralized_imagetext_understanding": 42.6,
            "Method": [
                "LLaVA-Next-Interleave-7B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen1.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 314
        },
        {
            "Overall": 79.1,
            "AR": 82.6,
            "CP": 84.6,
            "FP-C": 70.4,
            "FP-S": 84.2,
            "LR": 60.1,
            "RR": 78.2,
            "action_recognition": 93.2,
            "attribute_comparison": 66.7,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 88.1,
            "function_reasoning": 89.6,
            "future_prediction": 72.2,
            "identity_reasoning": 98.8,
            "image_emotion": 79.5,
            "image_quality": 70.6,
            "image_scene": 96.9,
            "image_style": 74.1,
            "image_topic": 95.3,
            "nature_relation": 93.8,
            "object_localization": 65.4,
            "ocr": 94.8,
            "physical_property_reasoning": 62.0,
            "physical_relation": 50.0,
            "social_relation": 80.8,
            "spatial_relationship": 49.4,
            "structuralized_imagetext_understanding": 51.5,
            "Method": [
                "LLaVA-Next-Qwen-32B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "33B",
            "Language Model": "Qwen1.5-32B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 315
        },
        {
            "Overall": 64.9,
            "AR": 76.0,
            "CP": 75.2,
            "FP-C": 53.4,
            "FP-S": 63.3,
            "LR": 46.2,
            "RR": 58.8,
            "action_recognition": 92.0,
            "attribute_comparison": 43.6,
            "attribute_recognition": 72.7,
            "celebrity_recognition": 72.9,
            "function_reasoning": 81.1,
            "future_prediction": 70.8,
            "identity_reasoning": 92.7,
            "image_emotion": 77.1,
            "image_quality": 29.4,
            "image_scene": 91.5,
            "image_style": 72.9,
            "image_topic": 96.5,
            "nature_relation": 46.9,
            "object_localization": 31.7,
            "ocr": 79.2,
            "physical_property_reasoning": 57.0,
            "physical_relation": 38.5,
            "social_relation": 84.6,
            "spatial_relationship": 21.0,
            "structuralized_imagetext_understanding": 28.7,
            "Method": [
                "Mantis-8B-clip-llama3",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-clip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 316
        },
        {
            "Overall": 65.3,
            "AR": 78.5,
            "CP": 77.5,
            "FP-C": 52.6,
            "FP-S": 67.1,
            "LR": 42.2,
            "RR": 50.7,
            "action_recognition": 95.5,
            "attribute_comparison": 32.1,
            "attribute_recognition": 73.7,
            "celebrity_recognition": 73.7,
            "function_reasoning": 84.9,
            "future_prediction": 68.1,
            "identity_reasoning": 97.6,
            "image_emotion": 80.7,
            "image_quality": 31.8,
            "image_scene": 95.3,
            "image_style": 76.5,
            "image_topic": 94.1,
            "nature_relation": 37.0,
            "object_localization": 36.5,
            "ocr": 89.6,
            "physical_property_reasoning": 56.0,
            "physical_relation": 30.8,
            "social_relation": 78.2,
            "spatial_relationship": 25.9,
            "structuralized_imagetext_understanding": 23.8,
            "Method": [
                "Mantis-8B-siglip-llama3",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-siglip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 317
        },
        {
            "Overall": 67.9,
            "AR": 74.3,
            "CP": 79.7,
            "FP-C": 62.8,
            "FP-S": 68.8,
            "LR": 43.9,
            "RR": 56.9,
            "action_recognition": 97.7,
            "attribute_comparison": 61.5,
            "attribute_recognition": 73.7,
            "celebrity_recognition": 67.8,
            "function_reasoning": 81.1,
            "future_prediction": 68.1,
            "identity_reasoning": 91.5,
            "image_emotion": 81.9,
            "image_quality": 51.8,
            "image_scene": 91.5,
            "image_style": 70.6,
            "image_topic": 96.5,
            "nature_relation": 37.0,
            "object_localization": 50.0,
            "ocr": 89.6,
            "physical_property_reasoning": 53.0,
            "physical_relation": 42.3,
            "social_relation": 87.2,
            "spatial_relationship": 25.9,
            "structuralized_imagetext_understanding": 26.7,
            "Method": [
                "Mantis-8B-Idefics2",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-Idefics2"
            ],
            "Parameters": "8B",
            "Language Model": "Mistral-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 318
        },
        {
            "Overall": 79.3,
            "AR": 82.6,
            "CP": 85.0,
            "FP-C": 70.4,
            "FP-S": 84.9,
            "LR": 61.8,
            "RR": 75.8,
            "action_recognition": 92.0,
            "attribute_comparison": 74.4,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 85.6,
            "function_reasoning": 85.8,
            "future_prediction": 70.8,
            "identity_reasoning": 97.6,
            "image_emotion": 77.1,
            "image_quality": 83.5,
            "image_scene": 90.7,
            "image_style": 75.3,
            "image_topic": 95.3,
            "nature_relation": 80.2,
            "object_localization": 71.2,
            "ocr": 94.8,
            "physical_property_reasoning": 67.0,
            "physical_relation": 63.5,
            "social_relation": 79.5,
            "spatial_relationship": 43.2,
            "structuralized_imagetext_understanding": 55.4,
            "Method": [
                "MiniCPM-V-2.6",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-siglip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "OpenBMB",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 319
        },
        {
            "Overall": 80.3,
            "AR": 85.1,
            "CP": 87.2,
            "FP-C": 78.9,
            "FP-S": 72.6,
            "LR": 76.9,
            "RR": 77.3,
            "action_recognition": 94.3,
            "attribute_comparison": 79.5,
            "attribute_recognition": 88.9,
            "celebrity_recognition": 45.8,
            "function_reasoning": 88.7,
            "future_prediction": 76.4,
            "identity_reasoning": 98.8,
            "image_emotion": 75.9,
            "image_quality": 83.5,
            "image_scene": 96.1,
            "image_style": 80.0,
            "image_topic": 95.3,
            "nature_relation": 92.6,
            "object_localization": 70.2,
            "ocr": 96.1,
            "physical_property_reasoning": 70.0,
            "physical_relation": 51.9,
            "social_relation": 78.2,
            "spatial_relationship": 61.7,
            "structuralized_imagetext_understanding": 77.2,
            "Method": [
                "GPT-4o (0806, detail-high)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 320
        },
        {
            "Overall": 72.9,
            "AR": 80.9,
            "CP": 80.1,
            "FP-C": 70.0,
            "FP-S": 71.6,
            "LR": 52.6,
            "RR": 68.7,
            "action_recognition": 95.5,
            "attribute_comparison": 75.6,
            "attribute_recognition": 78.8,
            "celebrity_recognition": 65.3,
            "function_reasoning": 84.0,
            "future_prediction": 70.8,
            "identity_reasoning": 93.9,
            "image_emotion": 74.7,
            "image_quality": 67.1,
            "image_scene": 89.1,
            "image_style": 69.4,
            "image_topic": 95.3,
            "nature_relation": 63.0,
            "object_localization": 59.6,
            "ocr": 88.3,
            "physical_property_reasoning": 67.0,
            "physical_relation": 46.2,
            "social_relation": 89.7,
            "spatial_relationship": 37.0,
            "structuralized_imagetext_understanding": 39.6,
            "Method": [
                "Llama-3-MixSense-v1.1",
                "https://huggingface.co/Zero-Vision/Llama-3-MixSenseV1_1"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "Florence-2-Large-FT",
            "Org": "ZeroVision",
            "Time": "2024/08/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 321
        },
        {
            "Overall": 81.4,
            "AR": 83.7,
            "CP": 85.0,
            "FP-C": 73.7,
            "FP-S": 87.2,
            "LR": 64.7,
            "RR": 82.5,
            "action_recognition": 93.2,
            "attribute_comparison": 82.1,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 87.3,
            "function_reasoning": 90.6,
            "future_prediction": 79.2,
            "identity_reasoning": 98.8,
            "image_emotion": 77.1,
            "image_quality": 75.3,
            "image_scene": 93.8,
            "image_style": 77.6,
            "image_topic": 96.5,
            "nature_relation": 88.9,
            "object_localization": 76.0,
            "ocr": 94.8,
            "physical_property_reasoning": 64.0,
            "physical_relation": 63.5,
            "social_relation": 88.5,
            "spatial_relationship": 44.4,
            "structuralized_imagetext_understanding": 54.5,
            "Method": [
                "OmChat-v2.0-13B",
                "https://huggingface.co/omlab/omchat-v2.0-13B-single-beta_hf"
            ],
            "Parameters": "13B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "InternViT-6B",
            "Org": "Om AI",
            "Time": "2024/08/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 323
        },
        {
            "Overall": 71.7,
            "AR": 83.3,
            "CP": 76.2,
            "FP-C": 64.4,
            "FP-S": 75.1,
            "LR": 45.7,
            "RR": 69.7,
            "action_recognition": 94.3,
            "attribute_comparison": 70.5,
            "attribute_recognition": 76.8,
            "celebrity_recognition": 74.6,
            "function_reasoning": 85.8,
            "future_prediction": 63.9,
            "identity_reasoning": 96.3,
            "image_emotion": 62.7,
            "image_quality": 49.4,
            "image_scene": 94.6,
            "image_style": 69.4,
            "image_topic": 95.3,
            "nature_relation": 72.8,
            "object_localization": 60.6,
            "ocr": 93.5,
            "physical_property_reasoning": 70.0,
            "physical_relation": 50.0,
            "social_relation": 79.5,
            "spatial_relationship": 25.9,
            "structuralized_imagetext_understanding": 32.7,
            "Method": [
                "Parrot-7B",
                "https://huggingface.co/AIDC-AI/Parrot-7B"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Alibaba",
            "Time": "2024/08/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 324
        },
        {
            "Overall": 56.2,
            "AR": 76.0,
            "CP": 69.8,
            "FP-C": 44.1,
            "FP-S": 48.7,
            "LR": 25.4,
            "RR": 52.1,
            "action_recognition": 93.2,
            "attribute_comparison": 12.8,
            "attribute_recognition": 59.6,
            "celebrity_recognition": 36.4,
            "function_reasoning": 79.2,
            "future_prediction": 48.6,
            "identity_reasoning": 92.7,
            "image_emotion": 80.7,
            "image_quality": 30.6,
            "image_scene": 88.4,
            "image_style": 44.7,
            "image_topic": 95.3,
            "nature_relation": 39.5,
            "object_localization": 25.0,
            "ocr": 85.7,
            "physical_property_reasoning": 59.0,
            "physical_relation": 28.8,
            "social_relation": 80.8,
            "spatial_relationship": 21.0,
            "structuralized_imagetext_understanding": 8.9,
            "Method": [
                "VILA1.5-3B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-3b"
            ],
            "Parameters": "3B",
            "Language Model": "Sheared-LLaMA-2.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 325
        },
        {
            "Overall": 60.4,
            "AR": 70.1,
            "CP": 73.2,
            "FP-C": 56.7,
            "FP-S": 59.3,
            "LR": 30.1,
            "RR": 49.8,
            "action_recognition": 92.0,
            "attribute_comparison": 53.8,
            "attribute_recognition": 69.7,
            "celebrity_recognition": 60.2,
            "function_reasoning": 74.5,
            "future_prediction": 50.0,
            "identity_reasoning": 91.5,
            "image_emotion": 77.1,
            "image_quality": 36.5,
            "image_scene": 90.7,
            "image_style": 57.6,
            "image_topic": 95.3,
            "nature_relation": 50.6,
            "object_localization": 29.8,
            "ocr": 84.4,
            "physical_property_reasoning": 48.0,
            "physical_relation": 28.8,
            "social_relation": 62.8,
            "spatial_relationship": 21.0,
            "structuralized_imagetext_understanding": 15.8,
            "Method": [
                "Llama-3-VILA1.5-8B",
                "https://huggingface.co/Efficient-Large-Model/Llama-3-VILA1.5-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 326
        },
        {
            "Overall": 67.7,
            "AR": 72.2,
            "CP": 79.7,
            "FP-C": 62.8,
            "FP-S": 64.6,
            "LR": 44.5,
            "RR": 65.4,
            "action_recognition": 89.8,
            "attribute_comparison": 62.8,
            "attribute_recognition": 81.8,
            "celebrity_recognition": 59.3,
            "function_reasoning": 81.1,
            "future_prediction": 63.9,
            "identity_reasoning": 96.3,
            "image_emotion": 80.7,
            "image_quality": 60.0,
            "image_scene": 89.1,
            "image_style": 67.1,
            "image_topic": 96.5,
            "nature_relation": 70.4,
            "object_localization": 34.6,
            "ocr": 90.9,
            "physical_property_reasoning": 43.0,
            "physical_relation": 40.4,
            "social_relation": 76.9,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 30.7,
            "Method": [
                "VILA1.5-13B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-13b"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 327
        },
        {
            "Overall": 81.2,
            "AR": 84.0,
            "CP": 85.7,
            "FP-C": 76.9,
            "FP-S": 87.4,
            "LR": 61.8,
            "RR": 76.8,
            "action_recognition": 94.3,
            "attribute_comparison": 73.1,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 89.8,
            "function_reasoning": 91.5,
            "future_prediction": 77.8,
            "identity_reasoning": 97.6,
            "image_emotion": 74.7,
            "image_quality": 83.5,
            "image_scene": 93.8,
            "image_style": 75.3,
            "image_topic": 96.5,
            "nature_relation": 87.7,
            "object_localization": 73.1,
            "ocr": 94.8,
            "physical_property_reasoning": 65.0,
            "physical_relation": 51.9,
            "social_relation": 82.1,
            "spatial_relationship": 61.7,
            "structuralized_imagetext_understanding": 50.5,
            "Method": [
                "VILA1.5-40B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-40b"
            ],
            "Parameters": "40B",
            "Language Model": "Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 328
        },
        {
            "Overall": 82.1,
            "AR": 84.4,
            "CP": 86.9,
            "FP-C": 73.7,
            "FP-S": 87.2,
            "LR": 71.7,
            "RR": 77.3,
            "action_recognition": 95.5,
            "attribute_comparison": 82.1,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 85.6,
            "function_reasoning": 85.8,
            "future_prediction": 80.6,
            "identity_reasoning": 98.8,
            "image_emotion": 78.3,
            "image_quality": 84.7,
            "image_scene": 93.8,
            "image_style": 77.6,
            "image_topic": 96.5,
            "nature_relation": 76.5,
            "object_localization": 76.9,
            "ocr": 92.2,
            "physical_property_reasoning": 71.0,
            "physical_relation": 69.2,
            "social_relation": 83.3,
            "spatial_relationship": 42.0,
            "structuralized_imagetext_understanding": 65.3,
            "Org": "DataCanvas",
            "Time": "2024/08/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "MMAlaya2",
                "https://huggingface.co/DataCanvas/MMAlaya2"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "key": 329
        },
        {
            "Overall": 74.5,
            "AR": 80.9,
            "CP": 82.0,
            "FP-C": 66.4,
            "FP-S": 76.1,
            "LR": 59.0,
            "RR": 68.2,
            "action_recognition": 92.0,
            "attribute_comparison": 67.9,
            "attribute_recognition": 85.9,
            "celebrity_recognition": 74.6,
            "function_reasoning": 85.8,
            "future_prediction": 62.5,
            "identity_reasoning": 97.6,
            "image_emotion": 75.9,
            "image_quality": 62.4,
            "image_scene": 93.0,
            "image_style": 75.3,
            "image_topic": 97.6,
            "nature_relation": 75.3,
            "object_localization": 56.7,
            "ocr": 92.2,
            "physical_property_reasoning": 62.0,
            "physical_relation": 40.4,
            "social_relation": 79.5,
            "spatial_relationship": 37.0,
            "structuralized_imagetext_understanding": 56.4,
            "Org": "HuggingFace",
            "Time": "2024/08/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "Idefics3-8B-Llama3",
                "https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "key": 330
        },
        {
            "Overall": 66.1,
            "AR": 76.7,
            "CP": 76.4,
            "FP-C": 60.3,
            "FP-S": 58.3,
            "LR": 52.0,
            "RR": 61.6,
            "action_recognition": 90.9,
            "attribute_comparison": 57.7,
            "attribute_recognition": 65.7,
            "celebrity_recognition": 53.4,
            "function_reasoning": 78.3,
            "future_prediction": 62.5,
            "identity_reasoning": 91.5,
            "image_emotion": 78.3,
            "image_quality": 61.2,
            "image_scene": 89.1,
            "image_style": 55.3,
            "image_topic": 91.8,
            "nature_relation": 55.6,
            "object_localization": 32.7,
            "ocr": 90.9,
            "physical_property_reasoning": 63.0,
            "physical_relation": 36.5,
            "social_relation": 84.6,
            "spatial_relationship": 29.6,
            "structuralized_imagetext_understanding": 44.6,
            "Org": "Microsoft",
            "Time": "2024/08/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "Phi-3.5-Vision",
                "https://huggingface.co/microsoft/Phi-3.5-vision-instruct"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3.5",
            "Vision Model": "CLIP ViT-L/14",
            "key": 331
        },
        {
            "Overall": 80.7,
            "AR": 80.9,
            "CP": 86.7,
            "FP-C": 72.5,
            "FP-S": 80.2,
            "LR": 71.7,
            "RR": 84.8,
            "action_recognition": 92.0,
            "attribute_comparison": 73.1,
            "attribute_recognition": 87.9,
            "celebrity_recognition": 76.3,
            "function_reasoning": 84.9,
            "future_prediction": 81.9,
            "identity_reasoning": 97.6,
            "image_emotion": 80.7,
            "image_quality": 85.9,
            "image_scene": 92.2,
            "image_style": 76.5,
            "image_topic": 95.3,
            "nature_relation": 95.1,
            "object_localization": 67.3,
            "ocr": 93.5,
            "physical_property_reasoning": 63.0,
            "physical_relation": 65.4,
            "social_relation": 87.2,
            "spatial_relationship": 50.6,
            "structuralized_imagetext_understanding": 64.4,
            "Org": "Monolith Foundation",
            "Time": "2024/08/30",
            "Verified": "No",
            "OpenSource": "Yes",
            "Method": [
                "Mirage-12B-v2.0",
                "https://huggingface.co/MonolithFoundation/Mirage-12B"
            ],
            "Parameters": "12B",
            "Language Model": "Mistral-12B",
            "Vision Model": "SigLIP-400M",
            "key": 332
        },
        {
            "Overall": 46.4,
            "AR": 62.2,
            "CP": 56.5,
            "FP-C": 46.6,
            "FP-S": 39.4,
            "LR": 26.6,
            "RR": 31.8,
            "action_recognition": 86.4,
            "attribute_comparison": 29.5,
            "attribute_recognition": 31.3,
            "celebrity_recognition": 37.3,
            "function_reasoning": 61.3,
            "future_prediction": 44.4,
            "identity_reasoning": 82.9,
            "image_emotion": 60.2,
            "image_quality": 8.2,
            "image_scene": 76.7,
            "image_style": 38.8,
            "image_topic": 88.2,
            "nature_relation": 19.8,
            "object_localization": 18.3,
            "ocr": 81.8,
            "physical_property_reasoning": 46.0,
            "physical_relation": 23.1,
            "social_relation": 50.0,
            "spatial_relationship": 19.8,
            "structuralized_imagetext_understanding": 13.9,
            "Method": [
                "LLaVA-v1.5-7B",
                "https://arxiv.org/abs/2310.03744"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2023/10/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 186
        },
        {
            "Overall": 58.2,
            "AR": 69.1,
            "CP": 70.7,
            "FP-C": 53.8,
            "FP-S": 54.3,
            "LR": 39.3,
            "RR": 44.1,
            "action_recognition": 89.8,
            "attribute_comparison": 51.3,
            "attribute_recognition": 52.5,
            "celebrity_recognition": 52.5,
            "function_reasoning": 76.4,
            "future_prediction": 59.7,
            "identity_reasoning": 90.2,
            "image_emotion": 66.3,
            "image_quality": 44.7,
            "image_scene": 85.3,
            "image_style": 54.1,
            "image_topic": 95.3,
            "nature_relation": 28.4,
            "object_localization": 38.5,
            "ocr": 80.5,
            "physical_property_reasoning": 44.0,
            "physical_relation": 28.8,
            "social_relation": 70.5,
            "spatial_relationship": 17.3,
            "structuralized_imagetext_understanding": 24.8,
            "Method": [
                "LLaVA-v1.5-13B",
                "https://arxiv.org/abs/2310.03744"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2023/10/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 188
        },
        {
            "Overall": 67.1,
            "AR": 72.9,
            "CP": 78.4,
            "FP-C": 62.3,
            "FP-S": 63.6,
            "LR": 41.6,
            "RR": 67.3,
            "action_recognition": 92.0,
            "attribute_comparison": 69.2,
            "attribute_recognition": 65.7,
            "celebrity_recognition": 49.2,
            "function_reasoning": 81.1,
            "future_prediction": 55.6,
            "identity_reasoning": 91.5,
            "image_emotion": 74.7,
            "image_quality": 67.1,
            "image_scene": 92.2,
            "image_style": 60.0,
            "image_topic": 90.6,
            "nature_relation": 72.8,
            "object_localization": 58.7,
            "ocr": 89.6,
            "physical_property_reasoning": 49.0,
            "physical_relation": 32.7,
            "social_relation": 84.6,
            "spatial_relationship": 23.5,
            "structuralized_imagetext_understanding": 31.7,
            "Method": [
                "XGen-MM-Instruct-Interleave-v1.5",
                "https://huggingface.co/Salesforce/xgen-mm-phi3-mini-instruct-interleave-r-v1.5"
            ],
            "Parameters": "4.4B",
            "Language Model": "Phi-3",
            "Vision Model": "SigLIP-400M",
            "Org": "Salesforce",
            "Time": "2024/09/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 333
        },
        {
            "Overall": 68.7,
            "AR": 79.2,
            "CP": 78.8,
            "FP-C": 59.5,
            "FP-S": 63.8,
            "LR": 48.6,
            "RR": 68.2,
            "action_recognition": 92.0,
            "attribute_comparison": 64.1,
            "attribute_recognition": 71.7,
            "celebrity_recognition": 52.5,
            "function_reasoning": 84.9,
            "future_prediction": 65.3,
            "identity_reasoning": 91.5,
            "image_emotion": 75.9,
            "image_quality": 64.7,
            "image_scene": 90.7,
            "image_style": 63.5,
            "image_topic": 92.9,
            "nature_relation": 69.1,
            "object_localization": 50.0,
            "ocr": 89.6,
            "physical_property_reasoning": 63.0,
            "physical_relation": 36.5,
            "social_relation": 88.5,
            "spatial_relationship": 19.8,
            "structuralized_imagetext_understanding": 36.6,
            "Method": [
                "XGen-MM-Instruct-DPO-v1.5",
                "https://huggingface.co/Salesforce/xgen-mm-phi3-mini-instruct-dpo-r-v1.5"
            ],
            "Parameters": "4.4B",
            "Language Model": "Phi-3",
            "Vision Model": "SigLIP-400M",
            "Org": "Salesforce",
            "Time": "2024/09/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 334
        },
        {
            "Overall": 80.6,
            "AR": 82.6,
            "CP": 86.9,
            "FP-C": 74.5,
            "FP-S": 85.2,
            "LR": 61.8,
            "RR": 77.7,
            "action_recognition": 94.3,
            "attribute_comparison": 75.6,
            "attribute_recognition": 88.9,
            "celebrity_recognition": 90.7,
            "function_reasoning": 85.8,
            "future_prediction": 69.4,
            "identity_reasoning": 98.8,
            "image_emotion": 83.1,
            "image_quality": 82.4,
            "image_scene": 92.2,
            "image_style": 78.8,
            "image_topic": 95.3,
            "nature_relation": 85.2,
            "object_localization": 67.3,
            "ocr": 96.1,
            "physical_property_reasoning": 66.0,
            "physical_relation": 50.0,
            "social_relation": 88.5,
            "spatial_relationship": 51.9,
            "structuralized_imagetext_understanding": 56.4,
            "Method": [
                "Qwen2-VL-7B",
                "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/09/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 336
        },
        {
            "Overall": 73.8,
            "AR": 79.9,
            "CP": 80.9,
            "FP-C": 61.9,
            "FP-S": 77.6,
            "LR": 53.2,
            "RR": 73.0,
            "action_recognition": 94.3,
            "attribute_comparison": 59.0,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 85.6,
            "function_reasoning": 86.8,
            "future_prediction": 68.1,
            "identity_reasoning": 96.3,
            "image_emotion": 78.3,
            "image_quality": 60.0,
            "image_scene": 93.8,
            "image_style": 70.6,
            "image_topic": 95.3,
            "nature_relation": 75.3,
            "object_localization": 53.8,
            "ocr": 94.8,
            "physical_property_reasoning": 59.0,
            "physical_relation": 50.0,
            "social_relation": 85.9,
            "spatial_relationship": 29.6,
            "structuralized_imagetext_understanding": 42.6,
            "Method": [
                "Qwen2-VL-2B",
                "https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct"
            ],
            "Parameters": "2B",
            "Language Model": "Qwen2-1.5B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/09/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 337
        },
        {
            "Overall": 33.4,
            "AR": 42.7,
            "CP": 48.2,
            "FP-C": 27.5,
            "FP-S": 24.9,
            "LR": 20.8,
            "RR": 21.3,
            "action_recognition": 55.7,
            "attribute_comparison": 16.7,
            "attribute_recognition": 50.5,
            "celebrity_recognition": 13.6,
            "function_reasoning": 42.5,
            "future_prediction": 38.9,
            "identity_reasoning": 56.1,
            "image_emotion": 49.4,
            "image_quality": 11.8,
            "image_scene": 65.1,
            "image_style": 27.1,
            "image_topic": 78.8,
            "nature_relation": 13.6,
            "object_localization": 9.6,
            "ocr": 29.9,
            "physical_property_reasoning": 32.0,
            "physical_relation": 11.5,
            "social_relation": 35.9,
            "spatial_relationship": 7.4,
            "structuralized_imagetext_understanding": 7.9,
            "Method": [
                "Mantis-8B-Fuyu",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-Fuyu"
            ],
            "Parameters": "8B",
            "Language Model": "Fuyu-8B",
            "Vision Model": "",
            "Org": "TIGER Lab",
            "Time": "2024/09/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 339
        },
        {
            "Overall": 56.7,
            "AR": 69.4,
            "CP": 72.2,
            "FP-C": 47.0,
            "FP-S": 49.0,
            "LR": 29.5,
            "RR": 53.1,
            "action_recognition": 92.0,
            "attribute_comparison": 25.6,
            "attribute_recognition": 56.6,
            "celebrity_recognition": 52.5,
            "function_reasoning": 78.3,
            "future_prediction": 50.0,
            "identity_reasoning": 89.0,
            "image_emotion": 78.3,
            "image_quality": 31.8,
            "image_scene": 90.7,
            "image_style": 57.6,
            "image_topic": 92.9,
            "nature_relation": 55.6,
            "object_localization": 24.0,
            "ocr": 67.5,
            "physical_property_reasoning": 44.0,
            "physical_relation": 26.9,
            "social_relation": 67.9,
            "spatial_relationship": 18.5,
            "structuralized_imagetext_understanding": 14.9,
            "Method": [
                "Slime-7B",
                "https://huggingface.co/yifanzhang114/SliME-vicuna-7B"
            ],
            "Parameters": "7B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 340
        },
        {
            "Overall": 66.0,
            "AR": 72.6,
            "CP": 80.7,
            "FP-C": 58.3,
            "FP-S": 65.1,
            "LR": 37.6,
            "RR": 58.8,
            "action_recognition": 93.2,
            "attribute_comparison": 47.4,
            "attribute_recognition": 69.7,
            "celebrity_recognition": 67.8,
            "function_reasoning": 81.1,
            "future_prediction": 65.3,
            "identity_reasoning": 95.1,
            "image_emotion": 79.5,
            "image_quality": 60.0,
            "image_scene": 95.3,
            "image_style": 65.9,
            "image_topic": 95.3,
            "nature_relation": 59.3,
            "object_localization": 51.0,
            "ocr": 74.0,
            "physical_property_reasoning": 45.0,
            "physical_relation": 38.5,
            "social_relation": 71.8,
            "spatial_relationship": 30.9,
            "structuralized_imagetext_understanding": 17.8,
            "Method": [
                "Slime-8B",
                "https://huggingface.co/yifanzhang114/SliME-Llama3-8B"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 341
        },
        {
            "Overall": 58.7,
            "AR": 68.4,
            "CP": 76.7,
            "FP-C": 46.2,
            "FP-S": 52.0,
            "LR": 31.2,
            "RR": 55.9,
            "action_recognition": 88.6,
            "attribute_comparison": 23.1,
            "attribute_recognition": 62.6,
            "celebrity_recognition": 54.2,
            "function_reasoning": 80.2,
            "future_prediction": 50.0,
            "identity_reasoning": 92.7,
            "image_emotion": 80.7,
            "image_quality": 50.6,
            "image_scene": 87.6,
            "image_style": 62.4,
            "image_topic": 96.5,
            "nature_relation": 61.7,
            "object_localization": 28.8,
            "ocr": 66.2,
            "physical_property_reasoning": 36.0,
            "physical_relation": 28.8,
            "social_relation": 67.9,
            "spatial_relationship": 22.2,
            "structuralized_imagetext_understanding": 17.8,
            "Method": [
                "Slime-13B",
                "https://huggingface.co/yifanzhang114/SliME-vicuna-13B"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 342
        },
        {
            "Overall": 74.4,
            "AR": 81.2,
            "CP": 77.7,
            "FP-C": 69.2,
            "FP-S": 78.1,
            "LR": 65.3,
            "RR": 64.5,
            "action_recognition": 87.5,
            "attribute_comparison": 67.9,
            "attribute_recognition": 85.9,
            "celebrity_recognition": 76.3,
            "function_reasoning": 88.7,
            "future_prediction": 66.7,
            "identity_reasoning": 93.9,
            "image_emotion": 67.5,
            "image_quality": 60.0,
            "image_scene": 86.8,
            "image_style": 72.9,
            "image_topic": 96.5,
            "nature_relation": 63.0,
            "object_localization": 61.5,
            "ocr": 93.5,
            "physical_property_reasoning": 63.0,
            "physical_relation": 46.2,
            "social_relation": 78.2,
            "spatial_relationship": 50.6,
            "structuralized_imagetext_understanding": 64.4,
            "Method": [
                "Pixtral-12B",
                "https://huggingface.co/mistralai/Pixtral-12B-2409"
            ],
            "Parameters": "13B",
            "Language Model": "Nemo-12B",
            "Vision Model": "ViT-400M",
            "Org": "Mistral AI",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 343
        },
        {
            "Overall": 78.6,
            "AR": 80.6,
            "CP": 85.7,
            "FP-C": 72.9,
            "FP-S": 82.9,
            "LR": 65.3,
            "RR": 69.7,
            "action_recognition": 86.4,
            "attribute_comparison": 69.2,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 86.4,
            "function_reasoning": 84.0,
            "future_prediction": 66.7,
            "identity_reasoning": 97.6,
            "image_emotion": 78.3,
            "image_quality": 75.3,
            "image_scene": 93.8,
            "image_style": 82.4,
            "image_topic": 94.1,
            "nature_relation": 85.2,
            "object_localization": 67.3,
            "ocr": 88.3,
            "physical_property_reasoning": 63.0,
            "physical_relation": 48.1,
            "social_relation": 67.9,
            "spatial_relationship": 61.7,
            "structuralized_imagetext_understanding": 64.4,
            "Method": [
                "Gemini-1.5-Flash",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 344
        },
        {
            "Overall": 55.5,
            "AR": 73.6,
            "CP": 66.2,
            "FP-C": 43.7,
            "FP-S": 50.5,
            "LR": 31.2,
            "RR": 50.7,
            "action_recognition": 90.9,
            "attribute_comparison": 19.2,
            "attribute_recognition": 58.6,
            "celebrity_recognition": 50.0,
            "function_reasoning": 74.5,
            "future_prediction": 55.6,
            "identity_reasoning": 91.5,
            "image_emotion": 80.7,
            "image_quality": 14.1,
            "image_scene": 85.3,
            "image_style": 45.9,
            "image_topic": 95.3,
            "nature_relation": 38.3,
            "object_localization": 16.3,
            "ocr": 87.0,
            "physical_property_reasoning": 58.0,
            "physical_relation": 55.8,
            "social_relation": 60.3,
            "spatial_relationship": 16.0,
            "structuralized_imagetext_understanding": 13.9,
            "Method": [
                "LLaVA-OneVision-0.5B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-0.5b-ov"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 345
        },
        {
            "Overall": 82.7,
            "AR": 84.0,
            "CP": 88.7,
            "FP-C": 74.1,
            "FP-S": 85.4,
            "LR": 67.6,
            "RR": 84.8,
            "action_recognition": 93.2,
            "attribute_comparison": 76.9,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 84.7,
            "function_reasoning": 90.6,
            "future_prediction": 69.4,
            "identity_reasoning": 98.8,
            "image_emotion": 85.5,
            "image_quality": 82.4,
            "image_scene": 96.1,
            "image_style": 80.0,
            "image_topic": 95.3,
            "nature_relation": 91.4,
            "object_localization": 76.0,
            "ocr": 93.5,
            "physical_property_reasoning": 65.0,
            "physical_relation": 71.2,
            "social_relation": 87.2,
            "spatial_relationship": 50.6,
            "structuralized_imagetext_understanding": 66.3,
            "Method": [
                "LLaVA-OneVision-7B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-7b-ov"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 346
        },
        {
            "Overall": 50.2,
            "AR": 70.5,
            "CP": 63.6,
            "FP-C": 35.2,
            "FP-S": 45.7,
            "LR": 23.7,
            "RR": 40.3,
            "action_recognition": 89.8,
            "attribute_comparison": 2.6,
            "attribute_recognition": 53.5,
            "celebrity_recognition": 44.9,
            "function_reasoning": 69.8,
            "future_prediction": 50.0,
            "identity_reasoning": 85.4,
            "image_emotion": 79.5,
            "image_quality": 4.7,
            "image_scene": 84.5,
            "image_style": 45.9,
            "image_topic": 92.9,
            "nature_relation": 23.5,
            "object_localization": 8.7,
            "ocr": 87.0,
            "physical_property_reasoning": 59.0,
            "physical_relation": 34.6,
            "social_relation": 61.5,
            "spatial_relationship": 7.4,
            "structuralized_imagetext_understanding": 5.0,
            "Method": [
                "LLaVA-OneVision-0.5B (SI)",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-0.5b-si"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 347
        },
        {
            "Overall": 78.0,
            "AR": 83.0,
            "CP": 84.4,
            "FP-C": 67.6,
            "FP-S": 78.6,
            "LR": 60.7,
            "RR": 82.0,
            "action_recognition": 92.0,
            "attribute_comparison": 69.2,
            "attribute_recognition": 82.8,
            "celebrity_recognition": 79.7,
            "function_reasoning": 90.6,
            "future_prediction": 75.0,
            "identity_reasoning": 97.6,
            "image_emotion": 78.3,
            "image_quality": 77.6,
            "image_scene": 93.8,
            "image_style": 71.8,
            "image_topic": 95.3,
            "nature_relation": 87.7,
            "object_localization": 62.5,
            "ocr": 93.5,
            "physical_property_reasoning": 63.0,
            "physical_relation": 59.6,
            "social_relation": 91.0,
            "spatial_relationship": 39.5,
            "structuralized_imagetext_understanding": 50.5,
            "Method": [
                "LLaVA-OneVision-7B (SI)",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-7b-si"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 348
        },
        {
            "Overall": 68.6,
            "AR": 79.2,
            "CP": 74.9,
            "FP-C": 67.2,
            "FP-S": 60.6,
            "LR": 59.5,
            "RR": 64.0,
            "action_recognition": 87.5,
            "attribute_comparison": 70.5,
            "attribute_recognition": 63.6,
            "celebrity_recognition": 55.9,
            "function_reasoning": 81.1,
            "future_prediction": 66.7,
            "identity_reasoning": 92.7,
            "image_emotion": 72.3,
            "image_quality": 75.3,
            "image_scene": 74.4,
            "image_style": 65.9,
            "image_topic": 87.1,
            "nature_relation": 85.2,
            "object_localization": 48.1,
            "ocr": 80.5,
            "physical_property_reasoning": 66.0,
            "physical_relation": 46.2,
            "social_relation": 53.8,
            "spatial_relationship": 42.0,
            "structuralized_imagetext_understanding": 54.5,
            "Method": [
                "Qwen-VL-Plus-0809",
                "https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-qianwen-vl-plus-api"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 349
        },
        {
            "Overall": 85.3,
            "AR": 87.5,
            "CP": 88.9,
            "FP-C": 84.2,
            "FP-S": 88.4,
            "LR": 71.7,
            "RR": 80.6,
            "action_recognition": 94.3,
            "attribute_comparison": 89.7,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 86.4,
            "function_reasoning": 89.6,
            "future_prediction": 79.2,
            "identity_reasoning": 100.0,
            "image_emotion": 80.7,
            "image_quality": 89.4,
            "image_scene": 94.6,
            "image_style": 80.0,
            "image_topic": 96.5,
            "nature_relation": 85.2,
            "object_localization": 79.8,
            "ocr": 96.1,
            "physical_property_reasoning": 75.0,
            "physical_relation": 61.5,
            "social_relation": 88.5,
            "spatial_relationship": 67.9,
            "structuralized_imagetext_understanding": 66.3,
            "Method": [
                "LLaVA-OneVision-72B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-72b-ov"
            ],
            "Parameters": "73B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 351
        },
        {
            "Overall": 82.0,
            "AR": 84.4,
            "CP": 86.1,
            "FP-C": 75.7,
            "FP-S": 84.9,
            "LR": 68.8,
            "RR": 82.0,
            "action_recognition": 90.9,
            "attribute_comparison": 78.2,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 81.4,
            "function_reasoning": 90.6,
            "future_prediction": 73.6,
            "identity_reasoning": 97.6,
            "image_emotion": 84.3,
            "image_quality": 81.2,
            "image_scene": 88.4,
            "image_style": 78.8,
            "image_topic": 96.5,
            "nature_relation": 91.4,
            "object_localization": 76.0,
            "ocr": 94.8,
            "physical_property_reasoning": 67.0,
            "physical_relation": 65.4,
            "social_relation": 83.3,
            "spatial_relationship": 56.8,
            "structuralized_imagetext_understanding": 65.3,
            "Method": [
                "Ovis1.6-Gemma2-9B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B"
            ],
            "Parameters": "10.2B",
            "Language Model": "Gemma2-9B-It",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/09/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 352
        },
        {
            "Overall": 62.5,
            "AR": 74.7,
            "CP": 76.4,
            "FP-C": 51.8,
            "FP-S": 60.6,
            "LR": 31.8,
            "RR": 56.4,
            "action_recognition": 94.3,
            "attribute_comparison": 33.3,
            "attribute_recognition": 71.7,
            "celebrity_recognition": 51.7,
            "function_reasoning": 81.1,
            "future_prediction": 51.4,
            "identity_reasoning": 92.7,
            "image_emotion": 74.7,
            "image_quality": 51.8,
            "image_scene": 89.1,
            "image_style": 65.9,
            "image_topic": 94.1,
            "nature_relation": 55.6,
            "object_localization": 39.4,
            "ocr": 88.3,
            "physical_property_reasoning": 53.0,
            "physical_relation": 30.8,
            "social_relation": 74.4,
            "spatial_relationship": 23.5,
            "structuralized_imagetext_understanding": 17.8,
            "Method": [
                "Eagle-X5-7B",
                "https://huggingface.co/NVEagle/Eagle-X5-7B"
            ],
            "Parameters": "9B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 353
        },
        {
            "Overall": 67.4,
            "AR": 76.0,
            "CP": 77.7,
            "FP-C": 58.7,
            "FP-S": 66.6,
            "LR": 43.9,
            "RR": 63.5,
            "action_recognition": 94.3,
            "attribute_comparison": 56.4,
            "attribute_recognition": 74.7,
            "celebrity_recognition": 56.8,
            "function_reasoning": 82.1,
            "future_prediction": 68.1,
            "identity_reasoning": 93.9,
            "image_emotion": 71.1,
            "image_quality": 54.1,
            "image_scene": 91.5,
            "image_style": 69.4,
            "image_topic": 95.3,
            "nature_relation": 64.2,
            "object_localization": 51.9,
            "ocr": 90.9,
            "physical_property_reasoning": 55.0,
            "physical_relation": 42.3,
            "social_relation": 76.9,
            "spatial_relationship": 22.2,
            "structuralized_imagetext_understanding": 26.7,
            "Method": [
                "Eagle-X5-13B",
                "https://huggingface.co/NVEagle/Eagle-X5-13B"
            ],
            "Parameters": "15B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 354
        },
        {
            "Overall": 19.8,
            "AR": 20.8,
            "CP": 24.0,
            "FP-C": 9.3,
            "FP-S": 24.6,
            "LR": 16.8,
            "RR": 14.7,
            "action_recognition": 10.2,
            "attribute_comparison": 10.3,
            "attribute_recognition": 15.2,
            "celebrity_recognition": 14.4,
            "function_reasoning": 16.0,
            "future_prediction": 23.6,
            "identity_reasoning": 31.7,
            "image_emotion": 31.3,
            "image_quality": 5.9,
            "image_scene": 30.2,
            "image_style": 23.5,
            "image_topic": 25.9,
            "nature_relation": 13.6,
            "object_localization": 6.7,
            "ocr": 76.6,
            "physical_property_reasoning": 17.0,
            "physical_relation": 9.6,
            "social_relation": 19.2,
            "spatial_relationship": 7.4,
            "structuralized_imagetext_understanding": 11.9,
            "Method": [
                "Moondream1",
                "https://huggingface.co/vikhyatk/moondream1"
            ],
            "Parameters": "1.9B",
            "Language Model": "SigLIP-400M",
            "Vision Model": "Phi-1.5",
            "Org": "Moondream",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 355
        },
        {
            "Overall": 70.3,
            "AR": 83.3,
            "CP": 80.5,
            "FP-C": 59.9,
            "FP-S": 69.3,
            "LR": 50.9,
            "RR": 60.2,
            "action_recognition": 95.5,
            "attribute_comparison": 50.0,
            "attribute_recognition": 80.8,
            "celebrity_recognition": 65.3,
            "function_reasoning": 84.0,
            "future_prediction": 65.3,
            "identity_reasoning": 97.6,
            "image_emotion": 75.9,
            "image_quality": 56.5,
            "image_scene": 91.5,
            "image_style": 76.5,
            "image_topic": 96.5,
            "nature_relation": 59.3,
            "object_localization": 46.2,
            "ocr": 92.2,
            "physical_property_reasoning": 71.0,
            "physical_relation": 28.8,
            "social_relation": 82.1,
            "spatial_relationship": 30.9,
            "structuralized_imagetext_understanding": 40.6,
            "Method": [
                "MiniMonkey",
                "https://huggingface.co/mx262/MiniMonkey"
            ],
            "Parameters": "2.2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "HUST",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 357
        },
        {
            "Overall": 75.7,
            "AR": 78.5,
            "CP": 84.2,
            "FP-C": 62.3,
            "FP-S": 80.4,
            "LR": 56.1,
            "RR": 76.3,
            "action_recognition": 94.3,
            "attribute_comparison": 59.0,
            "attribute_recognition": 84.8,
            "celebrity_recognition": 88.1,
            "function_reasoning": 85.8,
            "future_prediction": 70.8,
            "identity_reasoning": 96.3,
            "image_emotion": 77.1,
            "image_quality": 72.9,
            "image_scene": 94.6,
            "image_style": 74.1,
            "image_topic": 96.5,
            "nature_relation": 74.1,
            "object_localization": 56.7,
            "ocr": 94.8,
            "physical_property_reasoning": 56.0,
            "physical_relation": 71.2,
            "social_relation": 82.1,
            "spatial_relationship": 30.9,
            "structuralized_imagetext_understanding": 45.5,
            "Method": [
                "XinYuan-VL-2B-Instruct",
                "https://huggingface.co/Cylingo/Xinyuan-VL-2B"
            ],
            "Parameters": "2B",
            "Language Model": "Qwen2-1.5B",
            "Vision Model": "QwenViT",
            "Org": "Cylingo",
            "Time": "2024/09/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 359
        },
        {
            "Overall": 65.8,
            "AR": 72.6,
            "CP": 73.9,
            "FP-C": 57.5,
            "FP-S": 71.4,
            "LR": 42.8,
            "RR": 56.9,
            "action_recognition": 88.6,
            "attribute_comparison": 51.3,
            "attribute_recognition": 76.8,
            "celebrity_recognition": 70.3,
            "function_reasoning": 77.4,
            "future_prediction": 58.3,
            "identity_reasoning": 93.9,
            "image_emotion": 75.9,
            "image_quality": 44.7,
            "image_scene": 86.8,
            "image_style": 60.0,
            "image_topic": 95.3,
            "nature_relation": 48.1,
            "object_localization": 51.0,
            "ocr": 93.5,
            "physical_property_reasoning": 50.0,
            "physical_relation": 36.5,
            "social_relation": 79.5,
            "spatial_relationship": 29.6,
            "structuralized_imagetext_understanding": 31.7,
            "Method": [
                "Llama-3.2-11B-Vision-Instruct",
                "https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct"
            ],
            "Parameters": "11B",
            "Language Model": "Llama-3.1-8B",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/10/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 360
        },
        {
            "Overall": 84.5,
            "AR": 85.4,
            "CP": 87.8,
            "FP-C": 80.2,
            "FP-S": 89.9,
            "LR": 72.3,
            "RR": 81.0,
            "action_recognition": 92.0,
            "attribute_comparison": 78.2,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 95.8,
            "function_reasoning": 90.6,
            "future_prediction": 76.4,
            "identity_reasoning": 98.8,
            "image_emotion": 75.9,
            "image_quality": 83.5,
            "image_scene": 96.9,
            "image_style": 82.4,
            "image_topic": 95.3,
            "nature_relation": 93.8,
            "object_localization": 76.0,
            "ocr": 94.8,
            "physical_property_reasoning": 69.0,
            "physical_relation": 53.8,
            "social_relation": 85.9,
            "spatial_relationship": 69.1,
            "structuralized_imagetext_understanding": 69.3,
            "Method": [
                "Step-1.5V",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "Step-1.5",
            "Vision Model": "stepencoder",
            "Org": "StepFun",
            "Time": "2024/10/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 322
        },
        {
            "Overall": 80.3,
            "AR": 83.3,
            "CP": 86.9,
            "FP-C": 71.3,
            "FP-S": 85.4,
            "LR": 65.9,
            "RR": 74.4,
            "action_recognition": 94.3,
            "attribute_comparison": 76.9,
            "attribute_recognition": 88.9,
            "celebrity_recognition": 85.6,
            "function_reasoning": 84.9,
            "future_prediction": 72.2,
            "identity_reasoning": 96.3,
            "image_emotion": 78.3,
            "image_quality": 82.4,
            "image_scene": 95.3,
            "image_style": 77.6,
            "image_topic": 96.5,
            "nature_relation": 77.8,
            "object_localization": 75.0,
            "ocr": 94.8,
            "physical_property_reasoning": 71.0,
            "physical_relation": 50.0,
            "social_relation": 87.2,
            "spatial_relationship": 40.7,
            "structuralized_imagetext_understanding": 61.4,
            "Method": [
                "POINTS-Yi-1.5-9B",
                "https://huggingface.co/WePOINTS/POINTS-Yi-1-5-9B-Chat"
            ],
            "Parameters": "9.5B",
            "Language Model": "Yi-1.5-9B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "WeChat",
            "Time": "2024/10/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTS-Yi-1.5-9B-Chat",
            "key": 362
        },
        {
            "Overall": 79.0,
            "AR": 81.6,
            "CP": 85.7,
            "FP-C": 70.9,
            "FP-S": 83.2,
            "LR": 63.0,
            "RR": 75.4,
            "action_recognition": 93.2,
            "attribute_comparison": 74.4,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 79.7,
            "function_reasoning": 86.8,
            "future_prediction": 72.2,
            "identity_reasoning": 97.6,
            "image_emotion": 75.9,
            "image_quality": 83.5,
            "image_scene": 92.2,
            "image_style": 76.5,
            "image_topic": 96.5,
            "nature_relation": 77.8,
            "object_localization": 71.2,
            "ocr": 94.8,
            "physical_property_reasoning": 63.0,
            "physical_relation": 61.5,
            "social_relation": 82.1,
            "spatial_relationship": 43.2,
            "structuralized_imagetext_understanding": 56.4,
            "Method": [
                "POINTS-Qwen2.5-7B",
                "https://huggingface.co/WePOINTS/POINTS-Qwen-2-5-7B-Chat"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen-2.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "WeChat",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTS-Qwen-2.5-7B-Chat",
            "key": 363
        },
        {
            "Overall": 0.6,
            "AR": 0.3,
            "CP": 0.9,
            "FP-C": 0.4,
            "FP-S": 1.0,
            "LR": 0.0,
            "RR": 0.5,
            "action_recognition": 1.1,
            "attribute_comparison": 0.0,
            "attribute_recognition": 2.0,
            "celebrity_recognition": 0.8,
            "function_reasoning": 0.9,
            "future_prediction": 0.0,
            "identity_reasoning": 0.0,
            "image_emotion": 0.0,
            "image_quality": 0.0,
            "image_scene": 1.6,
            "image_style": 0.0,
            "image_topic": 2.4,
            "nature_relation": 1.2,
            "object_localization": 1.0,
            "ocr": 0.0,
            "physical_property_reasoning": 0.0,
            "physical_relation": 0.0,
            "social_relation": 0.0,
            "spatial_relationship": 0.0,
            "structuralized_imagetext_understanding": 0.0,
            "Method": [
                "Kosmos2",
                "https://huggingface.co/microsoft/kosmos-2-patch14-224"
            ],
            "Parameters": "1.7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Microsoft",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kosmos2",
            "key": 364
        },
        {
            "Overall": 77.8,
            "AR": 79.2,
            "CP": 81.6,
            "FP-C": 69.6,
            "FP-S": 86.2,
            "LR": 63.6,
            "RR": 73.0,
            "action_recognition": 92.0,
            "attribute_comparison": 64.1,
            "attribute_recognition": 86.9,
            "celebrity_recognition": 90.7,
            "function_reasoning": 86.8,
            "future_prediction": 69.4,
            "identity_reasoning": 97.6,
            "image_emotion": 74.7,
            "image_quality": 70.6,
            "image_scene": 92.2,
            "image_style": 68.2,
            "image_topic": 96.5,
            "nature_relation": 81.5,
            "object_localization": 73.1,
            "ocr": 96.1,
            "physical_property_reasoning": 56.0,
            "physical_relation": 51.9,
            "social_relation": 78.2,
            "spatial_relationship": 50.6,
            "structuralized_imagetext_understanding": 59.4,
            "Method": [
                "Llama-3.2-90B-Vision-Instruct",
                "https://huggingface.co/meta-llama/Llama-3.2-90B-Vision-Instruct"
            ],
            "Parameters": "88.6B",
            "Language Model": "Llama-3.1-70B",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Llama-3.2-90B-Vision-Instruct",
            "key": 365
        },
        {
            "Overall": 80.2,
            "AR": 83.7,
            "CP": 82.4,
            "FP-C": 76.9,
            "FP-S": 87.7,
            "LR": 59.5,
            "RR": 76.8,
            "action_recognition": 93.2,
            "attribute_comparison": 73.1,
            "attribute_recognition": 94.9,
            "celebrity_recognition": 88.1,
            "function_reasoning": 90.6,
            "future_prediction": 56.9,
            "identity_reasoning": 98.8,
            "image_emotion": 66.3,
            "image_quality": 82.4,
            "image_scene": 89.9,
            "image_style": 74.1,
            "image_topic": 95.3,
            "nature_relation": 80.2,
            "object_localization": 72.1,
            "ocr": 98.7,
            "physical_property_reasoning": 64.0,
            "physical_relation": 63.5,
            "social_relation": 82.1,
            "spatial_relationship": 63.0,
            "structuralized_imagetext_understanding": 61.4,
            "Method": [
                "NVLM-D-72B",
                "https://huggingface.co/nvidia/NVLM-D-72B"
            ],
            "Parameters": "79.4B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "InternViT-6B",
            "Org": "Nvidia",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "NVLM",
            "key": 366
        },
        {
            "Overall": 28.7,
            "AR": 30.2,
            "CP": 33.6,
            "FP-C": 21.9,
            "FP-S": 31.4,
            "LR": 15.0,
            "RR": 29.9,
            "action_recognition": 26.1,
            "attribute_comparison": 21.8,
            "attribute_recognition": 23.2,
            "celebrity_recognition": 21.2,
            "function_reasoning": 18.9,
            "future_prediction": 22.2,
            "identity_reasoning": 37.8,
            "image_emotion": 37.3,
            "image_quality": 27.1,
            "image_scene": 36.4,
            "image_style": 23.5,
            "image_topic": 42.4,
            "nature_relation": 37.0,
            "object_localization": 12.5,
            "ocr": 83.1,
            "physical_property_reasoning": 36.0,
            "physical_relation": 13.5,
            "social_relation": 33.3,
            "spatial_relationship": 17.3,
            "structuralized_imagetext_understanding": 9.9,
            "Method": [
                "Moondream2",
                "https://huggingface.co/vikhyatk/moondream2"
            ],
            "Parameters": "1.9B",
            "Language Model": "SigLIP-400M",
            "Vision Model": "Phi-1.5",
            "Org": "Moondream",
            "Time": "2024/10/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Moondream2",
            "key": 356
        },
        {
            "Overall": 75.2,
            "AR": 78.8,
            "CP": 79.7,
            "FP-C": 66.0,
            "FP-S": 79.6,
            "LR": 63.6,
            "RR": 72.5,
            "action_recognition": 90.9,
            "attribute_comparison": 69.2,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 76.3,
            "function_reasoning": 79.2,
            "future_prediction": 72.2,
            "identity_reasoning": 97.6,
            "image_emotion": 65.1,
            "image_quality": 71.8,
            "image_scene": 91.5,
            "image_style": 68.2,
            "image_topic": 95.3,
            "nature_relation": 75.3,
            "object_localization": 62.5,
            "ocr": 93.5,
            "physical_property_reasoning": 63.0,
            "physical_relation": 63.5,
            "social_relation": 75.6,
            "spatial_relationship": 35.8,
            "structuralized_imagetext_understanding": 57.4,
            "Method": [
                "Molmo-7B-D",
                "https://huggingface.co/allenai/Molmo-7B-D-0924"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 361,
            "dir_name": "molmo-7B-D-0924"
        },
        {
            "Overall": 59.4,
            "AR": 63.5,
            "CP": 71.5,
            "FP-C": 60.7,
            "FP-S": 50.0,
            "LR": 44.5,
            "RR": 55.5,
            "action_recognition": 86.4,
            "attribute_comparison": 65.4,
            "attribute_recognition": 58.6,
            "celebrity_recognition": 40.7,
            "function_reasoning": 63.2,
            "future_prediction": 61.1,
            "identity_reasoning": 87.8,
            "image_emotion": 66.3,
            "image_quality": 69.4,
            "image_scene": 82.2,
            "image_style": 44.7,
            "image_topic": 89.4,
            "nature_relation": 54.3,
            "object_localization": 26.0,
            "ocr": 85.7,
            "physical_property_reasoning": 44.0,
            "physical_relation": 36.5,
            "social_relation": 69.2,
            "spatial_relationship": 28.4,
            "structuralized_imagetext_understanding": 32.7,
            "Method": [
                "Molmo-7B-O",
                "https://huggingface.co/allenai/Molmo-7B-O-0924"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 367,
            "dir_name": "molmo-7B-O-0924"
        },
        {
            "Overall": 46.6,
            "AR": 55.6,
            "CP": 60.2,
            "FP-C": 39.7,
            "FP-S": 43.2,
            "LR": 30.1,
            "RR": 32.2,
            "action_recognition": 75.0,
            "attribute_comparison": 23.1,
            "attribute_recognition": 59.6,
            "celebrity_recognition": 32.2,
            "function_reasoning": 50.9,
            "future_prediction": 48.6,
            "identity_reasoning": 84.1,
            "image_emotion": 66.3,
            "image_quality": 27.1,
            "image_scene": 79.8,
            "image_style": 36.5,
            "image_topic": 81.2,
            "nature_relation": 14.8,
            "object_localization": 8.7,
            "ocr": 85.7,
            "physical_property_reasoning": 37.0,
            "physical_relation": 25.0,
            "social_relation": 55.1,
            "spatial_relationship": 17.3,
            "structuralized_imagetext_understanding": 16.8,
            "Method": [
                "MolmoE-1B",
                "https://huggingface.co/allenai/MolmoE-1B-0924"
            ],
            "Parameters": "7.2B",
            "Language Model": "OLMoE-1B-7B-0924",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "molmoE-1B-0924",
            "key": 368
        },
        {
            "Overall": 52.2,
            "AR": 63.5,
            "CP": 68.7,
            "FP-C": 40.5,
            "FP-S": 50.0,
            "LR": 23.1,
            "RR": 42.2,
            "action_recognition": 89.8,
            "attribute_comparison": 7.7,
            "attribute_recognition": 67.7,
            "celebrity_recognition": 39.8,
            "function_reasoning": 67.9,
            "future_prediction": 47.2,
            "identity_reasoning": 92.7,
            "image_emotion": 72.3,
            "image_quality": 25.9,
            "image_scene": 84.5,
            "image_style": 60.0,
            "image_topic": 92.9,
            "nature_relation": 35.8,
            "object_localization": 22.1,
            "ocr": 80.5,
            "physical_property_reasoning": 35.0,
            "physical_relation": 17.3,
            "social_relation": 65.4,
            "spatial_relationship": 18.5,
            "structuralized_imagetext_understanding": 5.9,
            "Method": [
                "Janus-1.3B",
                "https://huggingface.co/deepseek-ai/Janus-1.3B"
            ],
            "Parameters": "2.1B",
            "Language Model": "DeepSeek-1B",
            "Vision Model": "SigLIP-400M",
            "Org": "deepseek",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Janus-1.3B",
            "key": 370
        },
        {
            "Overall": 69.4,
            "AR": 77.1,
            "CP": 80.5,
            "FP-C": 59.5,
            "FP-S": 67.1,
            "LR": 52.6,
            "RR": 64.0,
            "action_recognition": 92.0,
            "attribute_comparison": 57.7,
            "attribute_recognition": 77.8,
            "celebrity_recognition": 62.7,
            "function_reasoning": 84.0,
            "future_prediction": 63.9,
            "identity_reasoning": 93.9,
            "image_emotion": 73.5,
            "image_quality": 57.6,
            "image_scene": 93.8,
            "image_style": 75.3,
            "image_topic": 95.3,
            "nature_relation": 54.3,
            "object_localization": 43.3,
            "ocr": 92.2,
            "physical_property_reasoning": 56.0,
            "physical_relation": 50.0,
            "social_relation": 83.3,
            "spatial_relationship": 25.9,
            "structuralized_imagetext_understanding": 44.6,
            "Method": [
                "Vintern-3B-beta",
                "https://huggingface.co/5CD-AI/Vintern-3B-beta"
            ],
            "Parameters": "3.7B",
            "Language Model": "Qwen-2.5-3B",
            "Vision Model": "InternViT-300M",
            "Org": "Fifth Civil Defender",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Vintern-3B-beta",
            "key": 371
        },
        {
            "Overall": 74.7,
            "AR": 83.0,
            "CP": 79.0,
            "FP-C": 66.4,
            "FP-S": 76.6,
            "LR": 63.6,
            "RR": 68.7,
            "action_recognition": 92.0,
            "attribute_comparison": 73.1,
            "attribute_recognition": 82.8,
            "celebrity_recognition": 70.3,
            "function_reasoning": 84.9,
            "future_prediction": 79.2,
            "identity_reasoning": 98.8,
            "image_emotion": 79.5,
            "image_quality": 68.2,
            "image_scene": 91.5,
            "image_style": 56.5,
            "image_topic": 92.9,
            "nature_relation": 69.1,
            "object_localization": 64.4,
            "ocr": 94.8,
            "physical_property_reasoning": 68.0,
            "physical_relation": 48.1,
            "social_relation": 82.1,
            "spatial_relationship": 32.1,
            "structuralized_imagetext_understanding": 52.5,
            "Method": [
                "Ovis1.6-Llama3.2-3B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Llama3.2-3B"
            ],
            "Parameters": "4.1B",
            "Language Model": "Llama-3.2-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis1.6-Llama3.2-3B",
            "key": 372
        },
        {
            "Overall": 76.3,
            "AR": 83.0,
            "CP": 82.9,
            "FP-C": 66.8,
            "FP-S": 79.1,
            "LR": 54.3,
            "RR": 76.8,
            "action_recognition": 94.3,
            "attribute_comparison": 73.1,
            "attribute_recognition": 88.9,
            "celebrity_recognition": 72.9,
            "function_reasoning": 84.9,
            "future_prediction": 69.4,
            "identity_reasoning": 96.3,
            "image_emotion": 80.7,
            "image_quality": 64.7,
            "image_scene": 91.5,
            "image_style": 76.5,
            "image_topic": 96.5,
            "nature_relation": 76.5,
            "object_localization": 66.3,
            "ocr": 93.5,
            "physical_property_reasoning": 70.0,
            "physical_relation": 57.7,
            "social_relation": 89.7,
            "spatial_relationship": 30.9,
            "structuralized_imagetext_understanding": 43.6,
            "Method": [
                "Aquila-VL-2B",
                "https://huggingface.co/BAAI/Aquila-VL-2B-llava-qwen"
            ],
            "Parameters": "2.2B",
            "Language Model": "Qwen-2.5-1.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "BAAI",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Aquila-VL-2B",
            "key": 373
        },
        {
            "Overall": 86.7,
            "AR": 85.1,
            "CP": 87.4,
            "FP-C": 88.3,
            "FP-S": 93.5,
            "LR": 78.0,
            "RR": 80.1,
            "action_recognition": 95.5,
            "attribute_comparison": 91.0,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 96.6,
            "function_reasoning": 87.7,
            "future_prediction": 80.6,
            "identity_reasoning": 97.6,
            "image_emotion": 77.1,
            "image_quality": 84.7,
            "image_scene": 95.3,
            "image_style": 78.8,
            "image_topic": 96.5,
            "nature_relation": 87.7,
            "object_localization": 86.5,
            "ocr": 97.4,
            "physical_property_reasoning": 72.0,
            "physical_relation": 57.7,
            "social_relation": 87.2,
            "spatial_relationship": 77.8,
            "structuralized_imagetext_understanding": 76.2,
            "Method": [
                "Qwen2-VL-72B",
                "https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct"
            ],
            "Parameters": "73.4B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/10/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2-VL-72B-Instruct",
            "key": 378
        },
        {
            "Overall": 80.3,
            "AR": 84.4,
            "CP": 85.0,
            "FP-C": 72.1,
            "FP-S": 80.2,
            "LR": 71.7,
            "RR": 81.0,
            "action_recognition": 93.2,
            "attribute_comparison": 73.1,
            "attribute_recognition": 84.8,
            "celebrity_recognition": 83.1,
            "function_reasoning": 90.6,
            "future_prediction": 80.6,
            "identity_reasoning": 97.6,
            "image_emotion": 74.7,
            "image_quality": 77.6,
            "image_scene": 93.0,
            "image_style": 80.0,
            "image_topic": 95.3,
            "nature_relation": 86.4,
            "object_localization": 60.6,
            "ocr": 96.1,
            "physical_property_reasoning": 67.0,
            "physical_relation": 65.4,
            "social_relation": 85.9,
            "spatial_relationship": 48.1,
            "structuralized_imagetext_understanding": 65.3,
            "Method": [
                "Bumblebee-7B-v2.2",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "Mono-Encoder",
            "Org": "Monolith Foundation",
            "Time": "2024/10/30",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 379
        },
        {
            "Overall": 83.3,
            "AR": 84.0,
            "CP": 87.6,
            "FP-C": 82.6,
            "FP-S": 84.2,
            "LR": 74.0,
            "RR": 79.6,
            "action_recognition": 93.2,
            "attribute_comparison": 83.3,
            "attribute_recognition": 85.9,
            "celebrity_recognition": 84.7,
            "function_reasoning": 87.7,
            "future_prediction": 73.6,
            "identity_reasoning": 95.1,
            "image_emotion": 73.5,
            "image_quality": 91.8,
            "image_scene": 96.1,
            "image_style": 76.5,
            "image_topic": 95.3,
            "nature_relation": 88.9,
            "object_localization": 74.0,
            "ocr": 94.8,
            "physical_property_reasoning": 71.0,
            "physical_relation": 59.6,
            "social_relation": 83.3,
            "spatial_relationship": 70.4,
            "structuralized_imagetext_understanding": 74.3,
            "Method": [
                "BlueLM-V-3B",
                "https://developers.vivo.com/product/ai/bluelm"
            ],
            "Parameters": "3B",
            "Language Model": "BlueLM-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "vivo",
            "Time": "2024/10/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 358,
            "dir_name": "BlueLM_V"
        },
        {
            "Overall": 67.2,
            "AR": 77.1,
            "CP": 78.2,
            "FP-C": 58.7,
            "FP-S": 63.8,
            "LR": 43.4,
            "RR": 64.9,
            "action_recognition": 94.3,
            "attribute_comparison": 55.1,
            "attribute_recognition": 70.7,
            "celebrity_recognition": 64.4,
            "function_reasoning": 81.1,
            "future_prediction": 58.3,
            "identity_reasoning": 95.1,
            "image_emotion": 77.1,
            "image_quality": 55.3,
            "image_scene": 93.0,
            "image_style": 62.4,
            "image_topic": 95.3,
            "nature_relation": 69.1,
            "object_localization": 40.4,
            "ocr": 85.7,
            "physical_property_reasoning": 58.0,
            "physical_relation": 38.5,
            "social_relation": 78.2,
            "spatial_relationship": 23.5,
            "structuralized_imagetext_understanding": 32.7,
            "Method": [
                "Falcon2-VLM-11B",
                "https://huggingface.co/tiiuae/falcon-11B-vlm"
            ],
            "Parameters": "11.4B",
            "Language Model": "Falcon2-11B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Technology Innovation Institute",
            "Time": "2024/10/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Falcon2-VLM-11B",
            "key": 380
        },
        {
            "Overall": 42.2,
            "AR": 52.8,
            "CP": 62.3,
            "FP-C": 26.3,
            "FP-S": 35.4,
            "LR": 17.3,
            "RR": 35.1,
            "action_recognition": 62.5,
            "attribute_comparison": 6.4,
            "attribute_recognition": 42.4,
            "celebrity_recognition": 23.7,
            "function_reasoning": 54.7,
            "future_prediction": 36.1,
            "identity_reasoning": 76.8,
            "image_emotion": 68.7,
            "image_quality": 34.1,
            "image_scene": 77.5,
            "image_style": 42.4,
            "image_topic": 81.2,
            "nature_relation": 23.5,
            "object_localization": 6.7,
            "ocr": 83.1,
            "physical_property_reasoning": 31.0,
            "physical_relation": 9.6,
            "social_relation": 64.1,
            "spatial_relationship": 6.2,
            "structuralized_imagetext_understanding": 4.0,
            "Method": [
                "H2OVL-800M",
                "https://huggingface.co/h2oai/h2ovl-mississippi-800m"
            ],
            "Parameters": "0.83B",
            "Language Model": "H2O-DANUBE3-500M",
            "Vision Model": "InternViT-300M",
            "Org": "H2O.ai",
            "Time": "2024/10/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "h2ovl-mississippi-1b",
            "key": 381
        },
        {
            "Overall": 62.9,
            "AR": 64.9,
            "CP": 79.4,
            "FP-C": 57.9,
            "FP-S": 57.3,
            "LR": 41.0,
            "RR": 58.3,
            "action_recognition": 94.3,
            "attribute_comparison": 50.0,
            "attribute_recognition": 73.7,
            "celebrity_recognition": 31.4,
            "function_reasoning": 71.7,
            "future_prediction": 48.6,
            "identity_reasoning": 90.2,
            "image_emotion": 73.5,
            "image_quality": 61.2,
            "image_scene": 90.7,
            "image_style": 71.8,
            "image_topic": 94.1,
            "nature_relation": 51.9,
            "object_localization": 45.2,
            "ocr": 92.2,
            "physical_property_reasoning": 37.0,
            "physical_relation": 34.6,
            "social_relation": 80.8,
            "spatial_relationship": 25.9,
            "structuralized_imagetext_understanding": 35.6,
            "Method": [
                "H2OVL-2B",
                "https://huggingface.co/h2oai/h2ovl-mississippi-2b"
            ],
            "Parameters": "2.2B",
            "Language Model": "H2O-DANUBE2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "H2O.ai",
            "Time": "2024/10/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "h2ovl-mississippi-2b",
            "key": 382
        },
        {
            "Overall": 50.3,
            "AR": 52.4,
            "CP": 47.1,
            "FP-C": 57.1,
            "FP-S": 46.7,
            "LR": 55.5,
            "RR": 48.8,
            "action_recognition": 42.0,
            "attribute_comparison": 91.0,
            "attribute_recognition": 46.5,
            "celebrity_recognition": 54.2,
            "function_reasoning": 44.3,
            "future_prediction": 80.6,
            "identity_reasoning": 36.6,
            "image_emotion": 33.7,
            "image_quality": 84.7,
            "image_scene": 52.7,
            "image_style": 35.3,
            "image_topic": 25.9,
            "nature_relation": 74.1,
            "object_localization": 45.2,
            "ocr": 37.7,
            "physical_property_reasoning": 74.0,
            "physical_relation": 30.8,
            "social_relation": 34.6,
            "spatial_relationship": 40.7,
            "structuralized_imagetext_understanding": 37.6,
            "Method": [
                "Qwen-VL-Max-0809",
                "https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-qianwen-vl-plus-api"
            ],
            "Parameters": "72B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/09/12",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "Qwen-VL-Max-0809",
            "key": 384
        },
        {
            "Overall": 83.5,
            "AR": 82.3,
            "CP": 84.6,
            "FP-C": 80.6,
            "FP-S": 88.4,
            "LR": 82.7,
            "RR": 77.3,
            "action_recognition": 84.1,
            "attribute_comparison": 84.6,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 93.2,
            "function_reasoning": 87.7,
            "future_prediction": 73.6,
            "identity_reasoning": 95.1,
            "image_emotion": 68.7,
            "image_quality": 78.8,
            "image_scene": 93.8,
            "image_style": 81.2,
            "image_topic": 95.3,
            "nature_relation": 87.7,
            "object_localization": 76.0,
            "ocr": 94.8,
            "physical_property_reasoning": 66.0,
            "physical_relation": 53.8,
            "social_relation": 82.1,
            "spatial_relationship": 72.8,
            "structuralized_imagetext_understanding": 89.1,
            "Method": [
                "Claude3.5-Sonnet-20241022",
                "https://docs.anthropic.com/en/docs/build-with-claude/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/11/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Claude3-5V_Sonnet_20241022",
            "key": 376
        },
        {
            "Overall": 83.0,
            "AR": 82.3,
            "CP": 86.3,
            "FP-C": 77.3,
            "FP-S": 88.7,
            "LR": 75.7,
            "RR": 78.7,
            "action_recognition": 93.2,
            "attribute_comparison": 76.9,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 85.6,
            "function_reasoning": 89.6,
            "future_prediction": 77.8,
            "identity_reasoning": 98.8,
            "image_emotion": 79.5,
            "image_quality": 84.7,
            "image_scene": 94.6,
            "image_style": 74.1,
            "image_topic": 94.1,
            "nature_relation": 80.2,
            "object_localization": 82.7,
            "ocr": 96.1,
            "physical_property_reasoning": 61.0,
            "physical_relation": 59.6,
            "social_relation": 89.7,
            "spatial_relationship": 60.5,
            "structuralized_imagetext_understanding": 74.3,
            "Method": [
                "RBDash-v1.5",
                "https://huggingface.co/RBDash-Team/RBDash-v1.5"
            ],
            "Parameters": "79B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "CLIP ViT-L/14\nInternViT-6B",
            "Org": "DLUT",
            "Time": "2024/11/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "RBDash_72b",
            "key": 388
        },
        {
            "Overall": 83.4,
            "AR": 86.8,
            "CP": 88.7,
            "FP-C": 77.7,
            "FP-S": 84.4,
            "LR": 68.2,
            "RR": 83.9,
            "action_recognition": 95.5,
            "attribute_comparison": 80.8,
            "attribute_recognition": 84.8,
            "celebrity_recognition": 92.4,
            "function_reasoning": 87.7,
            "future_prediction": 77.8,
            "identity_reasoning": 100.0,
            "image_emotion": 86.7,
            "image_quality": 84.7,
            "image_scene": 93.0,
            "image_style": 81.2,
            "image_topic": 95.3,
            "nature_relation": 93.8,
            "object_localization": 66.3,
            "ocr": 96.1,
            "physical_property_reasoning": 75.0,
            "physical_relation": 65.4,
            "social_relation": 85.9,
            "spatial_relationship": 55.6,
            "structuralized_imagetext_understanding": 61.4,
            "Method": [
                "Awaker2.5-VL",
                "https://github.com/MetabrainAGI/Awaker"
            ],
            "Parameters": "10.8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "QwenViT",
            "Org": "MetabrainAGI",
            "Time": "2024/11/23",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 389
        },
        {
            "Overall": 78.0,
            "AR": 77.8,
            "CP": 83.3,
            "FP-C": 70.4,
            "FP-S": 85.7,
            "LR": 62.4,
            "RR": 73.9,
            "action_recognition": 94.3,
            "attribute_comparison": 69.2,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 81.4,
            "function_reasoning": 84.9,
            "future_prediction": 63.9,
            "identity_reasoning": 96.3,
            "image_emotion": 73.5,
            "image_quality": 77.6,
            "image_scene": 91.5,
            "image_style": 72.9,
            "image_topic": 96.5,
            "nature_relation": 77.8,
            "object_localization": 76.9,
            "ocr": 93.5,
            "physical_property_reasoning": 55.0,
            "physical_relation": 50.0,
            "social_relation": 85.9,
            "spatial_relationship": 45.7,
            "structuralized_imagetext_understanding": 61.4,
            "Method": [
                "InternVL2-8B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/11/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2-8B-MPO",
            "key": 390
        },
        {
            "Overall": 77.2,
            "AR": 74.0,
            "CP": 83.1,
            "FP-C": 68.8,
            "FP-S": 86.4,
            "LR": 64.2,
            "RR": 72.0,
            "action_recognition": 93.2,
            "attribute_comparison": 67.9,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 82.2,
            "function_reasoning": 80.2,
            "future_prediction": 68.1,
            "identity_reasoning": 93.9,
            "image_emotion": 73.5,
            "image_quality": 80.0,
            "image_scene": 92.2,
            "image_style": 68.2,
            "image_topic": 96.5,
            "nature_relation": 76.5,
            "object_localization": 79.8,
            "ocr": 96.1,
            "physical_property_reasoning": 51.0,
            "physical_relation": 46.2,
            "social_relation": 84.6,
            "spatial_relationship": 43.2,
            "structuralized_imagetext_understanding": 61.4,
            "Method": [
                "InternVL2-8B-MPO-CoT",
                "https://huggingface.co/OpenGVLab/InternVL2-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/11/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2-8B-MPO-CoT",
            "key": 391
        },
        {
            "Overall": 75.2,
            "AR": 79.5,
            "CP": 81.8,
            "FP-C": 66.4,
            "FP-S": 78.4,
            "LR": 60.7,
            "RR": 71.1,
            "action_recognition": 90.9,
            "attribute_comparison": 59.0,
            "attribute_recognition": 88.9,
            "celebrity_recognition": 72.9,
            "function_reasoning": 86.8,
            "future_prediction": 68.1,
            "identity_reasoning": 89.0,
            "image_emotion": 73.5,
            "image_quality": 67.1,
            "image_scene": 91.5,
            "image_style": 76.5,
            "image_topic": 95.3,
            "nature_relation": 76.5,
            "object_localization": 68.3,
            "ocr": 87.0,
            "physical_property_reasoning": 64.0,
            "physical_relation": 48.1,
            "social_relation": 80.8,
            "spatial_relationship": 46.9,
            "structuralized_imagetext_understanding": 55.4,
            "Method": [
                "Eagle-X5-34B-Chat",
                "https://huggingface.co/NVEagle/Eagle-X5-34B-Chat"
            ],
            "Parameters": "36.8B",
            "Language Model": "Yi-34B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/11/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Eagle-X5-34B-Chat",
            "key": 395
        },
        {
            "Overall": 84.3,
            "AR": 87.2,
            "CP": 86.7,
            "FP-C": 80.6,
            "FP-S": 88.4,
            "LR": 72.3,
            "RR": 81.5,
            "action_recognition": 92.0,
            "attribute_comparison": 84.6,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 86.4,
            "function_reasoning": 87.7,
            "future_prediction": 77.8,
            "identity_reasoning": 98.8,
            "image_emotion": 78.3,
            "image_quality": 81.2,
            "image_scene": 93.8,
            "image_style": 80.0,
            "image_topic": 96.5,
            "nature_relation": 88.9,
            "object_localization": 80.8,
            "ocr": 96.1,
            "physical_property_reasoning": 77.0,
            "physical_relation": 69.2,
            "social_relation": 82.1,
            "spatial_relationship": 64.2,
            "structuralized_imagetext_understanding": 68.3,
            "Method": [
                "Ovis1.6-Gemma2-27B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-27B"
            ],
            "Parameters": "28.9B",
            "Language Model": "Gemma2-27B",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/11/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis1.6-Gemma2-27B",
            "key": 396
        },
        {
            "Overall": 78.3,
            "AR": 83.0,
            "CP": 79.2,
            "FP-C": 68.0,
            "FP-S": 86.2,
            "LR": 68.2,
            "RR": 74.9,
            "action_recognition": 89.8,
            "attribute_comparison": 69.2,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 86.4,
            "function_reasoning": 90.6,
            "future_prediction": 70.8,
            "identity_reasoning": 96.3,
            "image_emotion": 50.6,
            "image_quality": 84.7,
            "image_scene": 90.7,
            "image_style": 68.2,
            "image_topic": 95.3,
            "nature_relation": 82.7,
            "object_localization": 74.0,
            "ocr": 96.1,
            "physical_property_reasoning": 64.0,
            "physical_relation": 61.5,
            "social_relation": 75.6,
            "spatial_relationship": 43.2,
            "structuralized_imagetext_understanding": 66.3,
            "Method": [
                "Aria",
                "https://huggingface.co/rhymes-ai/Aria"
            ],
            "Parameters": "25.3B",
            "Language Model": "Aria-MoE",
            "Vision Model": "SigLIP-400M",
            "Org": "Rhymes AI",
            "Time": "2024/12/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Aria",
            "key": 401
        },
        {
            "Overall": 82.1,
            "AR": 84.4,
            "CP": 85.4,
            "FP-C": 76.1,
            "FP-S": 86.7,
            "LR": 68.2,
            "RR": 81.5,
            "action_recognition": 92.0,
            "attribute_comparison": 78.2,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 88.1,
            "function_reasoning": 89.6,
            "future_prediction": 77.8,
            "identity_reasoning": 97.6,
            "image_emotion": 78.3,
            "image_quality": 80.0,
            "image_scene": 91.5,
            "image_style": 78.8,
            "image_topic": 95.3,
            "nature_relation": 88.9,
            "object_localization": 70.2,
            "ocr": 94.8,
            "physical_property_reasoning": 68.0,
            "physical_relation": 63.5,
            "social_relation": 85.9,
            "spatial_relationship": 56.8,
            "structuralized_imagetext_understanding": 61.4,
            "Method": [
                "POINTS1.5-Qwen2.5-7B",
                "https://huggingface.co/WePOINTS/POINTS-1-5-Qwen-2-5-7B-Chat"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen-2.5-7B",
            "Vision Model": "NaViT",
            "Org": "WeChat",
            "Time": "2024/12/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTSV15-Qwen-2.5-7B-Chat",
            "key": 403
        },
        {
            "Overall": 83.4,
            "AR": 86.1,
            "CP": 88.0,
            "FP-C": 75.7,
            "FP-S": 89.9,
            "LR": 67.1,
            "RR": 79.1,
            "action_recognition": 93.2,
            "attribute_comparison": 82.1,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 88.1,
            "function_reasoning": 88.7,
            "future_prediction": 66.7,
            "identity_reasoning": 96.3,
            "image_emotion": 75.9,
            "image_quality": 84.7,
            "image_scene": 96.1,
            "image_style": 81.2,
            "image_topic": 97.6,
            "nature_relation": 87.7,
            "object_localization": 85.6,
            "ocr": 94.8,
            "physical_property_reasoning": 75.0,
            "physical_relation": 65.4,
            "social_relation": 79.5,
            "spatial_relationship": 50.6,
            "structuralized_imagetext_understanding": 67.3,
            "Method": [
                "BailingMM-Lite-1203",
                "https://zxb.alipay.com/llm/landing"
            ],
            "Parameters": "21B",
            "Language Model": "Bailing-20B",
            "Vision Model": "SigLIP-400M",
            "Org": "Ant Group",
            "Time": "2024/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "bailingMM-Lite",
            "key": 404
        },
        {
            "Overall": 82.1,
            "AR": 81.6,
            "CP": 82.4,
            "FP-C": 83.0,
            "FP-S": 87.7,
            "LR": 74.6,
            "RR": 76.8,
            "action_recognition": 94.3,
            "attribute_comparison": 79.5,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 85.6,
            "function_reasoning": 88.7,
            "future_prediction": 73.6,
            "identity_reasoning": 97.6,
            "image_emotion": 56.6,
            "image_quality": 82.4,
            "image_scene": 93.0,
            "image_style": 78.8,
            "image_topic": 95.3,
            "nature_relation": 88.9,
            "object_localization": 79.8,
            "ocr": 98.7,
            "physical_property_reasoning": 61.0,
            "physical_relation": 69.2,
            "social_relation": 69.2,
            "spatial_relationship": 74.1,
            "structuralized_imagetext_understanding": 75.2,
            "Method": [
                "GLM-4v-Plus",
                "https://open.bigmodel.cn/dev/api/normal-model/glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GLM4V_PLUS",
            "key": 412
        },
        {
            "Overall": 0.6,
            "AR": 1.7,
            "CP": 0.2,
            "FP-C": 0.0,
            "FP-S": 0.5,
            "LR": 0.6,
            "RR": 0.5,
            "action_recognition": 0.0,
            "attribute_comparison": 0.0,
            "attribute_recognition": 1.0,
            "celebrity_recognition": 0.0,
            "function_reasoning": 0.9,
            "future_prediction": 0.0,
            "identity_reasoning": 0.0,
            "image_emotion": 0.0,
            "image_quality": 0.0,
            "image_scene": 0.0,
            "image_style": 0.0,
            "image_topic": 1.2,
            "nature_relation": 0.0,
            "object_localization": 1.0,
            "ocr": 0.0,
            "physical_property_reasoning": 4.0,
            "physical_relation": 1.9,
            "social_relation": 0.0,
            "spatial_relationship": 0.0,
            "structuralized_imagetext_understanding": 1.0,
            "Method": [
                "Step-1.5V-mini",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "StepFun",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Step1.5V-mini",
            "key": 413
        },
        {
            "Overall": 60.9,
            "AR": 66.7,
            "CP": 73.2,
            "FP-C": 49.0,
            "FP-S": 57.3,
            "LR": 53.2,
            "RR": 53.1,
            "action_recognition": 88.6,
            "attribute_comparison": 16.7,
            "attribute_recognition": 71.7,
            "celebrity_recognition": 39.8,
            "function_reasoning": 79.2,
            "future_prediction": 56.9,
            "identity_reasoning": 81.7,
            "image_emotion": 66.3,
            "image_quality": 44.7,
            "image_scene": 91.5,
            "image_style": 61.2,
            "image_topic": 92.9,
            "nature_relation": 66.7,
            "object_localization": 36.5,
            "ocr": 93.5,
            "physical_property_reasoning": 41.0,
            "physical_relation": 34.6,
            "social_relation": 51.3,
            "spatial_relationship": 37.0,
            "structuralized_imagetext_understanding": 50.5,
            "Method": [
                "abab6.5s",
                "https://www.minimaxi.com/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "MiniMax",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "abab6.5s",
            "key": 414
        },
        {
            "Overall": 82.3,
            "AR": 80.2,
            "CP": 84.8,
            "FP-C": 80.2,
            "FP-S": 88.2,
            "LR": 74.0,
            "RR": 78.2,
            "action_recognition": 89.8,
            "attribute_comparison": 79.5,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 80.5,
            "function_reasoning": 88.7,
            "future_prediction": 80.6,
            "identity_reasoning": 90.2,
            "image_emotion": 72.3,
            "image_quality": 84.7,
            "image_scene": 93.8,
            "image_style": 71.8,
            "image_topic": 96.5,
            "nature_relation": 88.9,
            "object_localization": 82.7,
            "ocr": 97.4,
            "physical_property_reasoning": 63.0,
            "physical_relation": 57.7,
            "social_relation": 80.8,
            "spatial_relationship": 70.4,
            "structuralized_imagetext_understanding": 69.3,
            "Method": [
                "abab7-preview",
                "https://www.minimaxi.com/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "MiniMax",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "abab7-preview",
            "key": 415
        },
        {
            "Overall": 85.4,
            "AR": 87.5,
            "CP": 88.0,
            "FP-C": 81.8,
            "FP-S": 89.9,
            "LR": 71.7,
            "RR": 83.4,
            "action_recognition": 92.0,
            "attribute_comparison": 85.9,
            "attribute_recognition": 94.9,
            "celebrity_recognition": 90.7,
            "function_reasoning": 91.5,
            "future_prediction": 73.6,
            "identity_reasoning": 97.6,
            "image_emotion": 79.5,
            "image_quality": 87.1,
            "image_scene": 94.6,
            "image_style": 78.8,
            "image_topic": 96.5,
            "nature_relation": 84.0,
            "object_localization": 80.8,
            "ocr": 94.8,
            "physical_property_reasoning": 75.0,
            "physical_relation": 71.2,
            "social_relation": 91.0,
            "spatial_relationship": 66.7,
            "structuralized_imagetext_understanding": 70.3,
            "Method": [
                "Taiyi",
                "https://taiyi.megvii.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Megvii & StepFun",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Taiyi",
            "key": 383
        },
        {
            "Overall": 88.5,
            "AR": 85.4,
            "CP": 90.6,
            "FP-C": 85.4,
            "FP-S": 93.0,
            "LR": 80.9,
            "RR": 89.1,
            "action_recognition": 94.3,
            "attribute_comparison": 85.9,
            "attribute_recognition": 98.0,
            "celebrity_recognition": 89.8,
            "function_reasoning": 90.6,
            "future_prediction": 81.9,
            "identity_reasoning": 98.8,
            "image_emotion": 80.7,
            "image_quality": 87.1,
            "image_scene": 96.9,
            "image_style": 87.1,
            "image_topic": 97.6,
            "nature_relation": 93.8,
            "object_localization": 88.5,
            "ocr": 97.4,
            "physical_property_reasoning": 69.0,
            "physical_relation": 76.9,
            "social_relation": 92.3,
            "spatial_relationship": 75.3,
            "structuralized_imagetext_understanding": 80.2,
            "Method": [
                "InternVL2.5-78B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-78B"
            ],
            "Parameters": "78B",
            "Language Model": "Qwen-2.5-72B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-78B",
            "key": 423
        },
        {
            "Overall": 74.9,
            "AR": 82.6,
            "CP": 80.7,
            "FP-C": 66.8,
            "FP-S": 77.9,
            "LR": 53.8,
            "RR": 72.5,
            "action_recognition": 93.2,
            "attribute_comparison": 74.4,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 72.9,
            "function_reasoning": 84.0,
            "future_prediction": 61.1,
            "identity_reasoning": 95.1,
            "image_emotion": 73.5,
            "image_quality": 65.9,
            "image_scene": 90.7,
            "image_style": 71.8,
            "image_topic": 96.5,
            "nature_relation": 71.6,
            "object_localization": 60.6,
            "ocr": 93.5,
            "physical_property_reasoning": 71.0,
            "physical_relation": 51.9,
            "social_relation": 87.2,
            "spatial_relationship": 30.9,
            "structuralized_imagetext_understanding": 48.5,
            "Method": [
                "SAIL-VL-2B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL-2B"
            ],
            "Parameters": "2.1B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "InternViT-300M",
            "Org": "ByteDance",
            "Time": "2024/12/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL-2B",
            "key": 424
        },
        {
            "Overall": 65.7,
            "AR": 69.8,
            "CP": 78.8,
            "FP-C": 53.8,
            "FP-S": 68.8,
            "LR": 41.6,
            "RR": 58.8,
            "action_recognition": 92.0,
            "attribute_comparison": 34.6,
            "attribute_recognition": 78.8,
            "celebrity_recognition": 59.3,
            "function_reasoning": 75.5,
            "future_prediction": 51.4,
            "identity_reasoning": 91.5,
            "image_emotion": 78.3,
            "image_quality": 57.6,
            "image_scene": 91.5,
            "image_style": 67.1,
            "image_topic": 92.9,
            "nature_relation": 53.1,
            "object_localization": 51.9,
            "ocr": 93.5,
            "physical_property_reasoning": 46.0,
            "physical_relation": 42.3,
            "social_relation": 75.6,
            "spatial_relationship": 30.9,
            "structuralized_imagetext_understanding": 34.7,
            "Method": [
                "InternVL2.5-1B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-1B-MPO"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen-2.5-0.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-1B-MPO",
            "key": 425
        },
        {
            "Overall": 71.2,
            "AR": 79.2,
            "CP": 81.4,
            "FP-C": 63.6,
            "FP-S": 73.4,
            "LR": 47.4,
            "RR": 62.6,
            "action_recognition": 94.3,
            "attribute_comparison": 62.8,
            "attribute_recognition": 85.9,
            "celebrity_recognition": 66.9,
            "function_reasoning": 80.2,
            "future_prediction": 55.6,
            "identity_reasoning": 96.3,
            "image_emotion": 71.1,
            "image_quality": 68.2,
            "image_scene": 94.6,
            "image_style": 70.6,
            "image_topic": 95.3,
            "nature_relation": 59.3,
            "object_localization": 52.9,
            "ocr": 94.8,
            "physical_property_reasoning": 64.0,
            "physical_relation": 42.3,
            "social_relation": 79.5,
            "spatial_relationship": 30.9,
            "structuralized_imagetext_understanding": 41.6,
            "Method": [
                "InternVL2.5-2B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-2B-MPO"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2.5-1.8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-2B-MPO",
            "key": 426
        },
        {
            "Overall": 78.9,
            "AR": 84.0,
            "CP": 85.7,
            "FP-C": 69.2,
            "FP-S": 81.2,
            "LR": 65.9,
            "RR": 74.4,
            "action_recognition": 93.2,
            "attribute_comparison": 75.6,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 75.4,
            "function_reasoning": 88.7,
            "future_prediction": 73.6,
            "identity_reasoning": 97.6,
            "image_emotion": 79.5,
            "image_quality": 81.2,
            "image_scene": 93.8,
            "image_style": 75.3,
            "image_topic": 94.1,
            "nature_relation": 63.0,
            "object_localization": 70.2,
            "ocr": 93.5,
            "physical_property_reasoning": 68.0,
            "physical_relation": 69.2,
            "social_relation": 89.7,
            "spatial_relationship": 37.0,
            "structuralized_imagetext_understanding": 60.4,
            "Method": [
                "InternVL2.5-4B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-4B-MPO"
            ],
            "Parameters": "4B",
            "Language Model": "Qwen-2.5-3B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-4B-MPO",
            "key": 427
        },
        {
            "Overall": 82.4,
            "AR": 79.5,
            "CP": 86.9,
            "FP-C": 78.9,
            "FP-S": 88.7,
            "LR": 69.4,
            "RR": 79.1,
            "action_recognition": 93.2,
            "attribute_comparison": 89.7,
            "attribute_recognition": 97.0,
            "celebrity_recognition": 85.6,
            "function_reasoning": 85.8,
            "future_prediction": 75.0,
            "identity_reasoning": 98.8,
            "image_emotion": 77.1,
            "image_quality": 78.8,
            "image_scene": 95.3,
            "image_style": 82.4,
            "image_topic": 96.5,
            "nature_relation": 87.7,
            "object_localization": 78.8,
            "ocr": 96.1,
            "physical_property_reasoning": 57.0,
            "physical_relation": 53.8,
            "social_relation": 87.2,
            "spatial_relationship": 53.1,
            "structuralized_imagetext_understanding": 65.3,
            "Method": [
                "InternVL2.5-8B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-8B-MPO",
            "key": 428
        },
        {
            "Overall": 85.3,
            "AR": 84.7,
            "CP": 87.4,
            "FP-C": 80.2,
            "FP-S": 90.2,
            "LR": 77.5,
            "RR": 84.8,
            "action_recognition": 93.2,
            "attribute_comparison": 82.1,
            "attribute_recognition": 97.0,
            "celebrity_recognition": 86.4,
            "function_reasoning": 89.6,
            "future_prediction": 79.2,
            "identity_reasoning": 97.6,
            "image_emotion": 78.3,
            "image_quality": 81.2,
            "image_scene": 96.1,
            "image_style": 80.0,
            "image_topic": 96.5,
            "nature_relation": 86.4,
            "object_localization": 84.6,
            "ocr": 94.8,
            "physical_property_reasoning": 69.0,
            "physical_relation": 75.0,
            "social_relation": 89.7,
            "spatial_relationship": 64.2,
            "structuralized_imagetext_understanding": 76.2,
            "Method": [
                "InternVL2.5-26B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-26B-MPO"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2.5-20B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-26B-MPO",
            "key": 429
        },
        {
            "Overall": 86.4,
            "AR": 84.7,
            "CP": 86.9,
            "FP-C": 84.6,
            "FP-S": 91.2,
            "LR": 82.1,
            "RR": 84.4,
            "action_recognition": 94.3,
            "attribute_comparison": 79.5,
            "attribute_recognition": 97.0,
            "celebrity_recognition": 87.3,
            "function_reasoning": 89.6,
            "future_prediction": 81.9,
            "identity_reasoning": 97.6,
            "image_emotion": 77.1,
            "image_quality": 78.8,
            "image_scene": 95.3,
            "image_style": 82.4,
            "image_topic": 96.5,
            "nature_relation": 90.1,
            "object_localization": 84.6,
            "ocr": 98.7,
            "physical_property_reasoning": 69.0,
            "physical_relation": 71.2,
            "social_relation": 87.2,
            "spatial_relationship": 79.0,
            "structuralized_imagetext_understanding": 82.2,
            "Method": [
                "InternVL2.5-38B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-38B-MPO"
            ],
            "Parameters": "38B",
            "Language Model": "Qwen-2.5-32B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-38B-MPO",
            "key": 430
        },
        {
            "Overall": 88.2,
            "AR": 86.1,
            "CP": 89.3,
            "FP-C": 87.4,
            "FP-S": 91.7,
            "LR": 82.1,
            "RR": 87.7,
            "action_recognition": 92.0,
            "attribute_comparison": 89.7,
            "attribute_recognition": 97.0,
            "celebrity_recognition": 89.0,
            "function_reasoning": 90.6,
            "future_prediction": 81.9,
            "identity_reasoning": 98.8,
            "image_emotion": 79.5,
            "image_quality": 83.5,
            "image_scene": 96.1,
            "image_style": 85.9,
            "image_topic": 97.6,
            "nature_relation": 93.8,
            "object_localization": 86.5,
            "ocr": 96.1,
            "physical_property_reasoning": 71.0,
            "physical_relation": 73.1,
            "social_relation": 91.0,
            "spatial_relationship": 80.2,
            "structuralized_imagetext_understanding": 82.2,
            "Method": [
                "InternVL2.5-78B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-78B-MPO"
            ],
            "Parameters": "78B",
            "Language Model": "Qwen-2.5-72B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-78B-MPO",
            "key": 432
        },
        {
            "Overall": 72.1,
            "AR": 77.8,
            "CP": 80.1,
            "FP-C": 63.2,
            "FP-S": 75.9,
            "LR": 43.9,
            "RR": 73.0,
            "action_recognition": 90.9,
            "attribute_comparison": 66.7,
            "attribute_recognition": 83.8,
            "celebrity_recognition": 75.4,
            "function_reasoning": 82.1,
            "future_prediction": 52.8,
            "identity_reasoning": 95.1,
            "image_emotion": 73.5,
            "image_quality": 58.8,
            "image_scene": 91.5,
            "image_style": 74.1,
            "image_topic": 96.5,
            "nature_relation": 69.1,
            "object_localization": 54.8,
            "ocr": 94.8,
            "physical_property_reasoning": 59.0,
            "physical_relation": 63.5,
            "social_relation": 83.3,
            "spatial_relationship": 29.6,
            "structuralized_imagetext_understanding": 37.6,
            "Method": [
                "DeepSeek-VL2-Tiny",
                "https://huggingface.co/deepseek-ai/deepseek-vl2-tiny"
            ],
            "Parameters": "3.4B",
            "Language Model": "DeepSeekMoE-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2_tiny",
            "key": 433
        },
        {
            "Overall": 81.0,
            "AR": 80.2,
            "CP": 88.4,
            "FP-C": 75.7,
            "FP-S": 84.4,
            "LR": 67.6,
            "RR": 76.3,
            "action_recognition": 93.2,
            "attribute_comparison": 82.1,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 85.6,
            "function_reasoning": 86.8,
            "future_prediction": 79.2,
            "identity_reasoning": 96.3,
            "image_emotion": 75.9,
            "image_quality": 84.7,
            "image_scene": 96.1,
            "image_style": 84.7,
            "image_topic": 96.5,
            "nature_relation": 79.0,
            "object_localization": 69.2,
            "ocr": 96.1,
            "physical_property_reasoning": 60.0,
            "physical_relation": 61.5,
            "social_relation": 83.3,
            "spatial_relationship": 50.6,
            "structuralized_imagetext_understanding": 59.4,
            "Method": [
                "DeepSeek-VL2-Small",
                "https://huggingface.co/deepseek-ai/deepseek-vl2-small"
            ],
            "Parameters": "16.1B",
            "Language Model": "DeepSeekMoE-16B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2_small",
            "key": 434
        },
        {
            "Overall": 82.2,
            "AR": 85.4,
            "CP": 85.0,
            "FP-C": 78.9,
            "FP-S": 86.7,
            "LR": 74.0,
            "RR": 73.5,
            "action_recognition": 92.0,
            "attribute_comparison": 87.2,
            "attribute_recognition": 91.9,
            "celebrity_recognition": 81.4,
            "function_reasoning": 89.6,
            "future_prediction": 77.8,
            "identity_reasoning": 98.8,
            "image_emotion": 77.1,
            "image_quality": 78.8,
            "image_scene": 93.0,
            "image_style": 75.3,
            "image_topic": 96.5,
            "nature_relation": 75.3,
            "object_localization": 82.7,
            "ocr": 93.5,
            "physical_property_reasoning": 70.0,
            "physical_relation": 61.5,
            "social_relation": 79.5,
            "spatial_relationship": 56.8,
            "structuralized_imagetext_understanding": 71.3,
            "Method": [
                "VARCO-VISION-14B",
                "https://huggingface.co/NCSOFT/VARCO-VISION-14B-HF"
            ],
            "Parameters": "15.2B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "SigLIP-400M",
            "Org": "NC Research",
            "Time": "2025/01/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "varco-vision-hf",
            "key": 437
        },
        {
            "Overall": 87.6,
            "AR": 86.8,
            "CP": 89.1,
            "FP-C": 85.0,
            "FP-S": 93.7,
            "LR": 78.6,
            "RR": 83.9,
            "action_recognition": 94.3,
            "attribute_comparison": 83.3,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 99.2,
            "function_reasoning": 92.5,
            "future_prediction": 79.2,
            "identity_reasoning": 98.8,
            "image_emotion": 80.7,
            "image_quality": 85.9,
            "image_scene": 94.6,
            "image_style": 84.7,
            "image_topic": 96.5,
            "nature_relation": 95.1,
            "object_localization": 84.6,
            "ocr": 97.4,
            "physical_property_reasoning": 71.0,
            "physical_relation": 59.6,
            "social_relation": 88.5,
            "spatial_relationship": 76.5,
            "structuralized_imagetext_understanding": 78.2,
            "Method": [
                "Step-1o",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "StepFun",
            "Time": "2025/01/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Step1o",
            "key": 439
        },
        {
            "Overall": 85.0,
            "AR": 87.5,
            "CP": 85.7,
            "FP-C": 80.6,
            "FP-S": 90.2,
            "LR": 79.2,
            "RR": 80.1,
            "action_recognition": 94.3,
            "attribute_comparison": 78.2,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 94.9,
            "function_reasoning": 89.6,
            "future_prediction": 77.8,
            "identity_reasoning": 97.6,
            "image_emotion": 69.9,
            "image_quality": 80.0,
            "image_scene": 94.6,
            "image_style": 83.5,
            "image_topic": 95.3,
            "nature_relation": 90.1,
            "object_localization": 77.9,
            "ocr": 96.1,
            "physical_property_reasoning": 77.0,
            "physical_relation": 65.4,
            "social_relation": 79.5,
            "spatial_relationship": 67.9,
            "structuralized_imagetext_understanding": 80.2,
            "Method": [
                "HunYuan-Standard-Vision",
                "https://cloud.tencent.com/document/product/1729/104753"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Tencent",
            "Time": "2025/01/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "HunYuan-Standard-Vision",
            "key": 440
        },
        {
            "Overall": 76.9,
            "AR": 83.7,
            "CP": 85.2,
            "FP-C": 68.0,
            "FP-S": 77.1,
            "LR": 63.0,
            "RR": 70.6,
            "action_recognition": 94.3,
            "attribute_comparison": 74.4,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 78.8,
            "function_reasoning": 86.8,
            "future_prediction": 77.8,
            "identity_reasoning": 96.3,
            "image_emotion": 77.1,
            "image_quality": 75.3,
            "image_scene": 95.3,
            "image_style": 77.6,
            "image_topic": 95.3,
            "nature_relation": 69.1,
            "object_localization": 52.9,
            "ocr": 90.9,
            "physical_property_reasoning": 70.0,
            "physical_relation": 57.7,
            "social_relation": 80.8,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 52.5,
            "Method": [
                "Ross-Qwen2-7B",
                "https://huggingface.co/HaochenWang/ross-qwen2-7b"
            ],
            "Parameters": "8.2B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "CASIA",
            "Time": "2025/01/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "ross-qwen2-7b",
            "key": 441
        },
        {
            "Overall": 78.6,
            "AR": 81.9,
            "CP": 82.7,
            "FP-C": 70.0,
            "FP-S": 84.9,
            "LR": 62.4,
            "RR": 76.3,
            "action_recognition": 92.0,
            "attribute_comparison": 69.2,
            "attribute_recognition": 91.9,
            "celebrity_recognition": 79.7,
            "function_reasoning": 85.8,
            "future_prediction": 75.0,
            "identity_reasoning": 92.7,
            "image_emotion": 78.3,
            "image_quality": 68.2,
            "image_scene": 89.9,
            "image_style": 76.5,
            "image_topic": 96.5,
            "nature_relation": 79.0,
            "object_localization": 73.1,
            "ocr": 100.0,
            "physical_property_reasoning": 69.0,
            "physical_relation": 59.6,
            "social_relation": 84.6,
            "spatial_relationship": 46.9,
            "structuralized_imagetext_understanding": 53.5,
            "Method": [
                "VITA-1.5",
                "https://huggingface.co/VITA-MLLM/VITA-1.5"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "InternViT-300M",
            "Org": "NJU",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "vita_qwen2",
            "key": 442
        },
        {
            "Overall": 83.0,
            "AR": 87.8,
            "CP": 85.4,
            "FP-C": 75.3,
            "FP-S": 88.4,
            "LR": 67.6,
            "RR": 82.0,
            "action_recognition": 93.2,
            "attribute_comparison": 76.9,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 91.5,
            "function_reasoning": 91.5,
            "future_prediction": 73.6,
            "identity_reasoning": 97.6,
            "image_emotion": 79.5,
            "image_quality": 80.0,
            "image_scene": 93.0,
            "image_style": 74.1,
            "image_topic": 96.5,
            "nature_relation": 86.4,
            "object_localization": 78.8,
            "ocr": 93.5,
            "physical_property_reasoning": 76.0,
            "physical_relation": 61.5,
            "social_relation": 91.0,
            "spatial_relationship": 54.3,
            "structuralized_imagetext_understanding": 63.4,
            "Method": [
                "MiniCPM-o-2.6",
                "https://huggingface.co/openbmb/MiniCPM-o-2_6"
            ],
            "Parameters": "8.67B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "OpenBMB",
            "Time": "2025/01/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MiniCPM-o-2_6",
            "key": 444
        },
        {
            "Overall": 85.7,
            "AR": 87.2,
            "CP": 87.6,
            "FP-C": 80.2,
            "FP-S": 91.5,
            "LR": 80.3,
            "RR": 79.6,
            "action_recognition": 94.3,
            "attribute_comparison": 74.4,
            "attribute_recognition": 94.9,
            "celebrity_recognition": 94.9,
            "function_reasoning": 89.6,
            "future_prediction": 77.8,
            "identity_reasoning": 98.8,
            "image_emotion": 78.3,
            "image_quality": 85.9,
            "image_scene": 95.3,
            "image_style": 78.8,
            "image_topic": 95.3,
            "nature_relation": 90.1,
            "object_localization": 81.7,
            "ocr": 94.8,
            "physical_property_reasoning": 75.0,
            "physical_relation": 55.8,
            "social_relation": 84.6,
            "spatial_relationship": 70.4,
            "structuralized_imagetext_understanding": 82.2,
            "Method": [
                "BailingMM-Pro-0120",
                "https://zxb.alipay.com/llm/landing"
            ],
            "Parameters": "81B",
            "Language Model": "Bailing-80B",
            "Vision Model": "SigLIP-400M",
            "Org": "Ant Group",
            "Time": "2025/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "BailingMM-Pro-0120",
            "key": 445
        },
        {
            "Overall": 85.4,
            "AR": 84.4,
            "CP": 84.2,
            "FP-C": 83.8,
            "FP-S": 91.2,
            "LR": 83.2,
            "RR": 82.5,
            "action_recognition": 87.5,
            "attribute_comparison": 84.6,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 85.6,
            "function_reasoning": 86.8,
            "future_prediction": 81.9,
            "identity_reasoning": 96.3,
            "image_emotion": 68.7,
            "image_quality": 81.2,
            "image_scene": 94.6,
            "image_style": 78.8,
            "image_topic": 91.8,
            "nature_relation": 93.8,
            "object_localization": 87.5,
            "ocr": 98.7,
            "physical_property_reasoning": 72.0,
            "physical_relation": 53.8,
            "social_relation": 89.7,
            "spatial_relationship": 79.0,
            "structuralized_imagetext_understanding": 84.2,
            "Method": [
                "GLM-4v-Plus-20250111",
                "https://open.bigmodel.cn/dev/api/normal-model/glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2025/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GLM4V_PLUS_20250111",
            "key": 447
        },
        {
            "Overall": 49.8,
            "AR": 53.8,
            "CP": 63.6,
            "FP-C": 50.2,
            "FP-S": 45.7,
            "LR": 29.5,
            "RR": 37.4,
            "action_recognition": 79.5,
            "attribute_comparison": 43.6,
            "attribute_recognition": 53.5,
            "celebrity_recognition": 28.8,
            "function_reasoning": 50.0,
            "future_prediction": 44.4,
            "identity_reasoning": 64.6,
            "image_emotion": 60.2,
            "image_quality": 35.3,
            "image_scene": 78.3,
            "image_style": 44.7,
            "image_topic": 91.8,
            "nature_relation": 19.8,
            "object_localization": 29.8,
            "ocr": 83.1,
            "physical_property_reasoning": 49.0,
            "physical_relation": 28.8,
            "social_relation": 61.5,
            "spatial_relationship": 24.7,
            "structuralized_imagetext_understanding": 18.8,
            "Method": [
                "Emu3_chat",
                "https://huggingface.co/BAAI/Emu3-Chat"
            ],
            "Parameters": "8.49B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Beijing Academy of Artificial Intelligence",
            "Time": "2025/01/26",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "dir_name": "emu3_chat",
            "key": 448
        },
        {
            "Overall": 51.9,
            "AR": 63.2,
            "CP": 61.0,
            "FP-C": 44.9,
            "FP-S": 43.7,
            "LR": 38.7,
            "RR": 50.7,
            "action_recognition": 89.8,
            "attribute_comparison": 21.8,
            "attribute_recognition": 46.5,
            "celebrity_recognition": 33.1,
            "function_reasoning": 62.3,
            "future_prediction": 51.4,
            "identity_reasoning": 75.6,
            "image_emotion": 67.5,
            "image_quality": 29.4,
            "image_scene": 74.4,
            "image_style": 38.8,
            "image_topic": 88.2,
            "nature_relation": 54.3,
            "object_localization": 20.2,
            "ocr": 88.3,
            "physical_property_reasoning": 54.0,
            "physical_relation": 19.2,
            "social_relation": 67.9,
            "spatial_relationship": 18.5,
            "structuralized_imagetext_understanding": 29.7,
            "Method": [
                "SmolVLM-Instruct",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM",
            "key": 392
        },
        {
            "Overall": 49.8,
            "AR": 65.6,
            "CP": 57.0,
            "FP-C": 41.7,
            "FP-S": 43.5,
            "LR": 34.1,
            "RR": 46.9,
            "action_recognition": 86.4,
            "attribute_comparison": 17.9,
            "attribute_recognition": 51.5,
            "celebrity_recognition": 31.4,
            "function_reasoning": 67.9,
            "future_prediction": 48.6,
            "identity_reasoning": 73.2,
            "image_emotion": 66.3,
            "image_quality": 8.2,
            "image_scene": 76.0,
            "image_style": 40.0,
            "image_topic": 84.7,
            "nature_relation": 45.7,
            "object_localization": 17.3,
            "ocr": 87.0,
            "physical_property_reasoning": 57.0,
            "physical_relation": 19.2,
            "social_relation": 66.7,
            "spatial_relationship": 16.0,
            "structuralized_imagetext_understanding": 23.8,
            "Method": [
                "SmolVLM-Instruct-DPO",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct-DPO"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-DPO",
            "key": 393
        },
        {
            "Overall": 36.9,
            "AR": 45.5,
            "CP": 46.7,
            "FP-C": 35.6,
            "FP-S": 30.7,
            "LR": 22.0,
            "RR": 29.4,
            "action_recognition": 84.1,
            "attribute_comparison": 9.0,
            "attribute_recognition": 28.3,
            "celebrity_recognition": 21.2,
            "function_reasoning": 49.1,
            "future_prediction": 43.1,
            "identity_reasoning": 62.2,
            "image_emotion": 48.2,
            "image_quality": 2.4,
            "image_scene": 63.6,
            "image_style": 24.7,
            "image_topic": 85.9,
            "nature_relation": 30.9,
            "object_localization": 6.7,
            "ocr": 80.5,
            "physical_property_reasoning": 28.0,
            "physical_relation": 9.6,
            "social_relation": 41.0,
            "spatial_relationship": 8.6,
            "structuralized_imagetext_understanding": 6.9,
            "Method": [
                "SmolVLM-Synthetic",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Synthetic"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-Synthetic",
            "key": 394
        },
        {
            "Overall": 15.1,
            "AR": 18.4,
            "CP": 19.7,
            "FP-C": 4.5,
            "FP-S": 21.6,
            "LR": 3.5,
            "RR": 10.0,
            "action_recognition": 8.0,
            "attribute_comparison": 1.3,
            "attribute_recognition": 15.2,
            "celebrity_recognition": 7.6,
            "function_reasoning": 14.2,
            "future_prediction": 1.4,
            "identity_reasoning": 34.1,
            "image_emotion": 36.1,
            "image_quality": 4.7,
            "image_scene": 20.2,
            "image_style": 14.1,
            "image_topic": 23.5,
            "nature_relation": 8.6,
            "object_localization": 3.8,
            "ocr": 75.3,
            "physical_property_reasoning": 10.0,
            "physical_relation": 3.8,
            "social_relation": 15.4,
            "spatial_relationship": 3.7,
            "structuralized_imagetext_understanding": 5.0,
            "Method": [
                "SmolVLM-256M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct"
            ],
            "Parameters": "0.26B",
            "Language Model": "SmolLM2-135M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-256M",
            "key": 449
        },
        {
            "Overall": 35.4,
            "AR": 39.9,
            "CP": 48.0,
            "FP-C": 30.0,
            "FP-S": 30.9,
            "LR": 17.3,
            "RR": 30.8,
            "action_recognition": 61.4,
            "attribute_comparison": 10.3,
            "attribute_recognition": 38.4,
            "celebrity_recognition": 11.0,
            "function_reasoning": 32.1,
            "future_prediction": 37.5,
            "identity_reasoning": 58.5,
            "image_emotion": 47.0,
            "image_quality": 14.1,
            "image_scene": 65.9,
            "image_style": 27.1,
            "image_topic": 76.5,
            "nature_relation": 34.6,
            "object_localization": 8.7,
            "ocr": 81.8,
            "physical_property_reasoning": 33.0,
            "physical_relation": 7.7,
            "social_relation": 42.3,
            "spatial_relationship": 14.8,
            "structuralized_imagetext_understanding": 3.0,
            "Method": [
                "SmolVLM-500M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-500M-Instruct"
            ],
            "Parameters": "0.51B",
            "Language Model": "SmolLM2-360M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-500M",
            "key": 450
        },
        {
            "Overall": 61.2,
            "AR": 68.4,
            "CP": 73.0,
            "FP-C": 51.8,
            "FP-S": 61.6,
            "LR": 34.1,
            "RR": 57.3,
            "action_recognition": 88.6,
            "attribute_comparison": 35.9,
            "attribute_recognition": 76.8,
            "celebrity_recognition": 58.5,
            "function_reasoning": 70.8,
            "future_prediction": 59.7,
            "identity_reasoning": 92.7,
            "image_emotion": 59.0,
            "image_quality": 45.9,
            "image_scene": 90.7,
            "image_style": 65.9,
            "image_topic": 94.1,
            "nature_relation": 56.8,
            "object_localization": 31.7,
            "ocr": 87.0,
            "physical_property_reasoning": 46.0,
            "physical_relation": 40.4,
            "social_relation": 69.2,
            "spatial_relationship": 27.2,
            "structuralized_imagetext_understanding": 15.8,
            "Method": [
                "Janus-Pro-7B",
                "https://huggingface.co/deepseek-ai/Janus-Pro-7B"
            ],
            "Parameters": "7.42B",
            "Language Model": "DeepSeek-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "deepseek",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Janus-Pro-7B",
            "key": 454
        },
        {
            "Overall": 85.1,
            "AR": 90.6,
            "CP": 86.7,
            "FP-C": 81.0,
            "FP-S": 85.9,
            "LR": 76.9,
            "RR": 83.9,
            "action_recognition": 93.2,
            "attribute_comparison": 84.6,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 86.4,
            "function_reasoning": 93.4,
            "future_prediction": 84.7,
            "identity_reasoning": 100.0,
            "image_emotion": 77.1,
            "image_quality": 82.4,
            "image_scene": 95.3,
            "image_style": 77.6,
            "image_topic": 96.5,
            "nature_relation": 92.6,
            "object_localization": 74.0,
            "ocr": 94.8,
            "physical_property_reasoning": 80.0,
            "physical_relation": 67.3,
            "social_relation": 85.9,
            "spatial_relationship": 64.2,
            "structuralized_imagetext_understanding": 71.3,
            "Method": [
                "Ola-7b",
                "https://huggingface.co/THUdyh/Ola-7b"
            ],
            "Parameters": "8.88B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "Oryx-ViT",
            "Org": "THU",
            "Time": "2025/02/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "ola",
            "key": 455
        },
        {
            "Overall": 68.7,
            "AR": 79.5,
            "CP": 78.4,
            "FP-C": 56.7,
            "FP-S": 68.3,
            "LR": 45.1,
            "RR": 66.8,
            "action_recognition": 93.2,
            "attribute_comparison": 47.4,
            "attribute_recognition": 76.8,
            "celebrity_recognition": 56.8,
            "function_reasoning": 83.0,
            "future_prediction": 63.9,
            "identity_reasoning": 90.2,
            "image_emotion": 68.7,
            "image_quality": 63.5,
            "image_scene": 89.9,
            "image_style": 68.2,
            "image_topic": 95.3,
            "nature_relation": 65.4,
            "object_localization": 53.8,
            "ocr": 94.8,
            "physical_property_reasoning": 67.0,
            "physical_relation": 55.8,
            "social_relation": 75.6,
            "spatial_relationship": 25.9,
            "structuralized_imagetext_understanding": 31.7,
            "Method": [
                "Ovis2-1B",
                "https://huggingface.co/AIDC-AI/Ovis2-1B"
            ],
            "Parameters": "1.27B",
            "Language Model": "Qwen2.5-0.5B",
            "Vision Model": "AIMv2 Large",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-1B",
            "key": 456
        },
        {
            "Overall": 79.3,
            "AR": 83.7,
            "CP": 85.7,
            "FP-C": 72.5,
            "FP-S": 80.2,
            "LR": 64.2,
            "RR": 77.7,
            "action_recognition": 90.9,
            "attribute_comparison": 80.8,
            "attribute_recognition": 87.9,
            "celebrity_recognition": 70.3,
            "function_reasoning": 89.6,
            "future_prediction": 70.8,
            "identity_reasoning": 96.3,
            "image_emotion": 79.5,
            "image_quality": 77.6,
            "image_scene": 93.0,
            "image_style": 77.6,
            "image_topic": 96.5,
            "nature_relation": 72.8,
            "object_localization": 73.1,
            "ocr": 94.8,
            "physical_property_reasoning": 67.0,
            "physical_relation": 69.2,
            "social_relation": 88.5,
            "spatial_relationship": 44.4,
            "structuralized_imagetext_understanding": 59.4,
            "Method": [
                "Ovis2-2B",
                "https://huggingface.co/AIDC-AI/Ovis2-2B"
            ],
            "Parameters": "2.46B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "AIMv2 Large",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-2B",
            "key": 457
        },
        {
            "Overall": 82.9,
            "AR": 87.5,
            "CP": 87.4,
            "FP-C": 75.7,
            "FP-S": 85.7,
            "LR": 71.7,
            "RR": 79.1,
            "action_recognition": 92.0,
            "attribute_comparison": 83.3,
            "attribute_recognition": 88.9,
            "celebrity_recognition": 82.2,
            "function_reasoning": 88.7,
            "future_prediction": 79.2,
            "identity_reasoning": 100.0,
            "image_emotion": 78.3,
            "image_quality": 83.5,
            "image_scene": 93.8,
            "image_style": 82.4,
            "image_topic": 95.3,
            "nature_relation": 75.3,
            "object_localization": 79.8,
            "ocr": 94.8,
            "physical_property_reasoning": 76.0,
            "physical_relation": 75.0,
            "social_relation": 85.9,
            "spatial_relationship": 50.6,
            "structuralized_imagetext_understanding": 66.3,
            "Method": [
                "Ovis2-4B",
                "https://huggingface.co/AIDC-AI/Ovis2-4B"
            ],
            "Parameters": "4.62B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-4B",
            "key": 458
        },
        {
            "Overall": 85.0,
            "AR": 88.2,
            "CP": 88.2,
            "FP-C": 81.4,
            "FP-S": 86.7,
            "LR": 72.3,
            "RR": 84.8,
            "action_recognition": 96.6,
            "attribute_comparison": 89.7,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 86.4,
            "function_reasoning": 93.4,
            "future_prediction": 79.2,
            "identity_reasoning": 95.1,
            "image_emotion": 84.3,
            "image_quality": 84.7,
            "image_scene": 95.3,
            "image_style": 77.6,
            "image_topic": 95.3,
            "nature_relation": 91.4,
            "object_localization": 76.0,
            "ocr": 97.4,
            "physical_property_reasoning": 77.0,
            "physical_relation": 69.2,
            "social_relation": 88.5,
            "spatial_relationship": 56.8,
            "structuralized_imagetext_understanding": 67.3,
            "Method": [
                "Ovis2-8B",
                "https://huggingface.co/AIDC-AI/Ovis2-8B"
            ],
            "Parameters": "8.94B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-8B",
            "key": 459
        },
        {
            "Overall": 86.9,
            "AR": 88.9,
            "CP": 87.2,
            "FP-C": 89.9,
            "FP-S": 87.7,
            "LR": 80.9,
            "RR": 83.9,
            "action_recognition": 95.5,
            "attribute_comparison": 94.9,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 83.9,
            "function_reasoning": 91.5,
            "future_prediction": 83.3,
            "identity_reasoning": 97.6,
            "image_emotion": 77.1,
            "image_quality": 87.1,
            "image_scene": 93.8,
            "image_style": 77.6,
            "image_topic": 96.5,
            "nature_relation": 86.4,
            "object_localization": 79.8,
            "ocr": 100.0,
            "physical_property_reasoning": 79.0,
            "physical_relation": 78.8,
            "social_relation": 84.6,
            "spatial_relationship": 79.0,
            "structuralized_imagetext_understanding": 79.2,
            "Method": [
                "Ovis2-16B",
                "https://huggingface.co/AIDC-AI/Ovis2-16B"
            ],
            "Parameters": "16.2B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-16B",
            "key": 460
        },
        {
            "Overall": 88.0,
            "AR": 89.2,
            "CP": 88.4,
            "FP-C": 86.2,
            "FP-S": 91.7,
            "LR": 82.1,
            "RR": 85.3,
            "action_recognition": 93.2,
            "attribute_comparison": 89.7,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 87.3,
            "function_reasoning": 91.5,
            "future_prediction": 81.9,
            "identity_reasoning": 98.8,
            "image_emotion": 80.7,
            "image_quality": 87.1,
            "image_scene": 94.6,
            "image_style": 80.0,
            "image_topic": 96.5,
            "nature_relation": 92.6,
            "object_localization": 87.5,
            "ocr": 98.7,
            "physical_property_reasoning": 79.0,
            "physical_relation": 75.0,
            "social_relation": 84.6,
            "spatial_relationship": 75.3,
            "structuralized_imagetext_understanding": 82.2,
            "Method": [
                "Ovis2-34B",
                "https://huggingface.co/AIDC-AI/Ovis2-34B"
            ],
            "Parameters": "34.9B",
            "Language Model": "Qwen2.5-32B",
            "Vision Model": "AIMv2-1B",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-34B",
            "key": 461
        },
        {
            "Overall": 77.6,
            "AR": 77.8,
            "CP": 83.5,
            "FP-C": 65.6,
            "FP-S": 83.9,
            "LR": 68.2,
            "RR": 74.4,
            "action_recognition": 92.0,
            "attribute_comparison": 69.2,
            "attribute_recognition": 86.9,
            "celebrity_recognition": 93.2,
            "function_reasoning": 86.8,
            "future_prediction": 73.6,
            "identity_reasoning": 92.7,
            "image_emotion": 74.7,
            "image_quality": 74.1,
            "image_scene": 96.1,
            "image_style": 69.4,
            "image_topic": 96.5,
            "nature_relation": 74.1,
            "object_localization": 62.5,
            "ocr": 94.8,
            "physical_property_reasoning": 56.0,
            "physical_relation": 48.1,
            "social_relation": 92.3,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 64.4,
            "Method": [
                "Qwen2.5-VL-3B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct"
            ],
            "Parameters": "3.75B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-3B-Instruct",
            "key": 462
        },
        {
            "Overall": 82.8,
            "AR": 83.3,
            "CP": 88.2,
            "FP-C": 77.7,
            "FP-S": 88.9,
            "LR": 69.4,
            "RR": 75.8,
            "action_recognition": 94.3,
            "attribute_comparison": 78.2,
            "attribute_recognition": 86.9,
            "celebrity_recognition": 92.4,
            "function_reasoning": 87.7,
            "future_prediction": 73.6,
            "identity_reasoning": 97.6,
            "image_emotion": 77.1,
            "image_quality": 87.1,
            "image_scene": 95.3,
            "image_style": 82.4,
            "image_topic": 95.3,
            "nature_relation": 79.0,
            "object_localization": 81.7,
            "ocr": 96.1,
            "physical_property_reasoning": 67.0,
            "physical_relation": 53.8,
            "social_relation": 87.2,
            "spatial_relationship": 59.3,
            "structuralized_imagetext_understanding": 66.3,
            "Method": [
                "Qwen2.5-VL-7B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct"
            ],
            "Parameters": "8.29B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-7B-Instruct",
            "key": 463
        },
        {
            "Overall": 88.2,
            "AR": 84.4,
            "CP": 89.5,
            "FP-C": 86.2,
            "FP-S": 96.2,
            "LR": 83.8,
            "RR": 81.5,
            "action_recognition": 92.0,
            "attribute_comparison": 87.2,
            "attribute_recognition": 97.0,
            "celebrity_recognition": 97.5,
            "function_reasoning": 89.6,
            "future_prediction": 77.8,
            "identity_reasoning": 96.3,
            "image_emotion": 77.1,
            "image_quality": 90.6,
            "image_scene": 96.1,
            "image_style": 83.5,
            "image_topic": 96.5,
            "nature_relation": 88.9,
            "object_localization": 91.3,
            "ocr": 100.0,
            "physical_property_reasoning": 69.0,
            "physical_relation": 59.6,
            "social_relation": 88.5,
            "spatial_relationship": 79.0,
            "structuralized_imagetext_understanding": 88.1,
            "Method": [
                "Qwen2.5-VL-72B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct"
            ],
            "Parameters": "73.4B",
            "Language Model": "Qwen2.5-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-72B-Instruct",
            "key": 464
        },
        {
            "Overall": 80.9,
            "AR": 81.6,
            "CP": 87.6,
            "FP-C": 83.4,
            "FP-S": 77.1,
            "LR": 75.7,
            "RR": 73.9,
            "action_recognition": 89.8,
            "attribute_comparison": 88.5,
            "attribute_recognition": 88.9,
            "celebrity_recognition": 54.2,
            "function_reasoning": 89.6,
            "future_prediction": 62.5,
            "identity_reasoning": 95.1,
            "image_emotion": 77.1,
            "image_quality": 80.0,
            "image_scene": 95.3,
            "image_style": 85.9,
            "image_topic": 95.3,
            "nature_relation": 87.7,
            "object_localization": 76.9,
            "ocr": 97.4,
            "physical_property_reasoning": 62.0,
            "physical_relation": 50.0,
            "social_relation": 75.6,
            "spatial_relationship": 71.6,
            "structuralized_imagetext_understanding": 85.1,
            "Method": [
                "Claude3.7-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2025/02/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Claude3-7V_Sonnet",
            "key": 466
        },
        {
            "Overall": 78.9,
            "AR": 78.8,
            "CP": 82.9,
            "FP-C": 73.3,
            "FP-S": 81.9,
            "LR": 75.7,
            "RR": 73.5,
            "action_recognition": 90.9,
            "attribute_comparison": 71.8,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 76.3,
            "function_reasoning": 85.8,
            "future_prediction": 72.2,
            "identity_reasoning": 93.9,
            "image_emotion": 71.1,
            "image_quality": 72.9,
            "image_scene": 92.2,
            "image_style": 77.6,
            "image_topic": 95.3,
            "nature_relation": 79.0,
            "object_localization": 71.2,
            "ocr": 94.8,
            "physical_property_reasoning": 59.0,
            "physical_relation": 55.8,
            "social_relation": 79.5,
            "spatial_relationship": 55.6,
            "structuralized_imagetext_understanding": 78.2,
            "Method": [
                "moonshot-v1-8k",
                "https://platform.moonshot.cn/docs/api/chat"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Moonshot AI",
            "Time": "2025/03/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "moonshot-v1-8k",
            "key": 467
        },
        {
            "Overall": 84.8,
            "AR": 85.4,
            "CP": 83.9,
            "FP-C": 82.2,
            "FP-S": 91.2,
            "LR": 82.1,
            "RR": 78.7,
            "action_recognition": 94.3,
            "attribute_comparison": 76.9,
            "attribute_recognition": 97.0,
            "celebrity_recognition": 90.7,
            "function_reasoning": 91.5,
            "future_prediction": 83.3,
            "identity_reasoning": 98.8,
            "image_emotion": 78.3,
            "image_quality": 70.6,
            "image_scene": 92.2,
            "image_style": 78.8,
            "image_topic": 95.3,
            "nature_relation": 92.6,
            "object_localization": 79.8,
            "ocr": 100.0,
            "physical_property_reasoning": 68.0,
            "physical_relation": 50.0,
            "social_relation": 83.3,
            "spatial_relationship": 74.1,
            "structuralized_imagetext_understanding": 81.2,
            "Method": [
                "grok-2-vision-1212",
                "https://docs.x.ai/docs/overview"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "xAI",
            "Time": "2025/03/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "grok-2-vision-1212",
            "key": 468
        },
        {
            "Overall": 82.4,
            "AR": 84.0,
            "CP": 88.2,
            "FP-C": 78.1,
            "FP-S": 85.9,
            "LR": 69.9,
            "RR": 75.8,
            "action_recognition": 94.3,
            "attribute_comparison": 83.3,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 84.7,
            "function_reasoning": 86.8,
            "future_prediction": 75.0,
            "identity_reasoning": 96.3,
            "image_emotion": 80.7,
            "image_quality": 84.7,
            "image_scene": 95.3,
            "image_style": 81.2,
            "image_topic": 95.3,
            "nature_relation": 80.2,
            "object_localization": 76.9,
            "ocr": 94.8,
            "physical_property_reasoning": 71.0,
            "physical_relation": 53.8,
            "social_relation": 85.9,
            "spatial_relationship": 55.6,
            "structuralized_imagetext_understanding": 66.3,
            "Method": [
                "DeepSeek-VL2",
                "https://huggingface.co/deepseek-ai/deepseek-vl2"
            ],
            "Parameters": "27.5B",
            "Language Model": "DeepSeekMoE-27B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2",
            "key": 469
        },
        {
            "Overall": 55.0,
            "AR": 66.0,
            "CP": 66.8,
            "FP-C": 45.3,
            "FP-S": 48.5,
            "LR": 43.4,
            "RR": 46.9,
            "action_recognition": 88.6,
            "attribute_comparison": 23.1,
            "attribute_recognition": 61.6,
            "celebrity_recognition": 33.9,
            "function_reasoning": 69.8,
            "future_prediction": 58.3,
            "identity_reasoning": 79.3,
            "image_emotion": 66.3,
            "image_quality": 42.4,
            "image_scene": 86.0,
            "image_style": 43.5,
            "image_topic": 85.9,
            "nature_relation": 38.3,
            "object_localization": 26.0,
            "ocr": 84.4,
            "physical_property_reasoning": 51.0,
            "physical_relation": 32.7,
            "social_relation": 65.4,
            "spatial_relationship": 19.8,
            "structuralized_imagetext_understanding": 32.7,
            "Method": [
                "SmolVLM2",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct"
            ],
            "Parameters": "2.25B",
            "Language Model": "SmolLM2-1.7M",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2",
            "key": 470
        },
        {
            "Overall": 2.1,
            "AR": 2.8,
            "CP": 1.9,
            "FP-C": 0.4,
            "FP-S": 4.8,
            "LR": 0.6,
            "RR": 0.0,
            "action_recognition": 0.0,
            "attribute_comparison": 0.0,
            "attribute_recognition": 2.0,
            "celebrity_recognition": 0.0,
            "function_reasoning": 0.0,
            "future_prediction": 0.0,
            "identity_reasoning": 1.2,
            "image_emotion": 0.0,
            "image_quality": 8.2,
            "image_scene": 0.8,
            "image_style": 1.2,
            "image_topic": 0.0,
            "nature_relation": 0.0,
            "object_localization": 0.0,
            "ocr": 22.1,
            "physical_property_reasoning": 7.0,
            "physical_relation": 0.0,
            "social_relation": 0.0,
            "spatial_relationship": 1.2,
            "structuralized_imagetext_understanding": 1.0,
            "Method": [
                "SmolVLM2-256M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-256M-Video-Instruct"
            ],
            "Parameters": "0.26B",
            "Language Model": "SmolLM2-135M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2-256M",
            "key": 471
        },
        {
            "Overall": 34.9,
            "AR": 43.8,
            "CP": 45.2,
            "FP-C": 23.5,
            "FP-S": 30.4,
            "LR": 19.7,
            "RR": 34.6,
            "action_recognition": 47.7,
            "attribute_comparison": 11.5,
            "attribute_recognition": 39.4,
            "celebrity_recognition": 8.5,
            "function_reasoning": 35.8,
            "future_prediction": 40.3,
            "identity_reasoning": 59.8,
            "image_emotion": 44.6,
            "image_quality": 10.6,
            "image_scene": 67.4,
            "image_style": 30.6,
            "image_topic": 61.2,
            "nature_relation": 35.8,
            "object_localization": 8.7,
            "ocr": 81.8,
            "physical_property_reasoning": 39.0,
            "physical_relation": 7.7,
            "social_relation": 51.3,
            "spatial_relationship": 8.6,
            "structuralized_imagetext_understanding": 5.0,
            "Method": [
                "SmolVLM2-500M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
            ],
            "Parameters": "0.51B",
            "Language Model": "SmolLM2-360M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2-500M",
            "key": 472
        },
        {
            "Overall": 77.7,
            "AR": 84.0,
            "CP": 83.5,
            "FP-C": 72.1,
            "FP-S": 78.1,
            "LR": 68.8,
            "RR": 69.2,
            "action_recognition": 92.0,
            "attribute_comparison": 78.2,
            "attribute_recognition": 83.8,
            "celebrity_recognition": 74.6,
            "function_reasoning": 85.8,
            "future_prediction": 79.2,
            "identity_reasoning": 93.9,
            "image_emotion": 69.9,
            "image_quality": 77.6,
            "image_scene": 92.2,
            "image_style": 76.5,
            "image_topic": 96.5,
            "nature_relation": 77.8,
            "object_localization": 65.4,
            "ocr": 93.5,
            "physical_property_reasoning": 74.0,
            "physical_relation": 44.2,
            "social_relation": 76.9,
            "spatial_relationship": 44.4,
            "structuralized_imagetext_understanding": 61.4,
            "Method": [
                "Phi-4-MultiModal",
                "https://huggingface.co/microsoft/Phi-4-multimodal-instruct"
            ],
            "Parameters": "5.57B",
            "Language Model": "Phi-4-Mini",
            "Vision Model": "SigLIP-400M",
            "Org": "Microsoft",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Phi-4-Vision",
            "key": 473
        },
        {
            "Overall": 83.2,
            "AR": 83.7,
            "CP": 88.0,
            "FP-C": 75.3,
            "FP-S": 85.9,
            "LR": 74.0,
            "RR": 83.9,
            "action_recognition": 93.2,
            "attribute_comparison": 83.3,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 78.8,
            "function_reasoning": 89.6,
            "future_prediction": 79.2,
            "identity_reasoning": 97.6,
            "image_emotion": 81.9,
            "image_quality": 85.9,
            "image_scene": 92.2,
            "image_style": 81.2,
            "image_topic": 96.5,
            "nature_relation": 87.7,
            "object_localization": 78.8,
            "ocr": 97.4,
            "physical_property_reasoning": 66.0,
            "physical_relation": 63.5,
            "social_relation": 93.6,
            "spatial_relationship": 48.1,
            "structuralized_imagetext_understanding": 70.3,
            "Method": [
                "MUG-U-7B",
                "https://github.com/Shopee-MUG/MUG-U"
            ],
            "Parameters": "7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Shopee",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MUG-U-7B",
            "key": 474
        },
        {
            "Overall": 69.7,
            "AR": 77.4,
            "CP": 79.2,
            "FP-C": 55.1,
            "FP-S": 68.8,
            "LR": 51.4,
            "RR": 71.6,
            "action_recognition": 92.0,
            "attribute_comparison": 43.6,
            "attribute_recognition": 80.8,
            "celebrity_recognition": 83.1,
            "function_reasoning": 84.9,
            "future_prediction": 63.9,
            "identity_reasoning": 92.7,
            "image_emotion": 73.5,
            "image_quality": 51.8,
            "image_scene": 93.8,
            "image_style": 72.9,
            "image_topic": 96.5,
            "nature_relation": 79.0,
            "object_localization": 22.1,
            "ocr": 94.8,
            "physical_property_reasoning": 57.0,
            "physical_relation": 38.5,
            "social_relation": 85.9,
            "spatial_relationship": 25.9,
            "structuralized_imagetext_understanding": 42.6,
            "Method": [
                "Gemma3-4B",
                "https://huggingface.co/google/gemma-3-4b-it"
            ],
            "Parameters": "4.3B",
            "Language Model": "Gemma3-4B",
            "Vision Model": "SigLIP-400M",
            "Org": "Google",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Gemma3-4B",
            "key": 475
        },
        {
            "Overall": 77.1,
            "AR": 81.6,
            "CP": 82.2,
            "FP-C": 66.4,
            "FP-S": 78.1,
            "LR": 69.4,
            "RR": 76.3,
            "action_recognition": 90.9,
            "attribute_comparison": 65.4,
            "attribute_recognition": 85.9,
            "celebrity_recognition": 84.7,
            "function_reasoning": 86.8,
            "future_prediction": 73.6,
            "identity_reasoning": 97.6,
            "image_emotion": 69.9,
            "image_quality": 67.1,
            "image_scene": 92.2,
            "image_style": 80.0,
            "image_topic": 96.5,
            "nature_relation": 86.4,
            "object_localization": 52.9,
            "ocr": 92.2,
            "physical_property_reasoning": 63.0,
            "physical_relation": 44.2,
            "social_relation": 87.2,
            "spatial_relationship": 40.7,
            "structuralized_imagetext_understanding": 66.3,
            "Method": [
                "Gemma3-12B",
                "https://huggingface.co/google/gemma-3-12b-it"
            ],
            "Parameters": "12.2B",
            "Language Model": "Gemma3-12B",
            "Vision Model": "SigLIP-400M",
            "Org": "Google",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Gemma3-12B",
            "key": 476
        },
        {
            "Overall": 46.8,
            "AR": 57.3,
            "CP": 55.7,
            "FP-C": 40.9,
            "FP-S": 40.7,
            "LR": 25.4,
            "RR": 48.8,
            "action_recognition": 70.5,
            "attribute_comparison": 30.8,
            "attribute_recognition": 40.4,
            "celebrity_recognition": 32.2,
            "function_reasoning": 54.7,
            "future_prediction": 41.7,
            "identity_reasoning": 75.6,
            "image_emotion": 57.8,
            "image_quality": 7.1,
            "image_scene": 82.9,
            "image_style": 38.8,
            "image_topic": 77.6,
            "nature_relation": 49.4,
            "object_localization": 21.2,
            "ocr": 80.5,
            "physical_property_reasoning": 45.0,
            "physical_relation": 21.2,
            "social_relation": 66.7,
            "spatial_relationship": 18.5,
            "structuralized_imagetext_understanding": 13.9,
            "Method": [
                "AKI-4B",
                "https://huggingface.co/Sony/AKI-4B-phi-3.5-mini"
            ],
            "Parameters": "4.33B",
            "Language Model": "Phi-3.5",
            "Vision Model": "SigLIP-400M",
            "Org": "Sony",
            "Time": "2025/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "AKI",
            "key": 478
        },
        {
            "Overall": 81.9,
            "AR": 83.3,
            "CP": 86.5,
            "FP-C": 74.9,
            "FP-S": 89.4,
            "LR": 68.2,
            "RR": 74.9,
            "action_recognition": 93.2,
            "attribute_comparison": 76.9,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 90.7,
            "function_reasoning": 90.6,
            "future_prediction": 73.6,
            "identity_reasoning": 97.6,
            "image_emotion": 74.7,
            "image_quality": 82.4,
            "image_scene": 94.6,
            "image_style": 80.0,
            "image_topic": 96.5,
            "nature_relation": 76.5,
            "object_localization": 80.8,
            "ocr": 97.4,
            "physical_property_reasoning": 64.0,
            "physical_relation": 57.7,
            "social_relation": 84.6,
            "spatial_relationship": 53.1,
            "structuralized_imagetext_understanding": 64.4,
            "Method": [
                "Kimi-VL-A3B-Instruct",
                "https://huggingface.co/moonshotai/Kimi-VL-A3B-Instruct"
            ],
            "Parameters": "16.4B",
            "Language Model": "Moonlight-16B-A3B",
            "Vision Model": "MoonViT",
            "Org": "moonshot.ai",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kimi-VL-A3B-Instruct",
            "key": 483
        },
        {
            "Overall": 68.0,
            "AR": 73.3,
            "CP": 78.6,
            "FP-C": 57.9,
            "FP-S": 71.6,
            "LR": 43.9,
            "RR": 62.6,
            "action_recognition": 93.2,
            "attribute_comparison": 44.9,
            "attribute_recognition": 76.8,
            "celebrity_recognition": 62.7,
            "function_reasoning": 78.3,
            "future_prediction": 61.1,
            "identity_reasoning": 93.9,
            "image_emotion": 78.3,
            "image_quality": 47.1,
            "image_scene": 93.8,
            "image_style": 71.8,
            "image_topic": 94.1,
            "nature_relation": 55.6,
            "object_localization": 59.6,
            "ocr": 94.8,
            "physical_property_reasoning": 51.0,
            "physical_relation": 40.4,
            "social_relation": 84.6,
            "spatial_relationship": 32.1,
            "structuralized_imagetext_understanding": 31.7,
            "Method": [
                "InternVL3-1B",
                "https://huggingface.co/OpenGVLab/InternVL3-1B"
            ],
            "Parameters": "0.94B",
            "Language Model": "Qwen2.5-0.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-1B",
            "key": 484
        },
        {
            "Overall": 79.0,
            "AR": 83.0,
            "CP": 84.8,
            "FP-C": 70.9,
            "FP-S": 82.4,
            "LR": 63.6,
            "RR": 76.8,
            "action_recognition": 94.3,
            "attribute_comparison": 76.9,
            "attribute_recognition": 88.9,
            "celebrity_recognition": 75.4,
            "function_reasoning": 88.7,
            "future_prediction": 72.2,
            "identity_reasoning": 97.6,
            "image_emotion": 77.1,
            "image_quality": 80.0,
            "image_scene": 91.5,
            "image_style": 75.3,
            "image_topic": 96.5,
            "nature_relation": 81.5,
            "object_localization": 75.0,
            "ocr": 94.8,
            "physical_property_reasoning": 65.0,
            "physical_relation": 48.1,
            "social_relation": 91.0,
            "spatial_relationship": 39.5,
            "structuralized_imagetext_understanding": 57.4,
            "Method": [
                "InternVL3-2B",
                "https://huggingface.co/OpenGVLab/InternVL3-2B"
            ],
            "Parameters": "2.09B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-2B",
            "key": 485
        },
        {
            "Overall": 82.7,
            "AR": 84.0,
            "CP": 86.1,
            "FP-C": 78.1,
            "FP-S": 86.7,
            "LR": 69.4,
            "RR": 82.5,
            "action_recognition": 96.6,
            "attribute_comparison": 80.8,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 83.1,
            "function_reasoning": 88.7,
            "future_prediction": 75.0,
            "identity_reasoning": 98.8,
            "image_emotion": 80.7,
            "image_quality": 82.4,
            "image_scene": 91.5,
            "image_style": 75.3,
            "image_topic": 97.6,
            "nature_relation": 86.4,
            "object_localization": 77.9,
            "ocr": 96.1,
            "physical_property_reasoning": 67.0,
            "physical_relation": 69.2,
            "social_relation": 87.2,
            "spatial_relationship": 55.6,
            "structuralized_imagetext_understanding": 65.3,
            "Method": [
                "InternVL3-8B",
                "https://huggingface.co/OpenGVLab/InternVL3-8B"
            ],
            "Parameters": "7.94B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-8B",
            "key": 486
        },
        {
            "Overall": 83.6,
            "AR": 80.6,
            "CP": 87.8,
            "FP-C": 79.4,
            "FP-S": 87.4,
            "LR": 73.4,
            "RR": 84.8,
            "action_recognition": 94.3,
            "attribute_comparison": 91.0,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 82.2,
            "function_reasoning": 89.6,
            "future_prediction": 77.8,
            "identity_reasoning": 98.8,
            "image_emotion": 79.5,
            "image_quality": 83.5,
            "image_scene": 96.9,
            "image_style": 78.8,
            "image_topic": 95.3,
            "nature_relation": 92.6,
            "object_localization": 80.8,
            "ocr": 96.1,
            "physical_property_reasoning": 56.0,
            "physical_relation": 69.2,
            "social_relation": 87.2,
            "spatial_relationship": 51.9,
            "structuralized_imagetext_understanding": 70.3,
            "Method": [
                "InternVL3-9B",
                "https://huggingface.co/OpenGVLab/InternVL3-9B"
            ],
            "Parameters": "9.14B",
            "Language Model": "InternLM3-8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-9B",
            "key": 487
        },
        {
            "Overall": 84.4,
            "AR": 85.4,
            "CP": 86.1,
            "FP-C": 80.6,
            "FP-S": 87.7,
            "LR": 76.9,
            "RR": 83.4,
            "action_recognition": 93.2,
            "attribute_comparison": 79.5,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 83.1,
            "function_reasoning": 90.6,
            "future_prediction": 76.4,
            "identity_reasoning": 96.3,
            "image_emotion": 74.7,
            "image_quality": 83.5,
            "image_scene": 92.2,
            "image_style": 80.0,
            "image_topic": 96.5,
            "nature_relation": 84.0,
            "object_localization": 83.7,
            "ocr": 97.4,
            "physical_property_reasoning": 71.0,
            "physical_relation": 76.9,
            "social_relation": 87.2,
            "spatial_relationship": 67.9,
            "structuralized_imagetext_understanding": 77.2,
            "Method": [
                "InternVL3-14B",
                "https://huggingface.co/OpenGVLab/InternVL3-14B"
            ],
            "Parameters": "15.1B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-14B",
            "key": 488
        },
        {
            "Overall": 86.9,
            "AR": 88.5,
            "CP": 85.2,
            "FP-C": 85.0,
            "FP-S": 91.7,
            "LR": 83.2,
            "RR": 84.4,
            "action_recognition": 94.3,
            "attribute_comparison": 89.7,
            "attribute_recognition": 97.0,
            "celebrity_recognition": 86.4,
            "function_reasoning": 91.5,
            "future_prediction": 77.8,
            "identity_reasoning": 98.8,
            "image_emotion": 77.1,
            "image_quality": 80.0,
            "image_scene": 93.0,
            "image_style": 75.3,
            "image_topic": 96.5,
            "nature_relation": 86.4,
            "object_localization": 87.5,
            "ocr": 98.7,
            "physical_property_reasoning": 77.0,
            "physical_relation": 75.0,
            "social_relation": 88.5,
            "spatial_relationship": 70.4,
            "structuralized_imagetext_understanding": 87.1,
            "Method": [
                "InternVL3-38B",
                "https://huggingface.co/OpenGVLab/InternVL3-38B"
            ],
            "Parameters": "38.4B",
            "Language Model": "Qwen2.5-32B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-38B",
            "key": 489
        },
        {
            "Overall": 88.8,
            "AR": 87.8,
            "CP": 89.5,
            "FP-C": 87.4,
            "FP-S": 93.2,
            "LR": 81.5,
            "RR": 87.7,
            "action_recognition": 94.3,
            "attribute_comparison": 89.7,
            "attribute_recognition": 97.0,
            "celebrity_recognition": 91.5,
            "function_reasoning": 91.5,
            "future_prediction": 80.6,
            "identity_reasoning": 98.8,
            "image_emotion": 79.5,
            "image_quality": 87.1,
            "image_scene": 96.1,
            "image_style": 84.7,
            "image_topic": 96.5,
            "nature_relation": 91.4,
            "object_localization": 87.5,
            "ocr": 98.7,
            "physical_property_reasoning": 75.0,
            "physical_relation": 82.7,
            "social_relation": 87.2,
            "spatial_relationship": 77.8,
            "structuralized_imagetext_understanding": 82.2,
            "Method": [
                "InternVL3-78B",
                "https://huggingface.co/OpenGVLab/InternVL3-78B"
            ],
            "Parameters": "78.4B",
            "Language Model": "Qwen2.5-72B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-78B",
            "key": 490
        },
        {
            "Overall": 86.8,
            "AR": 87.2,
            "CP": 89.3,
            "FP-C": 85.0,
            "FP-S": 86.4,
            "LR": 89.0,
            "RR": 81.5,
            "action_recognition": 96.6,
            "attribute_comparison": 83.3,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 77.1,
            "function_reasoning": 90.6,
            "future_prediction": 84.7,
            "identity_reasoning": 98.8,
            "image_emotion": 81.9,
            "image_quality": 87.1,
            "image_scene": 93.8,
            "image_style": 83.5,
            "image_topic": 97.6,
            "nature_relation": 96.3,
            "object_localization": 80.8,
            "ocr": 100.0,
            "physical_property_reasoning": 74.0,
            "physical_relation": 55.8,
            "social_relation": 83.3,
            "spatial_relationship": 74.1,
            "structuralized_imagetext_understanding": 92.1,
            "Method": [
                "GPT-4.1-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-2025-04-14",
            "key": 491
        },
        {
            "Overall": 85.5,
            "AR": 84.4,
            "CP": 87.6,
            "FP-C": 84.6,
            "FP-S": 86.7,
            "LR": 86.7,
            "RR": 80.6,
            "action_recognition": 92.0,
            "attribute_comparison": 88.5,
            "attribute_recognition": 85.9,
            "celebrity_recognition": 84.7,
            "function_reasoning": 87.7,
            "future_prediction": 80.6,
            "identity_reasoning": 98.8,
            "image_emotion": 77.1,
            "image_quality": 83.5,
            "image_scene": 95.3,
            "image_style": 83.5,
            "image_topic": 94.1,
            "nature_relation": 91.4,
            "object_localization": 80.8,
            "ocr": 98.7,
            "physical_property_reasoning": 69.0,
            "physical_relation": 61.5,
            "social_relation": 82.1,
            "spatial_relationship": 72.8,
            "structuralized_imagetext_understanding": 91.1,
            "Method": [
                "GPT-4.1-mini-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-mini-2025-04-14",
            "key": 492
        },
        {
            "Overall": 65.1,
            "AR": 76.4,
            "CP": 76.7,
            "FP-C": 54.3,
            "FP-S": 60.6,
            "LR": 54.3,
            "RR": 54.0,
            "action_recognition": 84.1,
            "attribute_comparison": 43.6,
            "attribute_recognition": 77.8,
            "celebrity_recognition": 44.9,
            "function_reasoning": 83.0,
            "future_prediction": 66.7,
            "identity_reasoning": 91.5,
            "image_emotion": 69.9,
            "image_quality": 44.7,
            "image_scene": 93.0,
            "image_style": 74.1,
            "image_topic": 92.9,
            "nature_relation": 46.9,
            "object_localization": 39.4,
            "ocr": 90.9,
            "physical_property_reasoning": 57.0,
            "physical_relation": 34.6,
            "social_relation": 74.4,
            "spatial_relationship": 32.1,
            "structuralized_imagetext_understanding": 45.5,
            "Method": [
                "GPT-4.1-nano-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-nano-2025-04-14",
            "key": 493
        },
        {
            "Overall": 68.4,
            "AR": 76.7,
            "CP": 78.6,
            "FP-C": 65.2,
            "FP-S": 62.6,
            "LR": 53.8,
            "RR": 61.6,
            "action_recognition": 92.0,
            "attribute_comparison": 74.4,
            "attribute_recognition": 71.7,
            "celebrity_recognition": 48.3,
            "function_reasoning": 78.3,
            "future_prediction": 58.3,
            "identity_reasoning": 93.9,
            "image_emotion": 73.5,
            "image_quality": 67.1,
            "image_scene": 89.1,
            "image_style": 64.7,
            "image_topic": 92.9,
            "nature_relation": 54.3,
            "object_localization": 48.1,
            "ocr": 92.2,
            "physical_property_reasoning": 61.0,
            "physical_relation": 44.2,
            "social_relation": 80.8,
            "spatial_relationship": 27.2,
            "structuralized_imagetext_understanding": 50.5,
            "Method": [
                "granite-vision-3.2-2b",
                "https://huggingface.co/ibm-granite/granite-vision-3.2-2b"
            ],
            "Parameters": "2.98B",
            "Language Model": "granite-3.1-2b-instruct",
            "Vision Model": "SigLip",
            "Org": "IBM",
            "Time": "2025/06/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "granite_vision_3.2_2b",
            "key": 509
        },
        {
            "Overall": 67.3,
            "AR": 74.7,
            "CP": 75.8,
            "FP-C": 60.7,
            "FP-S": 64.8,
            "LR": 53.2,
            "RR": 62.1,
            "action_recognition": 90.9,
            "attribute_comparison": 71.8,
            "attribute_recognition": 71.7,
            "celebrity_recognition": 49.2,
            "function_reasoning": 79.2,
            "future_prediction": 58.3,
            "identity_reasoning": 92.7,
            "image_emotion": 74.7,
            "image_quality": 56.5,
            "image_scene": 88.4,
            "image_style": 56.5,
            "image_topic": 96.5,
            "nature_relation": 55.6,
            "object_localization": 56.7,
            "ocr": 90.9,
            "physical_property_reasoning": 55.0,
            "physical_relation": 42.3,
            "social_relation": 82.1,
            "spatial_relationship": 17.3,
            "structuralized_imagetext_understanding": 49.5,
            "Method": [
                "granite-vision-3.3-2b",
                "https://huggingface.co/ibm-granite/granite-vision-3.3-2b"
            ],
            "Parameters": "2.98B",
            "Language Model": "granite-3.1-2b-instruct",
            "Vision Model": "SigLIP2-400M",
            "Org": "IBM",
            "Time": "2025/06/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "granite_vision_3.3_2b",
            "key": 510
        }
    ],
    "MMBench_TEST_EN_Data": [
        {
            "Method": [
                "yuntiantianshu-3.0V",
                "https://www.intellif.com/"
            ],
            "Parameters": "",
            "Language Model": "tianshu-v3",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "yuntianlifei",
            "Time": "2024/05/13",
            "Verified": "No",
            "OpenSource": "No",
            "key": 259,
            "Overall": 83.6,
            "CP": 86.7,
            "FP-S": 90.5,
            "FP-C": 82.2,
            "AR": 76.4,
            "LR": 71.7,
            "RR": 85.3
        },
        {
            "Method": [
                "InternVL-Chat-V1.2-Plus",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "40B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/03/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 196,
            "Overall": 83.5,
            "CP": 85.9,
            "FP-S": 90.2,
            "FP-C": 82.2,
            "AR": 82.3,
            "LR": 68.2,
            "RR": 81.5
        },
        {
            "Method": [
                "GPT-4o (0513, detail-high)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 270,
            "Overall": 83.4,
            "CP": 87.4,
            "FP-S": 78.9,
            "FP-C": 83.8,
            "AR": 86.5,
            "LR": 80.3,
            "RR": 80.6
        },
        {
            "Method": [
                "GPT-4o (0513, detail-low)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 260,
            "Overall": 83.3,
            "CP": 87.6,
            "FP-S": 80.2,
            "FP-C": 84.6,
            "AR": 86.1,
            "LR": 77.5,
            "RR": 79.1
        },
        {
            "Method": [
                "Qwen-VL-Plus Base",
                "https://github.com/QwenLM/Qwen-VL?tab=readme-ov-file#qwen-vl-plus"
            ],
            "Parameters": "",
            "Language Model": "QwenLM",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2023/12/15",
            "OpenSource": "No",
            "Verified": "No",
            "key": 54,
            "Overall": 83.3,
            "CP": 86.7,
            "FP-S": 88.4,
            "FP-C": 72.1,
            "AR": 86.5,
            "LR": 75.1,
            "RR": 81.5
        },
        {
            "Method": [
                "Skywork-VL",
                "https://github.com/SkyworkAI/Skywork"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Skywork AI",
            "Time": "2024/05/31",
            "Verified": "No",
            "OpenSource": "No",
            "key": 272,
            "Overall": 82.5,
            "CP": 85.7,
            "FP-S": 88.9,
            "FP-C": 78.5,
            "AR": 83.3,
            "LR": 64.7,
            "RR": 81.5
        },
        {
            "Method": [
                "InternVL-Chat-V1.2",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "40B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/02/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 195,
            "Overall": 82.4,
            "CP": 85.2,
            "FP-S": 88.4,
            "FP-C": 77.7,
            "AR": 83.7,
            "LR": 67.1,
            "RR": 81.0
        },
        {
            "Method": [
                "InternVL-Chat-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/04/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 241,
            "Overall": 82.3,
            "CP": 85.0,
            "FP-S": 87.7,
            "FP-C": 74.1,
            "AR": 85.8,
            "LR": 69.9,
            "RR": 81.0
        },
        {
            "Method": [
                "TransCore-M",
                "https://github.com/PCIResearch/TransCore-M"
            ],
            "Parameters": "13.4B",
            "Language Model": "PCITransGPT-13B",
            "Vision Model": "CLIP ViT/L-14",
            "Org": "PCI Research",
            "Time": "2024/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 236,
            "Overall": 82.3,
            "CP": 85.0,
            "FP-S": 87.7,
            "FP-C": 74.1,
            "AR": 85.8,
            "LR": 69.9,
            "RR": 81.0
        },
        {
            "Method": [
                "GLM-4v",
                "https://open.bigmodel.cn/dev/api#glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2024/05/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 263,
            "Overall": 81.3,
            "CP": 85.2,
            "FP-S": 84.9,
            "FP-C": 73.3,
            "AR": 86.1,
            "LR": 67.6,
            "RR": 80.1
        },
        {
            "Method": [
                "Weitu-VL-1.0",
                ""
            ],
            "Parameters": "15B",
            "Vision Model": "",
            "Language Model": "",
            "Org": "Weitu AI",
            "Time": "2024/04/03",
            "Verified": "No",
            "OpenSource": "No",
            "key": 223,
            "Overall": 81.1,
            "CP": 86.1,
            "FP-S": 84.7,
            "FP-C": 75.3,
            "AR": 80.2,
            "LR": 61.8,
            "RR": 87.2
        },
        {
            "Method": [
                "LLaVA-Next-Yi-34B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "34.8B",
            "Language Model": "Yi-34B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 213,
            "Overall": 81.1,
            "CP": 84.8,
            "FP-S": 84.7,
            "FP-C": 78.1,
            "AR": 83.3,
            "LR": 67.6,
            "RR": 77.3
        },
        {
            "Method": [
                "GPT-4v (0409, detail-high)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 246,
            "Overall": 81.0,
            "CP": 85.2,
            "FP-S": 86.4,
            "FP-C": 73.3,
            "AR": 81.2,
            "LR": 75.1,
            "RR": 74.9
        },
        {
            "Method": [
                "GPT-4v (0409, detail-low)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 244,
            "Overall": 80.8,
            "CP": 84.4,
            "FP-S": 84.7,
            "FP-C": 74.1,
            "AR": 82.3,
            "LR": 75.7,
            "RR": 75.4
        },
        {
            "Method": [
                "InternLM-XComposer2",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 132,
            "Overall": 80.7,
            "CP": 87.4,
            "FP-S": 85.4,
            "FP-C": 74.1,
            "AR": 81.6,
            "LR": 65.9,
            "RR": 75.4
        },
        {
            "Method": [
                "InternLM-XComposer2-4KHD",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 276,
            "Overall": 80.2,
            "CP": 84.8,
            "FP-S": 84.4,
            "FP-C": 71.7,
            "AR": 84.0,
            "LR": 71.1,
            "RR": 73.9
        },
        {
            "Method": [
                "WeMM",
                "https://github.com/scenarios/WeMM/tree/main"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "SigLip-400M",
            "Org": "WechatCV",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 273,
            "Overall": 79.3,
            "CP": 85.9,
            "FP-S": 84.2,
            "FP-C": 72.5,
            "AR": 81.9,
            "LR": 64.7,
            "RR": 72.0
        },
        {
            "Method": [
                "360VL-70B",
                "https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5"
            ],
            "Parameters": "70B",
            "Language Model": "Llama-3-70B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "QiHoo360",
            "Time": "2024/05/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 264,
            "Overall": 78.8,
            "CP": 82.0,
            "FP-S": 85.9,
            "FP-C": 74.1,
            "AR": 85.1,
            "LR": 56.1,
            "RR": 73.9
        },
        {
            "Method": [
                "Marco-VL-Plus",
                ""
            ],
            "Parameters": "",
            "Vision Model": "CLIP ViT-L/14",
            "Language Model": "Marco-Chat",
            "Org": "Alibaba",
            "Time": "2024/04/09",
            "Verified": "No",
            "OpenSource": "No",
            "key": 224,
            "Overall": 78.2,
            "CP": 83.3,
            "FP-S": 83.7,
            "FP-C": 72.5,
            "AR": 81.2,
            "LR": 58.4,
            "RR": 75.4
        },
        {
            "Method": [
                "Marco-VL-34B",
                ""
            ],
            "Parameters": "34.2B",
            "Language Model": "Marco-Chat-34B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Alibaba",
            "Time": "2023/12/14",
            "OpenSource": "No",
            "Verified": "No",
            "key": 48,
            "Overall": 78.0,
            "CP": 84.4,
            "FP-S": 83.7,
            "FP-C": 70.9,
            "AR": 81.9,
            "LR": 56.1,
            "RR": 74.4
        },
        {
            "Method": [
                "MiniCPM-Llama3-V2.5",
                "https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLip-400M",
            "Org": "OpenBMB",
            "Time": "2024/05/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 265,
            "Overall": 77.6,
            "CP": 83.5,
            "FP-S": 84.4,
            "FP-C": 65.6,
            "AR": 79.5,
            "LR": 63.0,
            "RR": 75.4
        },
        {
            "Method": [
                "Qwen-VL-Max",
                "https://huggingface.co/spaces/Qwen/Qwen-VL-Max"
            ],
            "Parameters": "",
            "Language Model": "QwenLM",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 136,
            "Overall": 77.6,
            "CP": 82.2,
            "FP-S": 86.9,
            "FP-C": 64.8,
            "AR": 82.6,
            "LR": 59.5,
            "RR": 72.5
        },
        {
            "Method": [
                "EmbodiedGPT",
                "https://github.com/OpenGVLab/EmbodiedGPT"
            ],
            "Parameters": "8B",
            "Language Model": "LLaMA-7B",
            "Vision Model": "EVA-G",
            "Org": "The University of Hong Kong",
            "Time": "2024/02/06",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 139,
            "Overall": 77.5,
            "CP": 85.4,
            "FP-S": 78.1,
            "FP-C": 72.1,
            "AR": 81.9,
            "LR": 52.0,
            "RR": 80.1
        },
        {
            "Method": [
                "AntGMM-Chat",
                ""
            ],
            "Parameters": "8B",
            "Language Model": "LLaMA2-7B-ZH",
            "Vision Model": "AntGMM-Encoder-1B",
            "Org": "Ant Group",
            "Time": "2023/11/30",
            "Verified": "No",
            "OpenSource": "No",
            "key": 39,
            "Overall": 77.1,
            "CP": 84.8,
            "FP-S": 78.6,
            "FP-C": 66.0,
            "AR": 84.0,
            "LR": 59.5,
            "RR": 75.4
        },
        {
            "Method": [
                "GPT-4v (1106, detail-low)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2023/12/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 242,
            "Overall": 77.0,
            "CP": 84.8,
            "FP-S": 74.4,
            "FP-C": 70.9,
            "AR": 82.3,
            "LR": 66.5,
            "RR": 73.0
        },
        {
            "Method": [
                "RekaFlash",
                "https://www.reka.ai"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Reka AI",
            "Time": "2024/05/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 262,
            "Overall": 76.8,
            "CP": 83.1,
            "FP-S": 79.1,
            "FP-C": 69.6,
            "AR": 79.5,
            "LR": 64.2,
            "RR": 73.5
        },
        {
            "Method": [
                "Bumblebee-14B",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "14B",
            "Language Model": "Qwen2-14B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Monolith Foundation",
            "Time": "2024/04/26",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 249,
            "Overall": 76.8,
            "CP": 85.2,
            "FP-S": 78.9,
            "FP-C": 66.4,
            "AR": 83.0,
            "LR": 54.3,
            "RR": 76.8
        },
        {
            "Method": [
                "BlackSwan",
                ""
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "China Mobile (Suzhou) Software Technology Co., Ltd.",
            "Time": "2024/03/24",
            "Verified": "No",
            "OpenSource": "No",
            "key": 221,
            "Overall": 76.3,
            "CP": 84.6,
            "FP-S": 79.1,
            "FP-C": 65.2,
            "AR": 83.3,
            "LR": 54.3,
            "RR": 74.4
        },
        {
            "Method": [
                "Pink",
                "https://github.com/SY-Xuan/Pink"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Peking University, Ant Group",
            "Time": "2023/10/16",
            "key": 28,
            "Overall": 75.8,
            "CP": 80.7,
            "FP-S": 80.9,
            "FP-C": 66.4,
            "AR": 80.9,
            "LR": 62.4,
            "RR": 70.6,
            "Verified": "No",
            "OpenSource": "No"
        },
        {
            "Method": [
                "IDEFICS2-8B",
                "https://huggingface.co/HuggingFaceM4/idefics2-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Mistral-7B",
            "Vision Model": "SigLip-400M",
            "Org": "Hugging Face",
            "Time": "2024/04/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 248,
            "Overall": 75.7,
            "CP": 80.3,
            "FP-S": 79.9,
            "FP-C": 66.8,
            "AR": 82.3,
            "LR": 57.2,
            "RR": 73.9
        },
        {
            "Method": [
                "PureMM",
                "https://github.com/Q-MM/PureMM"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Tencent",
            "Time": "2024/01/16",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 116,
            "Overall": 75.5,
            "CP": 82.0,
            "FP-S": 78.9,
            "FP-C": 65.2,
            "AR": 80.2,
            "LR": 53.8,
            "RR": 78.2
        },
        {
            "Method": [
                "XVERSE-V-13B",
                "https://github.com/xverse-ai/XVERSE-V-13B"
            ],
            "Parameters": "13B",
            "Language Model": "XVERSE-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "XVERSE",
            "Time": "2024/05/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 256,
            "Overall": 75.4,
            "CP": 84.8,
            "FP-S": 81.9,
            "FP-C": 69.6,
            "AR": 73.3,
            "LR": 49.1,
            "RR": 73.5
        },
        {
            "Method": [
                "AllSeeing-v2",
                "https://github.com/OpenGVLab/all-seeing"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/03/19",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 198,
            "Overall": 75.2,
            "CP": 82.0,
            "FP-S": 83.2,
            "FP-C": 64.8,
            "AR": 82.3,
            "LR": 49.1,
            "RR": 69.2
        },
        {
            "Method": [
                "LLaVA-InternLM2-20B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "20.2B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 92,
            "Overall": 75.1,
            "CP": 82.9,
            "FP-S": 78.9,
            "FP-C": 68.4,
            "AR": 80.6,
            "LR": 52.0,
            "RR": 70.1
        },
        {
            "Method": [
                "InternVL-Chat-V1.1",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "19B",
            "Language Model": "LLaMA2-13B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/03/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 194,
            "Overall": 74.7,
            "CP": 83.7,
            "FP-S": 79.4,
            "FP-C": 66.8,
            "AR": 78.1,
            "LR": 51.4,
            "RR": 69.2
        },
        {
            "Method": [
                "Kanva-14B",
                "https://github.com/llp1992/Kanva"
            ],
            "Parameters": "14.2B",
            "Language Model": "Qwen-14B",
            "Vision Model": "EVA-CLIP-L/336",
            "Org": "KaLM",
            "Time": "2023/11/24",
            "Verified": "No",
            "OpenSource": "No",
            "key": 38,
            "Overall": 74.5,
            "CP": 82.7,
            "FP-S": 81.9,
            "FP-C": 64.0,
            "AR": 76.7,
            "LR": 46.2,
            "RR": 74.9
        },
        {
            "key": 22,
            "Method": [
                "InternLM-XComposer",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM-7B",
            "Vision Model": "EVA-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/9/26",
            "Overall": 74.4,
            "AR": 82.0,
            "CP": 81.7,
            "FP-C": 59.2,
            "FP-S": 79.3,
            "LR": 50.6,
            "RR": 76.1,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Method": [
                "HoneyBee",
                "https://github.com/kakaobrain/honeybee"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Kakao Brain",
            "Time": "2024/01/15",
            "OpenSource": "Yes",
            "Verified": "No",
            "key": 81,
            "Overall": 74.3,
            "CP": 83.1,
            "FP-S": 78.1,
            "FP-C": 63.2,
            "AR": 82.6,
            "LR": 50.9,
            "RR": 68.7
        },
        {
            "Method": [
                "CogVLM2-19B-Chat",
                "https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B"
            ],
            "Parameters": "19B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "EVA2-CLIP-E",
            "Org": "Zhipu AI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 269,
            "Overall": 73.9,
            "CP": 80.7,
            "FP-S": 77.4,
            "FP-C": 59.9,
            "AR": 79.2,
            "LR": 53.2,
            "RR": 78.7
        },
        {
            "Method": [
                "DeepSeek-VL-7B",
                "https://github.com/deepseek-ai/DeepSeek-VL"
            ],
            "Parameters": "7.3B",
            "Language Model": "DeekSeek-7B",
            "Vision Model": "SAM-B\nSigLIP-L",
            "Org": "DeepSeek",
            "Time": "2024/03/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 202,
            "Overall": 73.8,
            "CP": 83.5,
            "FP-S": 75.6,
            "FP-C": 65.2,
            "AR": 78.5,
            "LR": 52.6,
            "RR": 69.7
        },
        {
            "Method": [
                "mPLUG-Owl2.1",
                ""
            ],
            "Parameters": "9.8B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-G/16",
            "Org": "Alibaba",
            "Time": "2024/01/26",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 113,
            "Overall": 73.7,
            "CP": 82.4,
            "FP-S": 79.6,
            "FP-C": 62.8,
            "AR": 80.6,
            "LR": 46.8,
            "RR": 68.7
        },
        {
            "Method": [
                "Phi-3-Vision",
                "https://huggingface.co/microsoft/Phi-3-vision-128k-instruct"
            ],
            "Parameters": "4.2B",
            "Language Model": "Phi-3",
            "Vision Model": "CLIP ViT/L-14",
            "Org": "Microsoft",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 268,
            "Overall": 73.6,
            "CP": 79.4,
            "FP-S": 78.6,
            "FP-C": 61.5,
            "AR": 77.1,
            "LR": 63.0,
            "RR": 69.2
        },
        {
            "Method": [
                "Gemini-1.0-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2023/12/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 101,
            "Overall": 73.6,
            "CP": 77.7,
            "FP-S": 77.1,
            "FP-C": 63.6,
            "AR": 81.2,
            "LR": 58.4,
            "RR": 71.6
        },
        {
            "Method": [
                "LLaVA-InternLM2-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "8.1B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 91,
            "Overall": 73.3,
            "CP": 82.9,
            "FP-S": 75.6,
            "FP-C": 67.2,
            "AR": 78.5,
            "LR": 44.5,
            "RR": 71.6
        },
        {
            "Method": [
                "Marco-VL-13B",
                ""
            ],
            "Parameters": "13.2B",
            "Language Model": "Marco-Chat-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Alibaba",
            "Time": "2023/12/14",
            "OpenSource": "No",
            "Verified": "No",
            "key": 47,
            "Overall": 73.2,
            "CP": 83.3,
            "FP-S": 77.9,
            "FP-C": 66.4,
            "AR": 78.5,
            "LR": 48.0,
            "RR": 63.0
        },
        {
            "Method": [
                "InternLM-XComposer2-1.8B",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 275,
            "Overall": 73.0,
            "CP": 80.9,
            "FP-S": 78.4,
            "FP-C": 63.2,
            "AR": 78.5,
            "LR": 53.8,
            "RR": 65.4
        },
        {
            "Method": [
                "Marco-VL-6B",
                ""
            ],
            "Parameters": "6.2B",
            "Language Model": "Marco-Chat-6B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Alibaba",
            "Time": "2023/12/14",
            "OpenSource": "No",
            "Verified": "No",
            "key": 46,
            "Overall": 72.6,
            "CP": 79.2,
            "FP-S": 81.9,
            "FP-C": 63.6,
            "AR": 78.8,
            "LR": 48.6,
            "RR": 62.6
        },
        {
            "Method": [
                "Yi-VL-34B",
                "https://huggingface.co/01-ai/Yi-VL-34B"
            ],
            "Parameters": "34.6B",
            "Language Model": "Yi-34B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "01-AI",
            "Time": "2024/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 190,
            "Overall": 72.4,
            "CP": 78.8,
            "FP-S": 79.6,
            "FP-C": 58.7,
            "AR": 80.6,
            "LR": 49.1,
            "RR": 68.2
        },
        {
            "Method": [
                "Monkey-Chat",
                "https://github.com/Yuliang-Liu/Monkey"
            ],
            "Parameters": "9.8B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-BigHuge",
            "Org": "Huazhong University of Science and Technology",
            "Time": "2024/01/16",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 97,
            "Overall": 72.4,
            "CP": 81.6,
            "FP-S": 75.6,
            "FP-C": 60.3,
            "AR": 81.2,
            "LR": 52.6,
            "RR": 64.0
        },
        {
            "Method": [
                "Bumblebee-7B",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen-1.5-7B",
            "Vision Model": "SigLip-400M",
            "Org": "Monolith Foundation",
            "Time": "2024/05/07",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 250,
            "Overall": 71.9,
            "CP": 83.1,
            "FP-S": 72.9,
            "FP-C": 62.8,
            "AR": 80.2,
            "LR": 49.1,
            "RR": 63.0
        },
        {
            "key": 13,
            "Method": [
                "JiuTian",
                "https://github.com/rshaojimmy/JiuTian"
            ],
            "Parameters": "12.3B",
            "Overall": "71.8",
            "LR": "58.0",
            "AR": "82.0",
            "RR": "74.2",
            "FP-S": "70.8",
            "FP-C": "60.4",
            "CP": "76.6",
            "Language Model": "FLANT5-XXL",
            "Vision Model": "EVA-G",
            "Org": "HIT-Ruoyu",
            "Time": "2023/9/6",
            "Verified": "No",
            "OpenSource": "No"
        },
        {
            "Method": [
                "LLaVA-LLaMA-3-8B",
                "https://huggingface.co/xtuner/llava-llama-3-8b-v1_1"
            ],
            "Parameters": "8B",
            "Language Model": "LLaMA-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/05/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 254,
            "Overall": 71.7,
            "CP": 79.4,
            "FP-S": 73.6,
            "FP-C": 66.4,
            "AR": 80.2,
            "LR": 47.4,
            "RR": 65.9
        },
        {
            "Method": [
                "OmniLMM-12B",
                "https://huggingface.co/openbmb/OmniLMM-12B"
            ],
            "Parameters": "12B",
            "Language Model": "Zephyr-7B-β",
            "Vision Model": "EVA-02-5B",
            "Org": "OpenBMB",
            "Time": "2024/02/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 145,
            "Overall": 71.7,
            "CP": 78.2,
            "FP-S": 79.9,
            "FP-C": 61.1,
            "AR": 78.1,
            "LR": 46.2,
            "RR": 66.8
        },
        {
            "Method": [
                "RBDash-v1-13B",
                "https://huggingface.co/RBDash-Team/rbdash-v1-13b/tree/main"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "RBDash Team",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "No",
            "key": 73,
            "Overall": 71.1,
            "CP": 79.0,
            "FP-S": 77.6,
            "FP-C": 61.1,
            "AR": 77.1,
            "LR": 42.8,
            "RR": 67.8
        },
        {
            "Method": [
                "PaliGemma-3B-mix-448",
                "https://github.com/google-research/big_vision/blob/main/big_vision/configs/proj/paligemma/README.md"
            ],
            "Parameters": "3B",
            "Language Model": "Gemma-2B",
            "Vision Model": "SigLip-400M",
            "Org": "Google",
            "Time": "2024/05/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 261,
            "Overall": 71.0,
            "CP": 80.3,
            "FP-S": 73.9,
            "FP-C": 58.3,
            "AR": 78.8,
            "LR": 45.7,
            "RR": 69.7
        },
        {
            "Method": [
                "Sphinx-V2",
                "https://github.com/Alpha-VLLM/LLaMA2-Accessory/tree/main/SPHINX"
            ],
            "Parameters": "16.5B",
            "Language Model": "LLaMA2 13B",
            "Vision Model": "CLIP ViT-L/14\nCLIP ConvNeXT\nConvNeXT-XXLarge\nDinov2-VIT-G/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/11/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 34,
            "Overall": 71.0,
            "CP": 83.5,
            "FP-S": 78.6,
            "FP-C": 63.2,
            "AR": 72.9,
            "LR": 53.2,
            "RR": 49.8
        },
        {
            "Method": [
                "CatVision",
                ""
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "4paradigm.Inc",
            "Time": "2024/01/23",
            "Verified": "No",
            "OpenSource": "No",
            "key": 103,
            "Overall": 70.9,
            "CP": 78.8,
            "FP-S": 80.4,
            "FP-C": 60.3,
            "AR": 76.4,
            "LR": 46.8,
            "RR": 60.2
        },
        {
            "Method": [
                "Prompt Highlighter",
                "https://github.com/dvlab-research/Prompt-Highlighter"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "The Chinese University of Hong Kong",
            "Time": "2023/12/11",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 45,
            "Overall": 70.7,
            "CP": 79.4,
            "FP-S": 75.4,
            "FP-C": 61.5,
            "AR": 78.1,
            "LR": 45.1,
            "RR": 64.5
        },
        {
            "Method": [
                "LLaVA-Next-Vicuna-13B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 212,
            "Overall": 70.0,
            "CP": 78.2,
            "FP-S": 74.4,
            "FP-C": 61.9,
            "AR": 75.7,
            "LR": 48.0,
            "RR": 63.5
        },
        {
            "Method": [
                "ShareGPT4V-13B",
                "https://sharegpt4v.github.io"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 185,
            "Overall": 69.8,
            "CP": 81.2,
            "FP-S": 74.6,
            "FP-C": 61.9,
            "AR": 74.7,
            "LR": 41.0,
            "RR": 62.1
        },
        {
            "Method": [
                "LLaVA-Next-Mistral-7B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "7.6B",
            "Language Model": "Mistral-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 211,
            "Overall": 69.6,
            "CP": 76.9,
            "FP-S": 70.4,
            "FP-C": 64.8,
            "AR": 78.1,
            "LR": 52.6,
            "RR": 60.2
        },
        {
            "Method": [
                "LLaVA-Next-Vicuna-7B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "7.1B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 210,
            "Overall": 69.2,
            "CP": 79.2,
            "FP-S": 74.1,
            "FP-C": 59.9,
            "AR": 78.5,
            "LR": 39.9,
            "RR": 60.2
        },
        {
            "Method": [
                "Bunny-3B",
                "https://github.com/BAAI-DCAI/Bunny"
            ],
            "Parameters": "3B",
            "Language Model": "Phi-2",
            "Vision Model": "SigLip-400M",
            "Org": "Beijing Academy of Artificial Intelligence",
            "Time": "2024/02/13",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 155,
            "Overall": 69.2,
            "CP": 77.5,
            "FP-S": 70.4,
            "FP-C": 56.7,
            "AR": 80.6,
            "LR": 41.0,
            "RR": 70.6
        },
        {
            "Method": [
                "EasyGen",
                "https://github.com/zxy556677/EasyGen"
            ],
            "Parameters": "14.5B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14\nUniDiffuser",
            "Org": "The Hong Kong Polytechnic University",
            "Time": "2023/12/14",
            "OpenSource": "Yes",
            "Verified": "No",
            "key": 49,
            "Overall": 69.2,
            "CP": 76.7,
            "FP-S": 74.6,
            "FP-C": 59.5,
            "AR": 76.4,
            "LR": 45.7,
            "RR": 63.5
        },
        {
            "Method": [
                "MiniCPM-V-2",
                "https://huggingface.co/openbmb/MiniCPM-V-2"
            ],
            "Parameters": "2.8B",
            "Vision Model": "SigLip-400M",
            "Language Model": "MiniCPM-2.4B",
            "Org": "OpenBMB",
            "Time": "2024/04/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 231,
            "Overall": 69.1,
            "CP": 75.6,
            "FP-S": 72.6,
            "FP-C": 55.5,
            "AR": 79.2,
            "LR": 45.1,
            "RR": 70.1
        },
        {
            "Method": [
                "LLaVA-InternLM-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "7.6B",
            "Language Model": "InternLM-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 70,
            "Overall": 69.0,
            "CP": 79.0,
            "FP-S": 69.3,
            "FP-C": 59.1,
            "AR": 80.6,
            "LR": 42.2,
            "RR": 64.0
        },
        {
            "Method": [
                "StableLLaVA-13B",
                "https://github.com/icoz69/StableLLAVA"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Tencent",
            "Time": "2023/12/22",
            "OpenSource": "Yes",
            "Verified": "No",
            "key": 55,
            "Overall": 68.9,
            "CP": 80.9,
            "FP-S": 76.1,
            "FP-C": 57.9,
            "AR": 76.0,
            "LR": 39.3,
            "RR": 55.9
        },
        {
            "Method": [
                "LLaVA-v1.5-13B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 72,
            "Overall": 68.8,
            "CP": 79.2,
            "FP-S": 71.1,
            "FP-C": 59.9,
            "AR": 76.0,
            "LR": 44.5,
            "RR": 62.1
        },
        {
            "Method": [
                "CodeFuse-VLM",
                "https://huggingface.co/codefuse-ai/CodeFuse-VLM-14B"
            ],
            "Parameters": "14B",
            "Language Model": "Qwen-14B",
            "Vision Model": "Qwen-VL Vision Encoder",
            "Org": "Ant Group",
            "Time": "2024/01/29",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 129,
            "Overall": 68.7,
            "CP": 77.3,
            "FP-S": 73.6,
            "FP-C": 54.3,
            "AR": 79.2,
            "LR": 44.5,
            "RR": 63.0
        },
        {
            "Method": [
                "Yi-VL-6B",
                "https://huggingface.co/01-ai/Yi-VL-6B"
            ],
            "Parameters": "6.6B",
            "Language Model": "Yi-6B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "01-AI",
            "Time": "2024/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 189,
            "Overall": 68.4,
            "CP": 78.8,
            "FP-S": 73.9,
            "FP-C": 56.7,
            "AR": 75.7,
            "LR": 45.1,
            "RR": 58.3
        },
        {
            "Method": [
                "Claude3-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 218,
            "Overall": 67.8,
            "CP": 74.1,
            "FP-S": 67.3,
            "FP-C": 60.7,
            "AR": 75.7,
            "LR": 58.4,
            "RR": 59.7
        },
        {
            "Method": [
                "LLaVA-v1.5-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 71,
            "Overall": 67.7,
            "CP": 77.7,
            "FP-S": 70.1,
            "FP-C": 59.5,
            "AR": 78.5,
            "LR": 39.3,
            "RR": 59.2
        },
        {
            "Method": [
                "Kanva-7B",
                "https://github.com/llp1992/Kanva"
            ],
            "Parameters": "7.2B",
            "Language Model": "Baichuan2-7B",
            "Vision Model": "EVA-CLIP-L/336",
            "Org": "KaLM",
            "Time": "2023/11/21",
            "Verified": "No",
            "OpenSource": "No",
            "key": 37,
            "Overall": 67.7,
            "CP": 78.4,
            "FP-S": 72.6,
            "FP-C": 59.1,
            "AR": 74.3,
            "LR": 36.4,
            "RR": 61.1
        },
        {
            "Method": [
                "ShareGPT4V-7B",
                "https://sharegpt4v.github.io"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 184,
            "Overall": 67.6,
            "CP": 78.6,
            "FP-S": 70.4,
            "FP-C": 60.3,
            "AR": 72.9,
            "LR": 41.0,
            "RR": 61.1
        },
        {
            "Method": [
                "Sphinx",
                "https://github.com/Alpha-VLLM/LLaMA2-Accessory/tree/main/SPHINX"
            ],
            "Parameters": "16.5B",
            "Language Model": "LLaMA2 13B",
            "Vision Model": "CLIP ViT-L/14\nCLIP ConvNeXT\nConvNeXT-XXLarge\nDinov2-VIT-G/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/10/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 33,
            "Overall": 67.5,
            "CP": 79.2,
            "FP-S": 72.1,
            "FP-C": 63.2,
            "AR": 73.6,
            "LR": 32.9,
            "RR": 57.8
        },
        {
            "Method": [
                "Qwen-VL-Plus",
                "https://github.com/QwenLM/Qwen-VL?tab=readme-ov-file#qwen-vl-plus"
            ],
            "Parameters": "",
            "Language Model": "QwenLM",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/01/10",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 77,
            "Overall": 67.0,
            "CP": 71.1,
            "FP-S": 80.2,
            "FP-C": 45.3,
            "AR": 71.2,
            "LR": 50.3,
            "RR": 66.8
        },
        {
            "Method": [
                "ShareCaptioner",
                "https://huggingface.co/Lin-Chen/ShareCaptioner/"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM-7B",
            "Vision Model": "EVA-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 245,
            "Overall": 66.5,
            "CP": 64.9,
            "FP-S": 77.9,
            "FP-C": 62.3,
            "AR": 71.2,
            "LR": 41.6,
            "RR": 67.3
        },
        {
            "Method": [
                "SharedCaptioner",
                "https://huggingface.co/Lin-Chen/ShareCaptioner/"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM-7B",
            "Vision Model": "EVA-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/03",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 74,
            "Overall": 66.5,
            "CP": 64.9,
            "FP-S": 77.9,
            "FP-C": 62.3,
            "AR": 71.2,
            "LR": 41.6,
            "RR": 67.3
        },
        {
            "Method": [
                "RekaEdge",
                "https://www.reka.ai"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Reka AI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 271,
            "Overall": 66.4,
            "CP": 77.5,
            "FP-S": 68.8,
            "FP-C": 49.0,
            "AR": 77.4,
            "LR": 35.3,
            "RR": 68.2
        },
        {
            "Method": [
                "DeepSeek-VL-1.3B",
                "https://github.com/deepseek-ai/DeepSeek-VL"
            ],
            "Parameters": "2.0B",
            "Language Model": "DeekSeek-1B",
            "Vision Model": "SAM-B\nSigLIP-L",
            "Org": "DeepSeek",
            "Time": "2024/03/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 201,
            "Overall": 66.4,
            "CP": 78.4,
            "FP-S": 69.6,
            "FP-C": 56.7,
            "AR": 77.8,
            "LR": 34.7,
            "RR": 55.5
        },
        {
            "Method": [
                "mPLUG-Owl2",
                "https://github.com/X-PLUG/mPLUG-Owl/tree/main/mPLUG-Owl2"
            ],
            "Parameters": "8.2B",
            "Language Model": "LLaMA2 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "DAMO Academy",
            "Time": "2023/11/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 32,
            "Overall": 66.0,
            "CP": 73.0,
            "FP-S": 68.6,
            "FP-C": 55.9,
            "AR": 76.0,
            "LR": 43.4,
            "RR": 62.1
        },
        {
            "Method": [
                "CogVLM-17B-Chat",
                "https://huggingface.co/THUDM/cogvlm-chat-hf"
            ],
            "Parameters": "17B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "EVA2-CLIP-E",
            "Org": "Zhipu AI",
            "Time": "2024/01/03",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 75,
            "Overall": 65.8,
            "CP": 80.1,
            "FP-S": 65.3,
            "FP-C": 53.0,
            "AR": 70.5,
            "LR": 35.8,
            "RR": 67.8
        },
        {
            "Method": [
                "LLaVA-InternLM2-1.8B",
                "https://huggingface.co/StarCycle/llava-siglip-internlm2-1_8b-v1"
            ],
            "Parameters": "2.2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "SigLIP-400M",
            "Org": "Exponential Deep Space",
            "Time": "2024/03/10",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 167,
            "Overall": 65.7,
            "CP": 74.5,
            "FP-S": 65.8,
            "FP-C": 56.7,
            "AR": 75.0,
            "LR": 40.5,
            "RR": 64.5
        },
        {
            "Method": [
                "GPT-4v (1106, detail-high)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/04/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 243,
            "Overall": 65.4,
            "CP": 71.9,
            "FP-S": 63.8,
            "FP-C": 55.5,
            "AR": 77.1,
            "LR": 58.4,
            "RR": 55.5
        },
        {
            "key": 14,
            "Method": [
                "MMICL",
                "https://huggingface.co/BleachNick/MMICL-Instructblip-T5-xxl"
            ],
            "Parameters": "12.3B",
            "Overall": "65.2",
            "LR": "44.3",
            "AR": "77.9",
            "RR": "64.8",
            "FP-S": "66.5",
            "FP-C": "53.6",
            "CP": "70.6",
            "Language Model": "FLANT5-XXL",
            "Vision Model": "EVA-G",
            "Org": "Peking University",
            "Time": "2023/8/18",
            "Verified": "No",
            "OpenSource": "Yes"
        },
        {
            "Method": [
                "MiniCPM-V",
                "https://huggingface.co/openbmb/MiniCPM-V"
            ],
            "Parameters": "3B",
            "Language Model": "MiniCPM-2.4B",
            "Vision Model": "SigLip-400M",
            "Org": "OpenBMB",
            "Time": "2024/02/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 146,
            "Overall": 64.1,
            "CP": 71.3,
            "FP-S": 69.8,
            "FP-C": 50.2,
            "AR": 72.2,
            "LR": 36.4,
            "RR": 65.4
        },
        {
            "Method": [
                "LLaVA-DINOv2",
                "https://huggingface.co/StarCycle/llava-dinov2-internlm2-7b-v1"
            ],
            "Parameters": "8.1B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "DINOv2 ViT-L/13",
            "Org": "Exponential Deep Space",
            "Time": "2024/02/13",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 152,
            "Overall": 64.0,
            "CP": 76.0,
            "FP-S": 54.5,
            "FP-C": 61.5,
            "AR": 78.1,
            "LR": 38.2,
            "RR": 59.7
        },
        {
            "Method": [
                "Emu2_chat",
                "https://github.com/baaivision/Emu/tree/main/Emu2"
            ],
            "Parameters": "37B",
            "Language Model": "LLaMA-33B",
            "Vision Model": "EVA-02-CLIP-E-plus",
            "Org": "Beijing Academy of Artificial Intelligence",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 86,
            "Overall": 63.6,
            "CP": 72.8,
            "FP-S": 67.8,
            "FP-C": 57.1,
            "AR": 72.9,
            "LR": 27.2,
            "RR": 60.2
        },
        {
            "Method": [
                "Claude3-Opus",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 219,
            "Overall": 63.3,
            "CP": 74.1,
            "FP-S": 60.1,
            "FP-C": 52.2,
            "AR": 74.7,
            "LR": 57.8,
            "RR": 47.4
        },
        {
            "Method": [
                "LMEye",
                "https://arxiv.org/pdf/2305.03701.pdf"
            ],
            "Parameters": "4.4B",
            "Language Model": "FLANT5-XL",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Harbin Institute of Technology",
            "Time": "2023/10/16",
            "key": 29,
            "Overall": 62.6,
            "CP": 69.2,
            "FP-S": 61.6,
            "FP-C": 58.7,
            "AR": 74.3,
            "LR": 41.0,
            "RR": 55.9,
            "Verified": "No",
            "OpenSource": "Yes"
        },
        {
            "key": 24,
            "Method": [
                "Qwen-VL-Chat",
                "https://github.com/QwenLM/Qwen-VL"
            ],
            "Parameters": "9.6B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-G/16",
            "Org": "Alibaba",
            "Time": "2023/8/24",
            "Overall": 61.8,
            "CP": 72.8,
            "FP-S": 66.3,
            "FP-C": 46.2,
            "AR": 74.3,
            "LR": 40.5,
            "RR": 47.9,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "key": 16,
            "Method": [
                "JiuTian-Tiny",
                "https://github.com/rshaojimmy/JiuTian"
            ],
            "Parameters": "4.1B",
            "Overall": "61.7",
            "LR": "38.1",
            "AR": "76.1",
            "RR": "56.3",
            "FP-S": "62.5",
            "FP-C": "52.0",
            "CP": "68.7",
            "Language Model": "FLANT5-XL",
            "Vision Model": "EVA-G",
            "Org": "HIT-Ruoyu",
            "Time": "2023/8/9",
            "Verified": "No",
            "OpenSource": "No"
        },
        {
            "Method": [
                "Claude3-Haiku",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 217,
            "Overall": 60.7,
            "CP": 69.8,
            "FP-S": 58.8,
            "FP-C": 44.9,
            "AR": 74.7,
            "LR": 53.2,
            "RR": 49.8
        },
        {
            "key": 15,
            "Method": [
                "Shikra",
                "https://arxiv.org/abs/2306.15195"
            ],
            "Parameters": "7.2B",
            "Overall": "60.2",
            "LR": "33.5",
            "AR": "69.6",
            "RR": "53.1",
            "FP-S": "61.8",
            "FP-C": "50.4",
            "CP": "71.7",
            "Language Model": "Vicuna 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Sensetime Research",
            "Time": "2023/7/3",
            "Verified": "No",
            "OpenSource": "Yes"
        },
        {
            "Method": [
                "Monkey",
                "https://github.com/Yuliang-Liu/Monkey"
            ],
            "Parameters": "9.8B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-BigHuge",
            "Org": "Huazhong University of Science and Technology",
            "Time": "2024/01/11",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 79,
            "Overall": 59.6,
            "CP": 69.8,
            "FP-S": 63.3,
            "FP-C": 44.5,
            "AR": 74.7,
            "LR": 32.4,
            "RR": 49.8
        },
        {
            "Method": [
                "MMAlaya",
                "https://huggingface.co/DataCanvas/MMAlaya"
            ],
            "Parameters": "7.8B",
            "Language Model": "Alaya-7B-Chat",
            "Vision Model": "EVA-G",
            "Org": "DataCanvas",
            "Time": "2024/01/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 134,
            "Overall": 58.7,
            "CP": 69.8,
            "FP-S": 56.0,
            "FP-C": 51.8,
            "AR": 70.5,
            "LR": 32.9,
            "RR": 52.1
        },
        {
            "key": 19,
            "Method": [
                "IDEFICS-80B-Instruct",
                "https://huggingface.co/HuggingFaceM4/idefics-80b-instruct"
            ],
            "Language Model": "LLaMA65B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "Hugging Face",
            "Time": "2023/7/25",
            "Overall": 54.6,
            "AR": 67.8,
            "CP": 61.9,
            "FP-C": 48.0,
            "FP-S": 56.0,
            "LR": 29.0,
            "RR": 46.5,
            "Parameters": "80B",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "key": 6,
            "Method": [
                "Otter-I",
                "https://arxiv.org/abs/2305.03726"
            ],
            "Parameters": "9B",
            "Overall": "48.3",
            "LR": "22.2",
            "AR": "63.3",
            "RR": "39.4",
            "FP-S": "46.8",
            "FP-C": "36.4",
            "CP": "60.6",
            "Language Model": "LLaMA 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Nanyang Technological University",
            "Time": "2023/6/8",
            "Verified": "No",
            "OpenSource": "Yes"
        },
        {
            "key": 18,
            "Method": [
                "IDEFICS-9B-Instruct",
                "https://huggingface.co/HuggingFaceM4/idefics-9b-instruct"
            ],
            "Language Model": "LLaMA 7B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "Hugging Face",
            "Time": "2023/7/25",
            "Overall": "45.3",
            "AR": "64.7",
            "CP": "56.2",
            "FP-C": "36.4",
            "FP-S": "43.3",
            "LR": "21.0",
            "RR": "29.1",
            "Parameters": "9B",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Method": [
                "LLaVA-v1-7B",
                "https://arxiv.org/abs/2304.08485"
            ],
            "Parameters": "7.2B",
            "Language Model": "LLaMA 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin-Madison",
            "Time": "2023/4/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 187,
            "Overall": 43.8,
            "CP": 61.7,
            "FP-S": 39.4,
            "FP-C": 29.1,
            "AR": 58.0,
            "LR": 23.7,
            "RR": 27.0
        },
        {
            "Method": [
                "PandaGPT-13B",
                "https://arxiv.org/abs/2305.16355"
            ],
            "Parameters": "14B",
            "Language Model": "Vicuna 13B",
            "Vision Model": "ImageBind ViT-H/14",
            "Org": "Tencent AI Lab",
            "Time": "2023/5/25",
            "Overall": 42.5,
            "CP": 57.6,
            "FP-S": 32.7,
            "FP-C": 28.7,
            "AR": 61.5,
            "LR": 23.1,
            "RR": 34.1,
            "key": 25,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "key": 10,
            "Method": [
                "G2PT",
                ""
            ],
            "Parameters": "7B",
            "Overall": "39.8",
            "LR": "14.8",
            "AR": "46.7",
            "RR": "31.5",
            "FP-S": "41.8",
            "FP-C": "34.4",
            "CP": "49.8",
            "Language Model": "LLaMA 7B",
            "Vision Model": "ViT-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "",
            "Verified": "No",
            "OpenSource": "No"
        },
        {
            "key": 9,
            "Method": [
                "LLaMA-Adapter-v2",
                "https://arxiv.org/abs/2304.15010"
            ],
            "Parameters": "7.2B",
            "Overall": "38.9",
            "LR": "7.4",
            "AR": "45.3",
            "RR": "19.2",
            "FP-S": "45.0",
            "FP-C": "32.0",
            "CP": "54.0",
            "Language Model": "LLaMA 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/4/28",
            "Verified": "No",
            "OpenSource": "Yes"
        },
        {
            "Method": [
                "VisualGLM",
                "https://github.com/THUDM/VisualGLM-6B"
            ],
            "Parameters": "8B",
            "Language Model": "ChatGLM 6B",
            "Vision Model": "EVA-CLIP",
            "Org": "Tsinghua University",
            "Time": "2023/5/17",
            "key": 41,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Overall": 37.6,
            "CP": 47.3,
            "FP-S": 37.9,
            "FP-C": 25.5,
            "AR": 47.6,
            "LR": 22.0,
            "RR": 28.4
        },
        {
            "key": 7,
            "Method": [
                "InstructBLIP-7B",
                "https://arxiv.org/abs/2305.06500"
            ],
            "Parameters": "8B",
            "Overall": "33.9",
            "LR": "21.6",
            "AR": "47.4",
            "RR": "22.5",
            "FP-S": "33.0",
            "FP-C": "24.4",
            "CP": "41.1",
            "Language Model": "Vicuna 7B",
            "Vision Model": "EVA-G",
            "Org": "Salesforce Research",
            "Time": "2023/5/11",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "key": 23,
            "Method": [
                "Qwen-VL",
                "https://github.com/QwenLM/Qwen-VL"
            ],
            "Parameters": "9.6B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-G/16",
            "Org": "Alibaba",
            "Time": "2023/8/24",
            "Overall": 32.2,
            "AR": 43.1,
            "CP": 36.4,
            "FP-C": 27.9,
            "FP-S": 32.9,
            "LR": 9.8,
            "RR": 30.3,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "key": 17,
            "Method": [
                "LAMM",
                "https://arxiv.org/abs/2306.06687"
            ],
            "Language Model": "LLaMA 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Overall": "29.6",
            "AR": "45.0",
            "CP": "33.0",
            "FP-C": "26.0",
            "FP-S": "23.0",
            "LR": "25.6",
            "RR": "21.6",
            "Parameters": "7.2B",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/8/31",
            "Verified": "No",
            "OpenSource": "Yes"
        },
        {
            "key": 3,
            "Method": [
                "MiniGPT-4-v1-7B",
                "https://arxiv.org/abs/2304.10592"
            ],
            "Parameters": "8B",
            "Overall": "23.0",
            "LR": "13.6",
            "AR": "32.9",
            "RR": "8.9",
            "FP-S": "28.8",
            "FP-C": "11.2",
            "CP": "28.3",
            "Language Model": "Vicuna 7B",
            "Vision Model": "EVA-G",
            "Org": "King Abdullah University of Science and Technology",
            "Time": "2023/4/20",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "key": 2,
            "Method": [
                "MMGPT",
                "https://arxiv.org/abs/2305.04790"
            ],
            "Parameters": "9B",
            "Overall": "16.0",
            "LR": "1.1",
            "AR": "23.8",
            "RR": "20.7",
            "FP-S": "18.3",
            "FP-C": "5.2",
            "CP": "18.3",
            "Language Model": "LLaMA 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/5/8",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Method": [
                "MiniGPT-4-v2",
                "https://minigpt-v2.github.io"
            ],
            "Parameters": "8B",
            "Language Model": "LLaMA2 13B",
            "Vision Model": "EVA-G",
            "Org": "King Abdullah University of Science and Technology",
            "Time": "2023/10/27",
            "key": 31,
            "Overall": 9.4,
            "CP": 10.1,
            "FP-S": 9.5,
            "FP-C": 2.0,
            "AR": 20.8,
            "LR": 6.4,
            "RR": 3.3,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "key": 1,
            "Method": [
                "OpenFlamingo v2",
                "https://github.com/mlfoundations/open_flamingo"
            ],
            "Parameters": "9B",
            "Overall": "5.7",
            "LR": "11.4",
            "AR": "12.8",
            "RR": "1.4",
            "FP-S": "5.5",
            "FP-C": "0.8",
            "CP": "4.0",
            "Language Model": "MPT 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "The University of Washington",
            "Time": "2023/6/28",
            "Verified": "No",
            "OpenSource": "Yes"
        },
        {
            "key": 0,
            "Method": [
                "OpenFlamingo",
                "https://github.com/mlfoundations/open_flamingo"
            ],
            "Parameters": "9B",
            "Overall": "4.3",
            "LR": "9.1",
            "AR": "11.4",
            "RR": "3.3",
            "FP-S": "2.5",
            "FP-C": "1.6",
            "CP": "1.5",
            "Language Model": "LLaMA 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "The University of Washington",
            "Time": "2023/3/29",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 70.7,
            "AR": 76.4,
            "CP": 81.4,
            "FP-C": 59.5,
            "FP-S": 74.6,
            "LR": 50.9,
            "RR": 61.6,
            "action_recognition": 94.3,
            "attribute_comparison": 51.3,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 71.2,
            "function_reasoning": 79.2,
            "future_prediction": 62.5,
            "identity_reasoning": 95.1,
            "image_emotion": 74.7,
            "image_quality": 63.5,
            "image_scene": 92.2,
            "image_style": 72.9,
            "image_topic": 97.6,
            "nature_relation": 50.6,
            "object_localization": 48.1,
            "ocr": 92.2,
            "physical_property_reasoning": 58.0,
            "physical_relation": 51.9,
            "social_relation": 79.5,
            "spatial_relationship": 29.6,
            "structuralized_imagetext_understanding": 42.6,
            "Method": [
                "Mini-InternVL-Chat-2B-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 277
        },
        {
            "Overall": 75.7,
            "AR": 78.5,
            "CP": 78.8,
            "FP-C": 70.0,
            "FP-S": 80.4,
            "LR": 64.7,
            "RR": 72.0,
            "action_recognition": 93.2,
            "attribute_comparison": 74.4,
            "attribute_recognition": 94.9,
            "celebrity_recognition": 70.3,
            "function_reasoning": 85.8,
            "future_prediction": 69.4,
            "identity_reasoning": 96.3,
            "image_emotion": 65.1,
            "image_quality": 67.1,
            "image_scene": 89.1,
            "image_style": 71.8,
            "image_topic": 95.3,
            "nature_relation": 67.9,
            "object_localization": 67.3,
            "ocr": 94.8,
            "physical_property_reasoning": 56.0,
            "physical_relation": 61.5,
            "social_relation": 83.3,
            "spatial_relationship": 40.7,
            "structuralized_imagetext_understanding": 61.4,
            "Method": [
                "Mini-InternVL-Chat-4B-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 278
        },
        {
            "Overall": 73.9,
            "AR": 72.6,
            "CP": 77.1,
            "FP-C": 69.2,
            "FP-S": 79.9,
            "LR": 64.2,
            "RR": 71.1,
            "action_recognition": 89.8,
            "attribute_comparison": 78.2,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 75.4,
            "function_reasoning": 80.2,
            "future_prediction": 55.6,
            "identity_reasoning": 93.9,
            "image_emotion": 69.9,
            "image_quality": 75.3,
            "image_scene": 86.8,
            "image_style": 62.4,
            "image_topic": 85.9,
            "nature_relation": 79.0,
            "object_localization": 67.3,
            "ocr": 87.0,
            "physical_property_reasoning": 47.0,
            "physical_relation": 42.3,
            "social_relation": 82.1,
            "spatial_relationship": 38.3,
            "structuralized_imagetext_understanding": 70.3,
            "Method": [
                "Gemini-1.5-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 279
        },
        {
            "Overall": 77.3,
            "AR": 84.0,
            "CP": 83.5,
            "FP-C": 65.2,
            "FP-S": 80.7,
            "LR": 56.1,
            "RR": 79.6,
            "action_recognition": 95.5,
            "attribute_comparison": 64.1,
            "attribute_recognition": 86.9,
            "celebrity_recognition": 83.9,
            "function_reasoning": 86.8,
            "future_prediction": 69.4,
            "identity_reasoning": 98.8,
            "image_emotion": 75.9,
            "image_quality": 75.3,
            "image_scene": 91.5,
            "image_style": 75.3,
            "image_topic": 95.3,
            "nature_relation": 84.0,
            "object_localization": 61.5,
            "ocr": 93.5,
            "physical_property_reasoning": 69.0,
            "physical_relation": 55.8,
            "social_relation": 91.0,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 46.5,
            "Method": [
                "Bumblebee-7B-v1.5",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLip-400M",
            "Org": "Monolith Foundation",
            "Time": "2024/06/12",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 280
        },
        {
            "Overall": 71.4,
            "AR": 76.0,
            "CP": 71.7,
            "FP-C": 64.0,
            "FP-S": 82.2,
            "LR": 60.1,
            "RR": 61.6,
            "action_recognition": 87.5,
            "attribute_comparison": 64.1,
            "attribute_recognition": 87.9,
            "celebrity_recognition": 89.0,
            "function_reasoning": 77.4,
            "future_prediction": 58.3,
            "identity_reasoning": 89.0,
            "image_emotion": 62.7,
            "image_quality": 63.5,
            "image_scene": 76.7,
            "image_style": 63.5,
            "image_topic": 89.4,
            "nature_relation": 66.7,
            "object_localization": 64.4,
            "ocr": 88.3,
            "physical_property_reasoning": 64.0,
            "physical_relation": 61.5,
            "social_relation": 56.4,
            "spatial_relationship": 38.3,
            "structuralized_imagetext_understanding": 61.4,
            "Method": [
                "GLM-4v-9B",
                "https://huggingface.co/THUDM/glm-4v-9b"
            ],
            "Parameters": "9B",
            "Language Model": "GLM-4-9B",
            "Vision Model": "EVA-02-5B",
            "Org": "Zhipu AI",
            "Time": "2024/06/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 281
        },
        {
            "Overall": 73.8,
            "AR": 79.5,
            "CP": 82.4,
            "FP-C": 67.2,
            "FP-S": 77.1,
            "LR": 48.6,
            "RR": 68.7,
            "action_recognition": 93.2,
            "attribute_comparison": 67.9,
            "attribute_recognition": 85.9,
            "celebrity_recognition": 76.3,
            "function_reasoning": 84.0,
            "future_prediction": 69.4,
            "identity_reasoning": 96.3,
            "image_emotion": 78.3,
            "image_quality": 67.1,
            "image_scene": 95.3,
            "image_style": 68.2,
            "image_topic": 96.5,
            "nature_relation": 72.8,
            "object_localization": 59.6,
            "ocr": 90.9,
            "physical_property_reasoning": 61.0,
            "physical_relation": 48.1,
            "social_relation": 78.2,
            "spatial_relationship": 38.3,
            "structuralized_imagetext_understanding": 33.7,
            "Method": [
                "LLaVA-InternLM2-7B (QMoSLoRA)",
                "https://arxiv.org/abs/2406.11909"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "HKU",
            "Time": "2024/06/23",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 283
        },
        {
            "Overall": 79.7,
            "AR": 78.5,
            "CP": 83.5,
            "FP-C": 77.3,
            "FP-S": 83.2,
            "LR": 73.4,
            "RR": 73.9,
            "action_recognition": 87.5,
            "attribute_comparison": 78.2,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 78.8,
            "function_reasoning": 85.8,
            "future_prediction": 63.9,
            "identity_reasoning": 95.1,
            "image_emotion": 63.9,
            "image_quality": 80.0,
            "image_scene": 91.5,
            "image_style": 81.2,
            "image_topic": 96.5,
            "nature_relation": 84.0,
            "object_localization": 71.2,
            "ocr": 96.1,
            "physical_property_reasoning": 57.0,
            "physical_relation": 42.3,
            "social_relation": 84.6,
            "spatial_relationship": 65.4,
            "structuralized_imagetext_understanding": 80.2,
            "Method": [
                "Claude3.5-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/06/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 284
        },
        {
            "Overall": 82.8,
            "AR": 86.5,
            "CP": 87.2,
            "FP-C": 75.7,
            "FP-S": 88.4,
            "LR": 67.1,
            "RR": 78.7,
            "action_recognition": 95.5,
            "attribute_comparison": 80.8,
            "attribute_recognition": 97.0,
            "celebrity_recognition": 85.6,
            "function_reasoning": 90.6,
            "future_prediction": 75.0,
            "identity_reasoning": 97.6,
            "image_emotion": 75.9,
            "image_quality": 82.4,
            "image_scene": 95.3,
            "image_style": 80.0,
            "image_topic": 97.6,
            "nature_relation": 81.5,
            "object_localization": 78.8,
            "ocr": 94.8,
            "physical_property_reasoning": 73.0,
            "physical_relation": 69.2,
            "social_relation": 82.1,
            "spatial_relationship": 49.4,
            "structuralized_imagetext_understanding": 61.4,
            "Method": [
                "CongRong",
                "https://mllm.cloudwalk.com/web/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "CloudWalk",
            "Time": "2024/06/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 285
        },
        {
            "Overall": 77.1,
            "AR": 81.9,
            "CP": 85.4,
            "FP-C": 66.0,
            "FP-S": 80.9,
            "LR": 59.0,
            "RR": 73.0,
            "action_recognition": 96.6,
            "attribute_comparison": 66.7,
            "attribute_recognition": 85.9,
            "celebrity_recognition": 82.2,
            "function_reasoning": 87.7,
            "future_prediction": 73.6,
            "identity_reasoning": 97.6,
            "image_emotion": 79.5,
            "image_quality": 78.8,
            "image_scene": 93.0,
            "image_style": 76.5,
            "image_topic": 95.3,
            "nature_relation": 81.5,
            "object_localization": 63.5,
            "ocr": 96.1,
            "physical_property_reasoning": 63.0,
            "physical_relation": 53.8,
            "social_relation": 76.9,
            "spatial_relationship": 32.1,
            "structuralized_imagetext_understanding": 48.5,
            "Method": [
                "Bumblebee-7B-v1.6",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Monolith Foundation",
            "Time": "2024/06/27",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 286
        },
        {
            "Overall": 75.8,
            "AR": 81.6,
            "CP": 85.2,
            "FP-C": 67.2,
            "FP-S": 80.2,
            "LR": 47.4,
            "RR": 72.5,
            "action_recognition": 95.5,
            "attribute_comparison": 65.4,
            "attribute_recognition": 85.9,
            "celebrity_recognition": 81.4,
            "function_reasoning": 86.8,
            "future_prediction": 68.1,
            "identity_reasoning": 97.6,
            "image_emotion": 77.1,
            "image_quality": 80.0,
            "image_scene": 95.3,
            "image_style": 74.1,
            "image_topic": 94.1,
            "nature_relation": 67.9,
            "object_localization": 66.3,
            "ocr": 89.6,
            "physical_property_reasoning": 63.0,
            "physical_relation": 48.1,
            "social_relation": 93.6,
            "spatial_relationship": 38.3,
            "structuralized_imagetext_understanding": 32.7,
            "Method": [
                "Llama-3-MixSense",
                "https://huggingface.co/Zero-Vision/Llama-3-MixSense"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "ZeroVision",
            "Time": "2024/07/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 288
        },
        {
            "Overall": 87.7,
            "AR": 88.5,
            "CP": 88.9,
            "FP-C": 85.0,
            "FP-S": 91.5,
            "LR": 78.0,
            "RR": 88.2,
            "action_recognition": 96.6,
            "attribute_comparison": 82.1,
            "attribute_recognition": 97.0,
            "celebrity_recognition": 91.5,
            "function_reasoning": 90.6,
            "future_prediction": 77.8,
            "identity_reasoning": 98.8,
            "image_emotion": 75.9,
            "image_quality": 81.2,
            "image_scene": 95.3,
            "image_style": 90.6,
            "image_topic": 97.6,
            "nature_relation": 92.6,
            "object_localization": 80.8,
            "ocr": 98.7,
            "physical_property_reasoning": 78.0,
            "physical_relation": 80.8,
            "social_relation": 88.5,
            "spatial_relationship": 75.3,
            "structuralized_imagetext_understanding": 78.2,
            "Method": [
                "InternVL-2.0-Pro",
                "https://huggingface.co/spaces/OpenGVLab/InternVL/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/08",
            "Verified": "Yes",
            "OpenSource": "No",
            "key": 290
        },
        {
            "Overall": 65.2,
            "AR": 77.8,
            "CP": 75.2,
            "FP-C": 49.0,
            "FP-S": 70.6,
            "LR": 37.6,
            "RR": 57.8,
            "action_recognition": 92.0,
            "attribute_comparison": 26.9,
            "attribute_recognition": 86.9,
            "celebrity_recognition": 64.4,
            "function_reasoning": 74.5,
            "future_prediction": 51.4,
            "identity_reasoning": 93.9,
            "image_emotion": 59.0,
            "image_quality": 56.5,
            "image_scene": 86.8,
            "image_style": 70.6,
            "image_topic": 96.5,
            "nature_relation": 48.1,
            "object_localization": 48.1,
            "ocr": 89.6,
            "physical_property_reasoning": 68.0,
            "physical_relation": 53.8,
            "social_relation": 70.5,
            "spatial_relationship": 23.5,
            "structuralized_imagetext_understanding": 27.7,
            "Method": [
                "InternVL2-1B",
                "https://huggingface.co/OpenGVLab/InternVL2-1B"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 292
        },
        {
            "Overall": 73.4,
            "AR": 81.2,
            "CP": 80.9,
            "FP-C": 61.1,
            "FP-S": 76.9,
            "LR": 53.2,
            "RR": 70.1,
            "action_recognition": 95.5,
            "attribute_comparison": 51.3,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 72.0,
            "function_reasoning": 81.1,
            "future_prediction": 56.9,
            "identity_reasoning": 97.6,
            "image_emotion": 71.1,
            "image_quality": 65.9,
            "image_scene": 91.5,
            "image_style": 72.9,
            "image_topic": 97.6,
            "nature_relation": 69.1,
            "object_localization": 57.7,
            "ocr": 89.6,
            "physical_property_reasoning": 68.0,
            "physical_relation": 57.7,
            "social_relation": 79.5,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 50.5,
            "Method": [
                "InternVL2-2B",
                "https://huggingface.co/OpenGVLab/InternVL2-2B"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 293
        },
        {
            "Overall": 78.5,
            "AR": 81.9,
            "CP": 84.6,
            "FP-C": 69.6,
            "FP-S": 82.7,
            "LR": 61.3,
            "RR": 76.8,
            "action_recognition": 94.3,
            "attribute_comparison": 71.8,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 77.1,
            "function_reasoning": 85.8,
            "future_prediction": 58.3,
            "identity_reasoning": 96.3,
            "image_emotion": 75.9,
            "image_quality": 72.9,
            "image_scene": 91.5,
            "image_style": 81.2,
            "image_topic": 97.6,
            "nature_relation": 80.2,
            "object_localization": 69.2,
            "ocr": 94.8,
            "physical_property_reasoning": 66.0,
            "physical_relation": 55.8,
            "social_relation": 87.2,
            "spatial_relationship": 40.7,
            "structuralized_imagetext_understanding": 63.4,
            "Method": [
                "InternVL2-4B",
                "https://huggingface.co/OpenGVLab/InternVL2-4B"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 294
        },
        {
            "Overall": 82.0,
            "AR": 81.9,
            "CP": 85.7,
            "FP-C": 74.9,
            "FP-S": 86.2,
            "LR": 71.7,
            "RR": 82.5,
            "action_recognition": 95.5,
            "attribute_comparison": 76.9,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 81.4,
            "function_reasoning": 87.7,
            "future_prediction": 70.8,
            "identity_reasoning": 96.3,
            "image_emotion": 74.7,
            "image_quality": 76.5,
            "image_scene": 94.6,
            "image_style": 80.0,
            "image_topic": 97.6,
            "nature_relation": 85.2,
            "object_localization": 75.0,
            "ocr": 96.1,
            "physical_property_reasoning": 64.0,
            "physical_relation": 69.2,
            "social_relation": 88.5,
            "spatial_relationship": 50.6,
            "structuralized_imagetext_understanding": 72.3,
            "Method": [
                "InternVL2-8B",
                "https://huggingface.co/OpenGVLab/InternVL2-8B"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 295
        },
        {
            "Overall": 83.4,
            "AR": 87.8,
            "CP": 86.5,
            "FP-C": 74.9,
            "FP-S": 86.9,
            "LR": 71.7,
            "RR": 82.9,
            "action_recognition": 94.3,
            "attribute_comparison": 82.1,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 84.7,
            "function_reasoning": 90.6,
            "future_prediction": 76.4,
            "identity_reasoning": 98.8,
            "image_emotion": 73.5,
            "image_quality": 81.2,
            "image_scene": 93.8,
            "image_style": 82.4,
            "image_topic": 97.6,
            "nature_relation": 86.4,
            "object_localization": 75.0,
            "ocr": 94.8,
            "physical_property_reasoning": 76.0,
            "physical_relation": 75.0,
            "social_relation": 84.6,
            "spatial_relationship": 46.9,
            "structuralized_imagetext_understanding": 68.3,
            "Method": [
                "InternVL2-26B",
                "https://huggingface.co/OpenGVLab/InternVL2-26B"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 296
        },
        {
            "Overall": 86.8,
            "AR": 86.5,
            "CP": 87.4,
            "FP-C": 80.2,
            "FP-S": 93.0,
            "LR": 78.6,
            "RR": 89.1,
            "action_recognition": 94.3,
            "attribute_comparison": 79.5,
            "attribute_recognition": 97.0,
            "celebrity_recognition": 93.2,
            "function_reasoning": 91.5,
            "future_prediction": 77.8,
            "identity_reasoning": 96.3,
            "image_emotion": 78.3,
            "image_quality": 84.7,
            "image_scene": 90.7,
            "image_style": 83.5,
            "image_topic": 97.6,
            "nature_relation": 95.1,
            "object_localization": 86.5,
            "ocr": 96.1,
            "physical_property_reasoning": 73.0,
            "physical_relation": 75.0,
            "social_relation": 92.3,
            "spatial_relationship": 65.4,
            "structuralized_imagetext_understanding": 79.2,
            "Method": [
                "InternVL2-40B",
                "https://huggingface.co/OpenGVLab/InternVL2-40B"
            ],
            "Parameters": "40B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 297
        },
        {
            "Overall": 74.6,
            "AR": 77.8,
            "CP": 83.5,
            "FP-C": 68.8,
            "FP-S": 77.6,
            "LR": 52.0,
            "RR": 70.1,
            "action_recognition": 94.3,
            "attribute_comparison": 70.5,
            "attribute_recognition": 88.9,
            "celebrity_recognition": 64.4,
            "function_reasoning": 84.9,
            "future_prediction": 62.5,
            "identity_reasoning": 96.3,
            "image_emotion": 74.7,
            "image_quality": 70.6,
            "image_scene": 92.2,
            "image_style": 77.6,
            "image_topic": 97.6,
            "nature_relation": 76.5,
            "object_localization": 70.2,
            "ocr": 93.5,
            "physical_property_reasoning": 55.0,
            "physical_relation": 50.0,
            "social_relation": 76.9,
            "spatial_relationship": 39.5,
            "structuralized_imagetext_understanding": 44.6,
            "Method": [
                "Cambrian-8B",
                "https://huggingface.co/nyu-visionx/cambrian-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "NYU",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 298
        },
        {
            "Overall": 82.0,
            "AR": 84.0,
            "CP": 85.9,
            "FP-C": 75.3,
            "FP-S": 88.2,
            "LR": 69.4,
            "RR": 77.3,
            "action_recognition": 94.3,
            "attribute_comparison": 84.6,
            "attribute_recognition": 98.0,
            "celebrity_recognition": 84.7,
            "function_reasoning": 84.0,
            "future_prediction": 68.1,
            "identity_reasoning": 97.6,
            "image_emotion": 73.5,
            "image_quality": 84.7,
            "image_scene": 93.8,
            "image_style": 75.3,
            "image_topic": 97.6,
            "nature_relation": 76.5,
            "object_localization": 76.0,
            "ocr": 97.4,
            "physical_property_reasoning": 73.0,
            "physical_relation": 69.2,
            "social_relation": 83.3,
            "spatial_relationship": 45.7,
            "structuralized_imagetext_understanding": 70.3,
            "Method": [
                "InternLM-XComposer2.5",
                "https://huggingface.co/internlm/internlm-xcomposer2d5-7b"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 299
        },
        {
            "Overall": 78.4,
            "AR": 79.9,
            "CP": 86.1,
            "FP-C": 66.0,
            "FP-S": 79.6,
            "LR": 65.9,
            "RR": 82.0,
            "action_recognition": 89.8,
            "attribute_comparison": 73.1,
            "attribute_recognition": 85.9,
            "celebrity_recognition": 77.1,
            "function_reasoning": 91.5,
            "future_prediction": 75.0,
            "identity_reasoning": 97.6,
            "image_emotion": 78.3,
            "image_quality": 75.3,
            "image_scene": 91.5,
            "image_style": 85.9,
            "image_topic": 96.5,
            "nature_relation": 82.7,
            "object_localization": 66.3,
            "ocr": 93.5,
            "physical_property_reasoning": 53.0,
            "physical_relation": 73.1,
            "social_relation": 87.2,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 59.4,
            "Method": [
                "Bumblebee-7B-v2.0",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Monolith Foundation",
            "Time": "2024/07/11",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 300
        },
        {
            "Overall": 79.2,
            "AR": 85.4,
            "CP": 84.6,
            "FP-C": 69.2,
            "FP-S": 81.7,
            "LR": 59.5,
            "RR": 82.0,
            "action_recognition": 92.0,
            "attribute_comparison": 78.2,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 72.9,
            "function_reasoning": 87.7,
            "future_prediction": 75.0,
            "identity_reasoning": 98.8,
            "image_emotion": 79.5,
            "image_quality": 77.6,
            "image_scene": 92.2,
            "image_style": 72.9,
            "image_topic": 96.5,
            "nature_relation": 85.2,
            "object_localization": 72.1,
            "ocr": 93.5,
            "physical_property_reasoning": 72.0,
            "physical_relation": 63.5,
            "social_relation": 91.0,
            "spatial_relationship": 35.8,
            "structuralized_imagetext_understanding": 48.5,
            "Method": [
                "XinYuan-VL",
                "https://cece.com"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Cylingo Group",
            "Time": "2024/07/18",
            "Verified": "No",
            "OpenSource": "No",
            "key": 301
        },
        {
            "Overall": 80.4,
            "AR": 79.9,
            "CP": 83.5,
            "FP-C": 78.5,
            "FP-S": 86.2,
            "LR": 66.5,
            "RR": 76.8,
            "action_recognition": 89.8,
            "attribute_comparison": 83.3,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 85.6,
            "function_reasoning": 87.7,
            "future_prediction": 70.8,
            "identity_reasoning": 97.6,
            "image_emotion": 80.7,
            "image_quality": 69.4,
            "image_scene": 92.2,
            "image_style": 74.1,
            "image_topic": 96.5,
            "nature_relation": 85.2,
            "object_localization": 76.0,
            "ocr": 96.1,
            "physical_property_reasoning": 57.0,
            "physical_relation": 50.0,
            "social_relation": 85.9,
            "spatial_relationship": 61.7,
            "structuralized_imagetext_understanding": 63.4,
            "Method": [
                "Cambrian-34B",
                "https://huggingface.co/nyu-visionx/cambrian-34b"
            ],
            "Parameters": "34B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "NYU",
            "Time": "2024/07/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 302
        },
        {
            "Overall": 78.3,
            "AR": 85.1,
            "CP": 84.8,
            "FP-C": 66.0,
            "FP-S": 83.9,
            "LR": 54.9,
            "RR": 77.3,
            "action_recognition": 92.0,
            "attribute_comparison": 62.8,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 84.7,
            "function_reasoning": 87.7,
            "future_prediction": 72.2,
            "identity_reasoning": 98.8,
            "image_emotion": 73.5,
            "image_quality": 74.1,
            "image_scene": 96.1,
            "image_style": 76.5,
            "image_topic": 97.6,
            "nature_relation": 79.0,
            "object_localization": 70.2,
            "ocr": 92.2,
            "physical_property_reasoning": 71.0,
            "physical_relation": 53.8,
            "social_relation": 91.0,
            "spatial_relationship": 40.7,
            "structuralized_imagetext_understanding": 42.6,
            "Method": [
                "Bunny-Llama3-8B",
                "https://huggingface.co/BAAI/Bunny-v1_1-Llama-3-8B-V"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "BAAI",
            "Time": "2024/07/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 303
        },
        {
            "Overall": 80.8,
            "AR": 79.5,
            "CP": 86.3,
            "FP-C": 77.7,
            "FP-S": 85.2,
            "LR": 65.3,
            "RR": 78.2,
            "action_recognition": 94.3,
            "attribute_comparison": 84.6,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 83.1,
            "function_reasoning": 85.8,
            "future_prediction": 70.8,
            "identity_reasoning": 97.6,
            "image_emotion": 72.3,
            "image_quality": 84.7,
            "image_scene": 94.6,
            "image_style": 81.2,
            "image_topic": 94.1,
            "nature_relation": 74.1,
            "object_localization": 73.1,
            "ocr": 94.8,
            "physical_property_reasoning": 58.0,
            "physical_relation": 69.2,
            "social_relation": 88.5,
            "spatial_relationship": 53.1,
            "structuralized_imagetext_understanding": 61.4,
            "Method": [
                "Ovis1.5-Llama3-8B",
                "https://huggingface.co/AIDC-AI/Ovis1.5-Llama3-8B"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 306
        },
        {
            "Overall": 15.4,
            "AR": 21.2,
            "CP": 22.7,
            "FP-C": 10.9,
            "FP-S": 10.3,
            "LR": 8.1,
            "RR": 12.3,
            "action_recognition": 21.6,
            "attribute_comparison": 2.6,
            "attribute_recognition": 21.2,
            "celebrity_recognition": 10.2,
            "function_reasoning": 11.3,
            "future_prediction": 13.9,
            "identity_reasoning": 29.3,
            "image_emotion": 13.3,
            "image_quality": 2.4,
            "image_scene": 38.0,
            "image_style": 18.8,
            "image_topic": 32.9,
            "nature_relation": 7.4,
            "object_localization": 4.8,
            "ocr": 3.9,
            "physical_property_reasoning": 25.0,
            "physical_relation": 1.9,
            "social_relation": 24.4,
            "spatial_relationship": 7.4,
            "structuralized_imagetext_understanding": 4.0,
            "Method": [
                "Chameleon-7B",
                "https://huggingface.co/facebook/chameleon-7b"
            ],
            "Parameters": "7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 309
        },
        {
            "Overall": 32.5,
            "AR": 44.4,
            "CP": 48.4,
            "FP-C": 19.0,
            "FP-S": 25.9,
            "LR": 12.7,
            "RR": 25.6,
            "action_recognition": 34.1,
            "attribute_comparison": 11.5,
            "attribute_recognition": 50.5,
            "celebrity_recognition": 25.4,
            "function_reasoning": 38.7,
            "future_prediction": 15.3,
            "identity_reasoning": 63.4,
            "image_emotion": 36.1,
            "image_quality": 1.2,
            "image_scene": 65.1,
            "image_style": 45.9,
            "image_topic": 84.7,
            "nature_relation": 19.8,
            "object_localization": 10.6,
            "ocr": 15.6,
            "physical_property_reasoning": 35.0,
            "physical_relation": 5.8,
            "social_relation": 44.9,
            "spatial_relationship": 9.9,
            "structuralized_imagetext_understanding": 10.9,
            "Method": [
                "Chameleon-30B",
                "https://huggingface.co/facebook/chameleon-30b"
            ],
            "Parameters": "30B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 310
        },
        {
            "Overall": 73.2,
            "AR": 77.4,
            "CP": 79.9,
            "FP-C": 67.6,
            "FP-S": 76.4,
            "LR": 51.4,
            "RR": 70.6,
            "action_recognition": 92.0,
            "attribute_comparison": 73.1,
            "attribute_recognition": 83.8,
            "celebrity_recognition": 68.6,
            "function_reasoning": 83.0,
            "future_prediction": 56.9,
            "identity_reasoning": 96.3,
            "image_emotion": 72.3,
            "image_quality": 70.6,
            "image_scene": 91.5,
            "image_style": 62.4,
            "image_topic": 96.5,
            "nature_relation": 82.7,
            "object_localization": 64.4,
            "ocr": 94.8,
            "physical_property_reasoning": 56.0,
            "physical_relation": 46.2,
            "social_relation": 74.4,
            "spatial_relationship": 35.8,
            "structuralized_imagetext_understanding": 47.5,
            "Method": [
                "Cambrian-13B",
                "https://huggingface.co/nyu-visionx/cambrian-13b"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "NYU",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 311
        },
        {
            "Overall": 78.1,
            "AR": 80.9,
            "CP": 81.6,
            "FP-C": 72.1,
            "FP-S": 83.2,
            "LR": 65.9,
            "RR": 73.9,
            "action_recognition": 94.3,
            "attribute_comparison": 74.4,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 77.1,
            "function_reasoning": 86.8,
            "future_prediction": 68.1,
            "identity_reasoning": 97.6,
            "image_emotion": 74.7,
            "image_quality": 65.9,
            "image_scene": 91.5,
            "image_style": 74.1,
            "image_topic": 96.5,
            "nature_relation": 86.4,
            "object_localization": 73.1,
            "ocr": 96.1,
            "physical_property_reasoning": 61.0,
            "physical_relation": 51.9,
            "social_relation": 75.6,
            "spatial_relationship": 45.7,
            "structuralized_imagetext_understanding": 64.4,
            "Method": [
                "Yi-Vision",
                "https://platform.lingyiwanwu.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "01-AI",
            "Time": "2024/08/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 312
        },
        {
            "Overall": 80.9,
            "AR": 82.3,
            "CP": 85.7,
            "FP-C": 72.1,
            "FP-S": 84.4,
            "LR": 70.5,
            "RR": 81.0,
            "action_recognition": 89.8,
            "attribute_comparison": 78.2,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 79.7,
            "function_reasoning": 87.7,
            "future_prediction": 73.6,
            "identity_reasoning": 97.6,
            "image_emotion": 75.9,
            "image_quality": 87.1,
            "image_scene": 91.5,
            "image_style": 75.3,
            "image_topic": 95.3,
            "nature_relation": 86.4,
            "object_localization": 74.0,
            "ocr": 94.8,
            "physical_property_reasoning": 64.0,
            "physical_relation": 69.2,
            "social_relation": 83.3,
            "spatial_relationship": 46.9,
            "structuralized_imagetext_understanding": 68.3,
            "Method": [
                "Ovis1.5-Gemma2-9B",
                "https://huggingface.co/AIDC-AI/Ovis1.5-Gemma2-9B"
            ],
            "Parameters": "11.4B",
            "Language Model": "Gemma2-9B-It",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/08/04",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 313
        },
        {
            "Overall": 74.8,
            "AR": 82.3,
            "CP": 82.0,
            "FP-C": 68.0,
            "FP-S": 78.1,
            "LR": 55.5,
            "RR": 66.4,
            "action_recognition": 92.0,
            "attribute_comparison": 69.2,
            "attribute_recognition": 82.8,
            "celebrity_recognition": 77.1,
            "function_reasoning": 84.9,
            "future_prediction": 66.7,
            "identity_reasoning": 97.6,
            "image_emotion": 74.7,
            "image_quality": 63.5,
            "image_scene": 91.5,
            "image_style": 78.8,
            "image_topic": 96.5,
            "nature_relation": 63.0,
            "object_localization": 65.4,
            "ocr": 90.9,
            "physical_property_reasoning": 67.0,
            "physical_relation": 48.1,
            "social_relation": 82.1,
            "spatial_relationship": 40.7,
            "structuralized_imagetext_understanding": 47.5,
            "Method": [
                "LLaVA-Next-Llama3",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "ByteDance",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 307
        },
        {
            "Overall": 73.8,
            "AR": 84.0,
            "CP": 84.8,
            "FP-C": 64.0,
            "FP-S": 71.9,
            "LR": 52.6,
            "RR": 68.2,
            "action_recognition": 95.5,
            "attribute_comparison": 65.4,
            "attribute_recognition": 80.8,
            "celebrity_recognition": 70.3,
            "function_reasoning": 84.9,
            "future_prediction": 70.8,
            "identity_reasoning": 97.6,
            "image_emotion": 75.9,
            "image_quality": 74.1,
            "image_scene": 94.6,
            "image_style": 77.6,
            "image_topic": 96.5,
            "nature_relation": 72.8,
            "object_localization": 51.0,
            "ocr": 90.9,
            "physical_property_reasoning": 72.0,
            "physical_relation": 36.5,
            "social_relation": 84.6,
            "spatial_relationship": 28.4,
            "structuralized_imagetext_understanding": 39.6,
            "Method": [
                "LLaVA-Next-Interleave-7B-DPO",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen1.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 308
        },
        {
            "Overall": 74.7,
            "AR": 83.7,
            "CP": 84.8,
            "FP-C": 64.8,
            "FP-S": 73.6,
            "LR": 56.1,
            "RR": 69.2,
            "action_recognition": 94.3,
            "attribute_comparison": 61.5,
            "attribute_recognition": 83.8,
            "celebrity_recognition": 78.0,
            "function_reasoning": 83.0,
            "future_prediction": 70.8,
            "identity_reasoning": 98.8,
            "image_emotion": 72.3,
            "image_quality": 75.3,
            "image_scene": 93.8,
            "image_style": 81.2,
            "image_topic": 96.5,
            "nature_relation": 64.2,
            "object_localization": 45.2,
            "ocr": 92.2,
            "physical_property_reasoning": 72.0,
            "physical_relation": 44.2,
            "social_relation": 91.0,
            "spatial_relationship": 35.8,
            "structuralized_imagetext_understanding": 45.5,
            "Method": [
                "LLaVA-Next-Interleave-7B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen1.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 314
        },
        {
            "Overall": 79.4,
            "AR": 81.6,
            "CP": 83.7,
            "FP-C": 72.1,
            "FP-S": 85.4,
            "LR": 61.8,
            "RR": 78.2,
            "action_recognition": 93.2,
            "attribute_comparison": 70.5,
            "attribute_recognition": 91.9,
            "celebrity_recognition": 88.1,
            "function_reasoning": 91.5,
            "future_prediction": 70.8,
            "identity_reasoning": 98.8,
            "image_emotion": 77.1,
            "image_quality": 69.4,
            "image_scene": 95.3,
            "image_style": 74.1,
            "image_topic": 96.5,
            "nature_relation": 88.9,
            "object_localization": 69.2,
            "ocr": 94.8,
            "physical_property_reasoning": 57.0,
            "physical_relation": 51.9,
            "social_relation": 84.6,
            "spatial_relationship": 50.6,
            "structuralized_imagetext_understanding": 55.4,
            "Method": [
                "LLaVA-Next-Qwen-32B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "33B",
            "Language Model": "Qwen1.5-32B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 315
        },
        {
            "Overall": 68.2,
            "AR": 78.1,
            "CP": 79.0,
            "FP-C": 58.7,
            "FP-S": 66.6,
            "LR": 46.2,
            "RR": 62.6,
            "action_recognition": 95.5,
            "attribute_comparison": 41.0,
            "attribute_recognition": 78.8,
            "celebrity_recognition": 78.8,
            "function_reasoning": 80.2,
            "future_prediction": 73.6,
            "identity_reasoning": 96.3,
            "image_emotion": 73.5,
            "image_quality": 51.8,
            "image_scene": 90.7,
            "image_style": 75.3,
            "image_topic": 97.6,
            "nature_relation": 59.3,
            "object_localization": 32.7,
            "ocr": 77.9,
            "physical_property_reasoning": 61.0,
            "physical_relation": 34.6,
            "social_relation": 84.6,
            "spatial_relationship": 35.8,
            "structuralized_imagetext_understanding": 26.7,
            "Method": [
                "Mantis-8B-clip-llama3",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-clip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 316
        },
        {
            "Overall": 69.0,
            "AR": 79.2,
            "CP": 77.3,
            "FP-C": 58.7,
            "FP-S": 73.1,
            "LR": 43.9,
            "RR": 61.6,
            "action_recognition": 94.3,
            "attribute_comparison": 47.4,
            "attribute_recognition": 84.8,
            "celebrity_recognition": 79.7,
            "function_reasoning": 87.7,
            "future_prediction": 66.7,
            "identity_reasoning": 97.6,
            "image_emotion": 73.5,
            "image_quality": 32.9,
            "image_scene": 93.0,
            "image_style": 82.4,
            "image_topic": 96.5,
            "nature_relation": 48.1,
            "object_localization": 41.3,
            "ocr": 90.9,
            "physical_property_reasoning": 55.0,
            "physical_relation": 42.3,
            "social_relation": 88.5,
            "spatial_relationship": 30.9,
            "structuralized_imagetext_understanding": 27.7,
            "Method": [
                "Mantis-8B-siglip-llama3",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-siglip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 317
        },
        {
            "Overall": 76.0,
            "AR": 76.4,
            "CP": 84.8,
            "FP-C": 66.0,
            "FP-S": 83.4,
            "LR": 57.2,
            "RR": 68.7,
            "action_recognition": 93.2,
            "attribute_comparison": 69.2,
            "attribute_recognition": 87.9,
            "celebrity_recognition": 89.0,
            "function_reasoning": 83.0,
            "future_prediction": 73.6,
            "identity_reasoning": 97.6,
            "image_emotion": 78.3,
            "image_quality": 63.5,
            "image_scene": 95.3,
            "image_style": 84.7,
            "image_topic": 96.5,
            "nature_relation": 70.4,
            "object_localization": 64.4,
            "ocr": 94.8,
            "physical_property_reasoning": 52.0,
            "physical_relation": 46.2,
            "social_relation": 82.1,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 45.5,
            "Method": [
                "Mantis-8B-Idefics2",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-Idefics2"
            ],
            "Parameters": "8B",
            "Language Model": "Mistral-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 318
        },
        {
            "Overall": 81.5,
            "AR": 81.9,
            "CP": 86.1,
            "FP-C": 72.5,
            "FP-S": 87.9,
            "LR": 67.6,
            "RR": 80.6,
            "action_recognition": 92.0,
            "attribute_comparison": 78.2,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 86.4,
            "function_reasoning": 90.6,
            "future_prediction": 70.8,
            "identity_reasoning": 97.6,
            "image_emotion": 71.1,
            "image_quality": 83.5,
            "image_scene": 92.2,
            "image_style": 82.4,
            "image_topic": 97.6,
            "nature_relation": 84.0,
            "object_localization": 77.9,
            "ocr": 93.5,
            "physical_property_reasoning": 60.0,
            "physical_relation": 75.0,
            "social_relation": 80.8,
            "spatial_relationship": 45.7,
            "structuralized_imagetext_understanding": 65.3,
            "Method": [
                "MiniCPM-V-2.6",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-siglip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "OpenBMB",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 319
        },
        {
            "Overall": 82.1,
            "AR": 86.1,
            "CP": 86.7,
            "FP-C": 81.0,
            "FP-S": 76.4,
            "LR": 79.8,
            "RR": 80.6,
            "action_recognition": 95.5,
            "attribute_comparison": 78.2,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 49.2,
            "function_reasoning": 88.7,
            "future_prediction": 76.4,
            "identity_reasoning": 97.6,
            "image_emotion": 74.7,
            "image_quality": 81.2,
            "image_scene": 93.0,
            "image_style": 84.7,
            "image_topic": 96.5,
            "nature_relation": 92.6,
            "object_localization": 77.9,
            "ocr": 98.7,
            "physical_property_reasoning": 74.0,
            "physical_relation": 55.8,
            "social_relation": 84.6,
            "spatial_relationship": 67.9,
            "structuralized_imagetext_understanding": 82.2,
            "Method": [
                "GPT-4o (0806, detail-high)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 320
        },
        {
            "Overall": 77.0,
            "AR": 82.3,
            "CP": 83.3,
            "FP-C": 71.7,
            "FP-S": 80.7,
            "LR": 55.5,
            "RR": 72.5,
            "action_recognition": 93.2,
            "attribute_comparison": 78.2,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 72.0,
            "function_reasoning": 87.7,
            "future_prediction": 65.3,
            "identity_reasoning": 96.3,
            "image_emotion": 73.5,
            "image_quality": 71.8,
            "image_scene": 93.8,
            "image_style": 74.1,
            "image_topic": 97.6,
            "nature_relation": 65.4,
            "object_localization": 72.1,
            "ocr": 88.3,
            "physical_property_reasoning": 65.0,
            "physical_relation": 67.3,
            "social_relation": 83.3,
            "spatial_relationship": 42.0,
            "structuralized_imagetext_understanding": 48.5,
            "Method": [
                "Llama-3-MixSense-v1.1",
                "https://huggingface.co/Zero-Vision/Llama-3-MixSenseV1_1"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "Florence-2-Large-FT",
            "Org": "ZeroVision",
            "Time": "2024/08/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 321
        },
        {
            "Overall": 82.6,
            "AR": 86.5,
            "CP": 83.7,
            "FP-C": 78.1,
            "FP-S": 88.7,
            "LR": 68.8,
            "RR": 80.1,
            "action_recognition": 94.3,
            "attribute_comparison": 82.1,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 91.5,
            "function_reasoning": 90.6,
            "future_prediction": 79.2,
            "identity_reasoning": 97.6,
            "image_emotion": 72.3,
            "image_quality": 78.8,
            "image_scene": 90.7,
            "image_style": 76.5,
            "image_topic": 96.5,
            "nature_relation": 77.8,
            "object_localization": 75.0,
            "ocr": 96.1,
            "physical_property_reasoning": 73.0,
            "physical_relation": 67.3,
            "social_relation": 91.0,
            "spatial_relationship": 56.8,
            "structuralized_imagetext_understanding": 61.4,
            "Method": [
                "OmChat-v2.0-13B",
                "https://huggingface.co/omlab/omchat-v2.0-13B-single-beta_hf"
            ],
            "Parameters": "13B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "InternViT-6B",
            "Org": "Om AI",
            "Time": "2024/08/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 323
        },
        {
            "Overall": 72.0,
            "AR": 79.5,
            "CP": 79.4,
            "FP-C": 64.4,
            "FP-S": 77.4,
            "LR": 50.3,
            "RR": 61.6,
            "action_recognition": 94.3,
            "attribute_comparison": 66.7,
            "attribute_recognition": 78.8,
            "celebrity_recognition": 78.8,
            "function_reasoning": 82.1,
            "future_prediction": 68.1,
            "identity_reasoning": 95.1,
            "image_emotion": 66.3,
            "image_quality": 52.9,
            "image_scene": 93.0,
            "image_style": 81.2,
            "image_topic": 96.5,
            "nature_relation": 64.2,
            "object_localization": 61.5,
            "ocr": 94.8,
            "physical_property_reasoning": 64.0,
            "physical_relation": 36.5,
            "social_relation": 75.6,
            "spatial_relationship": 29.6,
            "structuralized_imagetext_understanding": 37.6,
            "Method": [
                "Parrot-7B",
                "https://huggingface.co/AIDC-AI/Parrot-7B"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Alibaba",
            "Time": "2024/08/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 324
        },
        {
            "Overall": 64.5,
            "AR": 76.0,
            "CP": 74.5,
            "FP-C": 51.8,
            "FP-S": 67.8,
            "LR": 32.9,
            "RR": 61.1,
            "action_recognition": 90.9,
            "attribute_comparison": 39.7,
            "attribute_recognition": 76.8,
            "celebrity_recognition": 78.0,
            "function_reasoning": 81.1,
            "future_prediction": 55.6,
            "identity_reasoning": 95.1,
            "image_emotion": 72.3,
            "image_quality": 34.1,
            "image_scene": 89.1,
            "image_style": 72.9,
            "image_topic": 96.5,
            "nature_relation": 63.0,
            "object_localization": 35.6,
            "ocr": 84.4,
            "physical_property_reasoning": 55.0,
            "physical_relation": 32.7,
            "social_relation": 78.2,
            "spatial_relationship": 21.0,
            "structuralized_imagetext_understanding": 16.8,
            "Method": [
                "VILA1.5-3B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-3b"
            ],
            "Parameters": "3B",
            "Language Model": "Sheared-LLaMA-2.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 325
        },
        {
            "Overall": 62.1,
            "AR": 75.3,
            "CP": 71.7,
            "FP-C": 55.9,
            "FP-S": 62.6,
            "LR": 36.4,
            "RR": 50.2,
            "action_recognition": 92.0,
            "attribute_comparison": 52.6,
            "attribute_recognition": 70.7,
            "celebrity_recognition": 66.9,
            "function_reasoning": 84.9,
            "future_prediction": 59.7,
            "identity_reasoning": 91.5,
            "image_emotion": 68.7,
            "image_quality": 47.1,
            "image_scene": 82.9,
            "image_style": 58.8,
            "image_topic": 95.3,
            "nature_relation": 43.2,
            "object_localization": 30.8,
            "ocr": 88.3,
            "physical_property_reasoning": 52.0,
            "physical_relation": 28.8,
            "social_relation": 71.8,
            "spatial_relationship": 19.8,
            "structuralized_imagetext_understanding": 19.8,
            "Method": [
                "Llama-3-VILA1.5-8B",
                "https://huggingface.co/Efficient-Large-Model/Llama-3-VILA1.5-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 326
        },
        {
            "Overall": 74.4,
            "AR": 77.4,
            "CP": 83.3,
            "FP-C": 66.0,
            "FP-S": 78.6,
            "LR": 50.9,
            "RR": 72.0,
            "action_recognition": 92.0,
            "attribute_comparison": 71.8,
            "attribute_recognition": 86.9,
            "celebrity_recognition": 82.2,
            "function_reasoning": 86.8,
            "future_prediction": 63.9,
            "identity_reasoning": 96.3,
            "image_emotion": 75.9,
            "image_quality": 68.2,
            "image_scene": 92.2,
            "image_style": 78.8,
            "image_topic": 96.5,
            "nature_relation": 81.5,
            "object_localization": 56.7,
            "ocr": 92.2,
            "physical_property_reasoning": 52.0,
            "physical_relation": 42.3,
            "social_relation": 82.1,
            "spatial_relationship": 32.1,
            "structuralized_imagetext_understanding": 41.6,
            "Method": [
                "VILA1.5-13B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-13b"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 327
        },
        {
            "Overall": 81.7,
            "AR": 83.0,
            "CP": 85.4,
            "FP-C": 74.1,
            "FP-S": 89.4,
            "LR": 63.6,
            "RR": 80.6,
            "action_recognition": 94.3,
            "attribute_comparison": 69.2,
            "attribute_recognition": 94.9,
            "celebrity_recognition": 90.7,
            "function_reasoning": 89.6,
            "future_prediction": 72.2,
            "identity_reasoning": 97.6,
            "image_emotion": 75.9,
            "image_quality": 76.5,
            "image_scene": 93.0,
            "image_style": 81.2,
            "image_topic": 96.5,
            "nature_relation": 88.9,
            "object_localization": 79.8,
            "ocr": 93.5,
            "physical_property_reasoning": 64.0,
            "physical_relation": 55.8,
            "social_relation": 88.5,
            "spatial_relationship": 56.8,
            "structuralized_imagetext_understanding": 57.4,
            "Method": [
                "VILA1.5-40B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-40b"
            ],
            "Parameters": "40B",
            "Language Model": "Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 328
        },
        {
            "Overall": 82.5,
            "AR": 85.4,
            "CP": 87.2,
            "FP-C": 74.5,
            "FP-S": 87.9,
            "LR": 68.2,
            "RR": 78.7,
            "action_recognition": 95.5,
            "attribute_comparison": 82.1,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 85.6,
            "function_reasoning": 88.7,
            "future_prediction": 76.4,
            "identity_reasoning": 98.8,
            "image_emotion": 79.5,
            "image_quality": 80.0,
            "image_scene": 95.3,
            "image_style": 80.0,
            "image_topic": 96.5,
            "nature_relation": 81.5,
            "object_localization": 77.9,
            "ocr": 94.8,
            "physical_property_reasoning": 71.0,
            "physical_relation": 69.2,
            "social_relation": 82.1,
            "spatial_relationship": 44.4,
            "structuralized_imagetext_understanding": 62.4,
            "Org": "DataCanvas",
            "Time": "2024/08/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "MMAlaya2",
                "https://huggingface.co/DataCanvas/MMAlaya2"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "key": 329
        },
        {
            "Overall": 77.5,
            "AR": 83.7,
            "CP": 83.5,
            "FP-C": 67.6,
            "FP-S": 80.9,
            "LR": 62.4,
            "RR": 73.0,
            "action_recognition": 92.0,
            "attribute_comparison": 66.7,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 78.0,
            "function_reasoning": 85.8,
            "future_prediction": 70.8,
            "identity_reasoning": 96.3,
            "image_emotion": 77.1,
            "image_quality": 67.1,
            "image_scene": 93.8,
            "image_style": 76.5,
            "image_topic": 97.6,
            "nature_relation": 74.1,
            "object_localization": 62.5,
            "ocr": 93.5,
            "physical_property_reasoning": 71.0,
            "physical_relation": 57.7,
            "social_relation": 82.1,
            "spatial_relationship": 42.0,
            "structuralized_imagetext_understanding": 56.4,
            "Org": "HuggingFace",
            "Time": "2024/08/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "Idefics3-8B-Llama3",
                "https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "key": 330
        },
        {
            "Overall": 76.0,
            "AR": 78.1,
            "CP": 82.7,
            "FP-C": 66.0,
            "FP-S": 79.1,
            "LR": 63.0,
            "RR": 74.9,
            "action_recognition": 90.9,
            "attribute_comparison": 64.1,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 79.7,
            "function_reasoning": 83.0,
            "future_prediction": 66.7,
            "identity_reasoning": 97.6,
            "image_emotion": 74.7,
            "image_quality": 69.4,
            "image_scene": 92.2,
            "image_style": 76.5,
            "image_topic": 95.3,
            "nature_relation": 79.0,
            "object_localization": 54.8,
            "ocr": 93.5,
            "physical_property_reasoning": 57.0,
            "physical_relation": 53.8,
            "social_relation": 84.6,
            "spatial_relationship": 40.7,
            "structuralized_imagetext_understanding": 60.4,
            "Org": "Microsoft",
            "Time": "2024/08/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "Phi-3.5-Vision",
                "https://huggingface.co/microsoft/Phi-3.5-vision-instruct"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3.5",
            "Vision Model": "CLIP ViT-L/14",
            "key": 331
        },
        {
            "Overall": 81.8,
            "AR": 81.9,
            "CP": 86.5,
            "FP-C": 74.5,
            "FP-S": 82.7,
            "LR": 74.6,
            "RR": 84.4,
            "action_recognition": 93.2,
            "attribute_comparison": 76.9,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 78.0,
            "function_reasoning": 87.7,
            "future_prediction": 83.3,
            "identity_reasoning": 96.3,
            "image_emotion": 72.3,
            "image_quality": 84.7,
            "image_scene": 92.2,
            "image_style": 82.4,
            "image_topic": 97.6,
            "nature_relation": 93.8,
            "object_localization": 73.1,
            "ocr": 93.5,
            "physical_property_reasoning": 64.0,
            "physical_relation": 69.2,
            "social_relation": 84.6,
            "spatial_relationship": 51.9,
            "structuralized_imagetext_understanding": 68.3,
            "Org": "Monolith Foundation",
            "Time": "2024/08/30",
            "Verified": "No",
            "OpenSource": "Yes",
            "Method": [
                "Mirage-12B-v2.0",
                "https://huggingface.co/MonolithFoundation/Mirage-12B"
            ],
            "Parameters": "12B",
            "Language Model": "Mistral-12B",
            "Vision Model": "SigLIP-400M",
            "key": 332
        },
        {
            "Overall": 66.5,
            "AR": 78.8,
            "CP": 75.8,
            "FP-C": 57.9,
            "FP-S": 68.8,
            "LR": 37.0,
            "RR": 58.8,
            "action_recognition": 92.0,
            "attribute_comparison": 55.1,
            "attribute_recognition": 78.8,
            "celebrity_recognition": 72.0,
            "function_reasoning": 82.1,
            "future_prediction": 58.3,
            "identity_reasoning": 98.8,
            "image_emotion": 73.5,
            "image_quality": 48.2,
            "image_scene": 86.8,
            "image_style": 68.2,
            "image_topic": 96.5,
            "nature_relation": 51.9,
            "object_localization": 44.2,
            "ocr": 84.4,
            "physical_property_reasoning": 59.0,
            "physical_relation": 38.5,
            "social_relation": 79.5,
            "spatial_relationship": 23.5,
            "structuralized_imagetext_understanding": 21.8,
            "Method": [
                "LLaVA-v1.5-7B",
                "https://arxiv.org/abs/2310.03744"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2023/10/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 186
        },
        {
            "Overall": 69.2,
            "AR": 76.7,
            "CP": 77.7,
            "FP-C": 59.9,
            "FP-S": 74.1,
            "LR": 43.4,
            "RR": 63.0,
            "action_recognition": 92.0,
            "attribute_comparison": 55.1,
            "attribute_recognition": 80.8,
            "celebrity_recognition": 79.7,
            "function_reasoning": 83.0,
            "future_prediction": 70.8,
            "identity_reasoning": 92.7,
            "image_emotion": 75.9,
            "image_quality": 48.2,
            "image_scene": 92.2,
            "image_style": 68.2,
            "image_topic": 96.5,
            "nature_relation": 60.5,
            "object_localization": 50.0,
            "ocr": 89.6,
            "physical_property_reasoning": 57.0,
            "physical_relation": 38.5,
            "social_relation": 82.1,
            "spatial_relationship": 29.6,
            "structuralized_imagetext_understanding": 23.8,
            "Method": [
                "LLaVA-v1.5-13B",
                "https://arxiv.org/abs/2310.03744"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2023/10/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 188
        },
        {
            "Overall": 78.3,
            "AR": 80.9,
            "CP": 84.4,
            "FP-C": 70.9,
            "FP-S": 84.4,
            "LR": 52.6,
            "RR": 79.1,
            "action_recognition": 92.0,
            "attribute_comparison": 80.8,
            "attribute_recognition": 91.9,
            "celebrity_recognition": 83.9,
            "function_reasoning": 86.8,
            "future_prediction": 70.8,
            "identity_reasoning": 98.8,
            "image_emotion": 78.3,
            "image_quality": 67.1,
            "image_scene": 92.2,
            "image_style": 82.4,
            "image_topic": 97.6,
            "nature_relation": 81.5,
            "object_localization": 72.1,
            "ocr": 92.2,
            "physical_property_reasoning": 60.0,
            "physical_relation": 59.6,
            "social_relation": 89.7,
            "spatial_relationship": 38.3,
            "structuralized_imagetext_understanding": 39.6,
            "Method": [
                "XGen-MM-Instruct-Interleave-v1.5",
                "https://huggingface.co/Salesforce/xgen-mm-phi3-mini-instruct-interleave-r-v1.5"
            ],
            "Parameters": "4.4B",
            "Language Model": "Phi-3",
            "Vision Model": "SigLIP-400M",
            "Org": "Salesforce",
            "Time": "2024/09/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 333
        },
        {
            "Overall": 78.0,
            "AR": 83.0,
            "CP": 82.4,
            "FP-C": 71.7,
            "FP-S": 82.2,
            "LR": 53.8,
            "RR": 80.6,
            "action_recognition": 93.2,
            "attribute_comparison": 82.1,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 83.9,
            "function_reasoning": 86.8,
            "future_prediction": 72.2,
            "identity_reasoning": 97.6,
            "image_emotion": 75.9,
            "image_quality": 63.5,
            "image_scene": 93.8,
            "image_style": 76.5,
            "image_topic": 96.5,
            "nature_relation": 86.4,
            "object_localization": 64.4,
            "ocr": 92.2,
            "physical_property_reasoning": 67.0,
            "physical_relation": 63.5,
            "social_relation": 85.9,
            "spatial_relationship": 38.3,
            "structuralized_imagetext_understanding": 40.6,
            "Method": [
                "XGen-MM-Instruct-DPO-v1.5",
                "https://huggingface.co/Salesforce/xgen-mm-phi3-mini-instruct-dpo-r-v1.5"
            ],
            "Parameters": "4.4B",
            "Language Model": "Phi-3",
            "Vision Model": "SigLIP-400M",
            "Org": "Salesforce",
            "Time": "2024/09/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 334
        },
        {
            "Overall": 46.6,
            "AR": 53.1,
            "CP": 63.6,
            "FP-C": 38.9,
            "FP-S": 42.2,
            "LR": 28.3,
            "RR": 32.2,
            "action_recognition": 72.7,
            "attribute_comparison": 25.6,
            "attribute_recognition": 67.7,
            "celebrity_recognition": 33.9,
            "function_reasoning": 55.7,
            "future_prediction": 48.6,
            "identity_reasoning": 68.3,
            "image_emotion": 41.0,
            "image_quality": 29.4,
            "image_scene": 82.2,
            "image_style": 64.7,
            "image_topic": 90.6,
            "nature_relation": 19.8,
            "object_localization": 24.0,
            "ocr": 46.8,
            "physical_property_reasoning": 38.0,
            "physical_relation": 28.8,
            "social_relation": 47.4,
            "spatial_relationship": 14.8,
            "structuralized_imagetext_understanding": 13.9,
            "Method": [
                "Mantis-8B-Fuyu",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-Fuyu"
            ],
            "Parameters": "8B",
            "Language Model": "Fuyu-8B",
            "Vision Model": "",
            "Org": "TIGER Lab",
            "Time": "2024/09/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 339
        },
        {
            "Overall": 65.8,
            "AR": 76.7,
            "CP": 77.3,
            "FP-C": 56.7,
            "FP-S": 65.1,
            "LR": 35.3,
            "RR": 62.6,
            "action_recognition": 95.5,
            "attribute_comparison": 46.2,
            "attribute_recognition": 77.8,
            "celebrity_recognition": 72.0,
            "function_reasoning": 84.0,
            "future_prediction": 55.6,
            "identity_reasoning": 97.6,
            "image_emotion": 73.5,
            "image_quality": 48.2,
            "image_scene": 91.5,
            "image_style": 70.6,
            "image_topic": 95.3,
            "nature_relation": 56.8,
            "object_localization": 43.3,
            "ocr": 67.5,
            "physical_property_reasoning": 52.0,
            "physical_relation": 50.0,
            "social_relation": 76.9,
            "spatial_relationship": 24.7,
            "structuralized_imagetext_understanding": 20.8,
            "Method": [
                "Slime-7B",
                "https://huggingface.co/yifanzhang114/SliME-vicuna-7B"
            ],
            "Parameters": "7B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 340
        },
        {
            "Overall": 72.8,
            "AR": 80.2,
            "CP": 81.8,
            "FP-C": 63.2,
            "FP-S": 72.4,
            "LR": 44.5,
            "RR": 77.7,
            "action_recognition": 92.0,
            "attribute_comparison": 56.4,
            "attribute_recognition": 81.8,
            "celebrity_recognition": 78.0,
            "function_reasoning": 86.8,
            "future_prediction": 63.9,
            "identity_reasoning": 97.6,
            "image_emotion": 74.7,
            "image_quality": 64.7,
            "image_scene": 91.5,
            "image_style": 77.6,
            "image_topic": 95.3,
            "nature_relation": 80.2,
            "object_localization": 57.7,
            "ocr": 71.4,
            "physical_property_reasoning": 59.0,
            "physical_relation": 57.7,
            "social_relation": 88.5,
            "spatial_relationship": 38.3,
            "structuralized_imagetext_understanding": 30.7,
            "Method": [
                "Slime-8B",
                "https://huggingface.co/yifanzhang114/SliME-Llama3-8B"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 341
        },
        {
            "Overall": 65.4,
            "AR": 76.4,
            "CP": 77.7,
            "FP-C": 55.9,
            "FP-S": 65.8,
            "LR": 35.3,
            "RR": 57.8,
            "action_recognition": 93.2,
            "attribute_comparison": 44.9,
            "attribute_recognition": 77.8,
            "celebrity_recognition": 74.6,
            "function_reasoning": 84.9,
            "future_prediction": 55.6,
            "identity_reasoning": 96.3,
            "image_emotion": 75.9,
            "image_quality": 58.8,
            "image_scene": 87.6,
            "image_style": 67.1,
            "image_topic": 94.1,
            "nature_relation": 56.8,
            "object_localization": 47.1,
            "ocr": 62.3,
            "physical_property_reasoning": 51.0,
            "physical_relation": 42.3,
            "social_relation": 69.2,
            "spatial_relationship": 25.9,
            "structuralized_imagetext_understanding": 20.8,
            "Method": [
                "Slime-13B",
                "https://huggingface.co/yifanzhang114/SliME-vicuna-13B"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 342
        },
        {
            "Overall": 77.9,
            "AR": 81.2,
            "CP": 81.4,
            "FP-C": 72.5,
            "FP-S": 82.4,
            "LR": 69.4,
            "RR": 70.6,
            "action_recognition": 90.9,
            "attribute_comparison": 76.9,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 78.0,
            "function_reasoning": 90.6,
            "future_prediction": 66.7,
            "identity_reasoning": 93.9,
            "image_emotion": 67.5,
            "image_quality": 65.9,
            "image_scene": 89.9,
            "image_style": 82.4,
            "image_topic": 96.5,
            "nature_relation": 74.1,
            "object_localization": 69.2,
            "ocr": 96.1,
            "physical_property_reasoning": 61.0,
            "physical_relation": 59.6,
            "social_relation": 74.4,
            "spatial_relationship": 48.1,
            "structuralized_imagetext_understanding": 71.3,
            "Method": [
                "Pixtral-12B",
                "https://huggingface.co/mistralai/Pixtral-12B-2409"
            ],
            "Parameters": "13B",
            "Language Model": "Nemo-12B",
            "Vision Model": "ViT-400M",
            "Org": "Mistral AI",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 343
        },
        {
            "Overall": 79.4,
            "AR": 82.6,
            "CP": 85.4,
            "FP-C": 73.3,
            "FP-S": 86.2,
            "LR": 63.6,
            "RR": 69.2,
            "action_recognition": 86.4,
            "attribute_comparison": 73.1,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 90.7,
            "function_reasoning": 90.6,
            "future_prediction": 62.5,
            "identity_reasoning": 96.3,
            "image_emotion": 74.7,
            "image_quality": 77.6,
            "image_scene": 93.8,
            "image_style": 83.5,
            "image_topic": 92.9,
            "nature_relation": 86.4,
            "object_localization": 76.9,
            "ocr": 85.7,
            "physical_property_reasoning": 63.0,
            "physical_relation": 48.1,
            "social_relation": 65.4,
            "spatial_relationship": 59.3,
            "structuralized_imagetext_understanding": 64.4,
            "Method": [
                "Gemini-1.5-Flash",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 344
        },
        {
            "Overall": 61.6,
            "AR": 77.1,
            "CP": 73.9,
            "FP-C": 43.7,
            "FP-S": 62.1,
            "LR": 31.2,
            "RR": 58.3,
            "action_recognition": 93.2,
            "attribute_comparison": 15.4,
            "attribute_recognition": 75.8,
            "celebrity_recognition": 67.8,
            "function_reasoning": 78.3,
            "future_prediction": 50.0,
            "identity_reasoning": 91.5,
            "image_emotion": 74.7,
            "image_quality": 27.1,
            "image_scene": 87.6,
            "image_style": 76.5,
            "image_topic": 96.5,
            "nature_relation": 53.1,
            "object_localization": 24.0,
            "ocr": 87.0,
            "physical_property_reasoning": 64.0,
            "physical_relation": 51.9,
            "social_relation": 67.9,
            "spatial_relationship": 17.3,
            "structuralized_imagetext_understanding": 17.8,
            "Method": [
                "LLaVA-OneVision-0.5B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-0.5b-ov"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 345
        },
        {
            "Overall": 83.2,
            "AR": 87.2,
            "CP": 87.8,
            "FP-C": 74.1,
            "FP-S": 85.4,
            "LR": 71.7,
            "RR": 83.9,
            "action_recognition": 95.5,
            "attribute_comparison": 71.8,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 83.9,
            "function_reasoning": 91.5,
            "future_prediction": 79.2,
            "identity_reasoning": 97.6,
            "image_emotion": 80.7,
            "image_quality": 87.1,
            "image_scene": 93.8,
            "image_style": 76.5,
            "image_topic": 97.6,
            "nature_relation": 87.7,
            "object_localization": 71.2,
            "ocr": 93.5,
            "physical_property_reasoning": 74.0,
            "physical_relation": 73.1,
            "social_relation": 87.2,
            "spatial_relationship": 53.1,
            "structuralized_imagetext_understanding": 66.3,
            "Method": [
                "LLaVA-OneVision-7B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-7b-ov"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 346
        },
        {
            "Overall": 55.8,
            "AR": 72.9,
            "CP": 67.9,
            "FP-C": 36.0,
            "FP-S": 57.5,
            "LR": 20.2,
            "RR": 54.5,
            "action_recognition": 90.9,
            "attribute_comparison": 1.3,
            "attribute_recognition": 74.7,
            "celebrity_recognition": 65.3,
            "function_reasoning": 71.7,
            "future_prediction": 41.7,
            "identity_reasoning": 93.9,
            "image_emotion": 73.5,
            "image_quality": 1.2,
            "image_scene": 85.3,
            "image_style": 75.3,
            "image_topic": 95.3,
            "nature_relation": 49.4,
            "object_localization": 10.6,
            "ocr": 87.0,
            "physical_property_reasoning": 57.0,
            "physical_relation": 40.4,
            "social_relation": 69.2,
            "spatial_relationship": 9.9,
            "structuralized_imagetext_understanding": 5.0,
            "Method": [
                "LLaVA-OneVision-0.5B (SI)",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-0.5b-si"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 347
        },
        {
            "Overall": 80.5,
            "AR": 86.1,
            "CP": 84.8,
            "FP-C": 71.7,
            "FP-S": 83.2,
            "LR": 65.9,
            "RR": 80.6,
            "action_recognition": 94.3,
            "attribute_comparison": 76.9,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 80.5,
            "function_reasoning": 91.5,
            "future_prediction": 77.8,
            "identity_reasoning": 97.6,
            "image_emotion": 77.1,
            "image_quality": 80.0,
            "image_scene": 92.2,
            "image_style": 72.9,
            "image_topic": 97.6,
            "nature_relation": 79.0,
            "object_localization": 70.2,
            "ocr": 96.1,
            "physical_property_reasoning": 71.0,
            "physical_relation": 67.3,
            "social_relation": 91.0,
            "spatial_relationship": 42.0,
            "structuralized_imagetext_understanding": 57.4,
            "Method": [
                "LLaVA-OneVision-7B (SI)",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-7b-si"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 348
        },
        {
            "Overall": 82.7,
            "AR": 84.7,
            "CP": 86.9,
            "FP-C": 77.7,
            "FP-S": 89.2,
            "LR": 66.5,
            "RR": 77.3,
            "action_recognition": 95.5,
            "attribute_comparison": 83.3,
            "attribute_recognition": 91.9,
            "celebrity_recognition": 94.9,
            "function_reasoning": 86.8,
            "future_prediction": 72.2,
            "identity_reasoning": 97.6,
            "image_emotion": 80.7,
            "image_quality": 83.5,
            "image_scene": 92.2,
            "image_style": 80.0,
            "image_topic": 95.3,
            "nature_relation": 82.7,
            "object_localization": 74.0,
            "ocr": 97.4,
            "physical_property_reasoning": 72.0,
            "physical_relation": 53.8,
            "social_relation": 87.2,
            "spatial_relationship": 53.1,
            "structuralized_imagetext_understanding": 62.4,
            "Method": [
                "Qwen-VL-Plus-0809",
                "https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-qianwen-vl-plus-api"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 349
        },
        {
            "Overall": 85.8,
            "AR": 86.5,
            "CP": 88.0,
            "FP-C": 85.8,
            "FP-S": 89.9,
            "LR": 71.1,
            "RR": 84.4,
            "action_recognition": 94.3,
            "attribute_comparison": 91.0,
            "attribute_recognition": 94.9,
            "celebrity_recognition": 88.1,
            "function_reasoning": 91.5,
            "future_prediction": 75.0,
            "identity_reasoning": 100.0,
            "image_emotion": 78.3,
            "image_quality": 84.7,
            "image_scene": 93.0,
            "image_style": 83.5,
            "image_topic": 97.6,
            "nature_relation": 87.7,
            "object_localization": 81.7,
            "ocr": 97.4,
            "physical_property_reasoning": 70.0,
            "physical_relation": 69.2,
            "social_relation": 91.0,
            "spatial_relationship": 71.6,
            "structuralized_imagetext_understanding": 68.3,
            "Method": [
                "LLaVA-OneVision-72B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-72b-ov"
            ],
            "Parameters": "73B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 351
        },
        {
            "Overall": 83.4,
            "AR": 84.7,
            "CP": 85.9,
            "FP-C": 80.6,
            "FP-S": 85.4,
            "LR": 74.0,
            "RR": 83.4,
            "action_recognition": 95.5,
            "attribute_comparison": 83.3,
            "attribute_recognition": 91.9,
            "celebrity_recognition": 79.7,
            "function_reasoning": 87.7,
            "future_prediction": 76.4,
            "identity_reasoning": 97.6,
            "image_emotion": 77.1,
            "image_quality": 83.5,
            "image_scene": 90.7,
            "image_style": 80.0,
            "image_topic": 95.3,
            "nature_relation": 92.6,
            "object_localization": 78.8,
            "ocr": 94.8,
            "physical_property_reasoning": 71.0,
            "physical_relation": 69.2,
            "social_relation": 83.3,
            "spatial_relationship": 61.7,
            "structuralized_imagetext_understanding": 72.3,
            "Method": [
                "Ovis1.6-Gemma2-9B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B"
            ],
            "Parameters": "10.2B",
            "Language Model": "Gemma2-9B-It",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/09/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 352
        },
        {
            "Overall": 70.1,
            "AR": 78.8,
            "CP": 79.2,
            "FP-C": 63.2,
            "FP-S": 72.6,
            "LR": 42.8,
            "RR": 63.5,
            "action_recognition": 95.5,
            "attribute_comparison": 60.3,
            "attribute_recognition": 81.8,
            "celebrity_recognition": 71.2,
            "function_reasoning": 83.0,
            "future_prediction": 59.7,
            "identity_reasoning": 96.3,
            "image_emotion": 74.7,
            "image_quality": 54.1,
            "image_scene": 90.7,
            "image_style": 74.1,
            "image_topic": 96.5,
            "nature_relation": 60.5,
            "object_localization": 51.9,
            "ocr": 90.9,
            "physical_property_reasoning": 60.0,
            "physical_relation": 44.2,
            "social_relation": 79.5,
            "spatial_relationship": 30.9,
            "structuralized_imagetext_understanding": 30.7,
            "Method": [
                "Eagle-X5-7B",
                "https://huggingface.co/NVEagle/Eagle-X5-7B"
            ],
            "Parameters": "9B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 353
        },
        {
            "Overall": 72.6,
            "AR": 80.6,
            "CP": 80.3,
            "FP-C": 64.0,
            "FP-S": 75.4,
            "LR": 49.1,
            "RR": 68.7,
            "action_recognition": 94.3,
            "attribute_comparison": 66.7,
            "attribute_recognition": 85.9,
            "celebrity_recognition": 68.6,
            "function_reasoning": 85.8,
            "future_prediction": 66.7,
            "identity_reasoning": 95.1,
            "image_emotion": 69.9,
            "image_quality": 67.1,
            "image_scene": 91.5,
            "image_style": 70.6,
            "image_topic": 96.5,
            "nature_relation": 66.7,
            "object_localization": 60.6,
            "ocr": 92.2,
            "physical_property_reasoning": 63.0,
            "physical_relation": 55.8,
            "social_relation": 79.5,
            "spatial_relationship": 28.4,
            "structuralized_imagetext_understanding": 36.6,
            "Method": [
                "Eagle-X5-13B",
                "https://huggingface.co/NVEagle/Eagle-X5-13B"
            ],
            "Parameters": "15B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 354
        },
        {
            "Overall": 62.3,
            "AR": 74.3,
            "CP": 72.2,
            "FP-C": 47.4,
            "FP-S": 59.5,
            "LR": 34.7,
            "RR": 69.7,
            "action_recognition": 79.5,
            "attribute_comparison": 41.0,
            "attribute_recognition": 68.7,
            "celebrity_recognition": 57.6,
            "function_reasoning": 79.2,
            "future_prediction": 62.5,
            "identity_reasoning": 93.9,
            "image_emotion": 62.7,
            "image_quality": 32.9,
            "image_scene": 90.7,
            "image_style": 68.2,
            "image_topic": 96.5,
            "nature_relation": 72.8,
            "object_localization": 35.6,
            "ocr": 83.1,
            "physical_property_reasoning": 53.0,
            "physical_relation": 36.5,
            "social_relation": 88.5,
            "spatial_relationship": 18.5,
            "structuralized_imagetext_understanding": 14.9,
            "Method": [
                "Moondream1",
                "https://huggingface.co/vikhyatk/moondream1"
            ],
            "Parameters": "1.9B",
            "Language Model": "SigLIP-400M",
            "Vision Model": "Phi-1.5",
            "Org": "Moondream",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 355
        },
        {
            "Overall": 72.4,
            "AR": 81.2,
            "CP": 80.9,
            "FP-C": 57.5,
            "FP-S": 76.1,
            "LR": 55.5,
            "RR": 65.4,
            "action_recognition": 95.5,
            "attribute_comparison": 42.3,
            "attribute_recognition": 88.9,
            "celebrity_recognition": 70.3,
            "function_reasoning": 83.0,
            "future_prediction": 61.1,
            "identity_reasoning": 96.3,
            "image_emotion": 71.1,
            "image_quality": 63.5,
            "image_scene": 91.5,
            "image_style": 75.3,
            "image_topic": 97.6,
            "nature_relation": 63.0,
            "object_localization": 57.7,
            "ocr": 93.5,
            "physical_property_reasoning": 67.0,
            "physical_relation": 57.7,
            "social_relation": 73.1,
            "spatial_relationship": 30.9,
            "structuralized_imagetext_understanding": 51.5,
            "Method": [
                "MiniMonkey",
                "https://huggingface.co/mx262/MiniMonkey"
            ],
            "Parameters": "2.2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "HUST",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 357
        },
        {
            "Overall": 78.4,
            "AR": 79.2,
            "CP": 84.2,
            "FP-C": 69.6,
            "FP-S": 86.4,
            "LR": 56.1,
            "RR": 78.2,
            "action_recognition": 94.3,
            "attribute_comparison": 69.2,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 92.4,
            "function_reasoning": 85.8,
            "future_prediction": 68.1,
            "identity_reasoning": 96.3,
            "image_emotion": 73.5,
            "image_quality": 76.5,
            "image_scene": 94.6,
            "image_style": 74.1,
            "image_topic": 96.5,
            "nature_relation": 69.1,
            "object_localization": 66.3,
            "ocr": 96.1,
            "physical_property_reasoning": 58.0,
            "physical_relation": 67.3,
            "social_relation": 94.9,
            "spatial_relationship": 43.2,
            "structuralized_imagetext_understanding": 47.5,
            "Method": [
                "XinYuan-VL-2B-Instruct",
                "https://huggingface.co/Cylingo/Xinyuan-VL-2B"
            ],
            "Parameters": "2B",
            "Language Model": "Qwen2-1.5B",
            "Vision Model": "QwenViT",
            "Org": "Cylingo",
            "Time": "2024/09/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 359
        },
        {
            "Overall": 68.0,
            "AR": 73.6,
            "CP": 74.5,
            "FP-C": 61.9,
            "FP-S": 73.1,
            "LR": 50.3,
            "RR": 57.8,
            "action_recognition": 87.5,
            "attribute_comparison": 52.6,
            "attribute_recognition": 86.9,
            "celebrity_recognition": 61.9,
            "function_reasoning": 80.2,
            "future_prediction": 62.5,
            "identity_reasoning": 93.9,
            "image_emotion": 68.7,
            "image_quality": 43.5,
            "image_scene": 92.2,
            "image_style": 64.7,
            "image_topic": 94.1,
            "nature_relation": 53.1,
            "object_localization": 58.7,
            "ocr": 92.2,
            "physical_property_reasoning": 50.0,
            "physical_relation": 38.5,
            "social_relation": 75.6,
            "spatial_relationship": 43.2,
            "structuralized_imagetext_understanding": 41.6,
            "Method": [
                "Llama-3.2-11B-Vision-Instruct",
                "https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct"
            ],
            "Parameters": "11B",
            "Language Model": "Llama-3.1-8B",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/10/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 360
        },
        {
            "Overall": 85.3,
            "AR": 85.1,
            "CP": 87.8,
            "FP-C": 81.4,
            "FP-S": 89.2,
            "LR": 75.1,
            "RR": 85.8,
            "action_recognition": 94.3,
            "attribute_comparison": 83.3,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 96.6,
            "function_reasoning": 94.3,
            "future_prediction": 77.8,
            "identity_reasoning": 96.3,
            "image_emotion": 71.1,
            "image_quality": 84.7,
            "image_scene": 96.1,
            "image_style": 85.9,
            "image_topic": 96.5,
            "nature_relation": 91.4,
            "object_localization": 75.0,
            "ocr": 94.8,
            "physical_property_reasoning": 66.0,
            "physical_relation": 73.1,
            "social_relation": 88.5,
            "spatial_relationship": 65.4,
            "structuralized_imagetext_understanding": 73.3,
            "Method": [
                "Step-1.5V",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "Step-1.5",
            "Vision Model": "stepencoder",
            "Org": "StepFun",
            "Time": "2024/10/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 322
        },
        {
            "Overall": 81.6,
            "AR": 80.9,
            "CP": 86.3,
            "FP-C": 75.7,
            "FP-S": 88.9,
            "LR": 67.1,
            "RR": 76.8,
            "action_recognition": 92.0,
            "attribute_comparison": 78.2,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 87.3,
            "function_reasoning": 86.8,
            "future_prediction": 72.2,
            "identity_reasoning": 96.3,
            "image_emotion": 77.1,
            "image_quality": 85.9,
            "image_scene": 93.0,
            "image_style": 74.1,
            "image_topic": 97.6,
            "nature_relation": 75.3,
            "object_localization": 79.8,
            "ocr": 94.8,
            "physical_property_reasoning": 62.0,
            "physical_relation": 67.3,
            "social_relation": 84.6,
            "spatial_relationship": 55.6,
            "structuralized_imagetext_understanding": 63.4,
            "Method": [
                "POINTS-Yi-1.5-9B",
                "https://huggingface.co/WePOINTS/POINTS-Yi-1-5-9B-Chat"
            ],
            "Parameters": "9.5B",
            "Language Model": "Yi-1.5-9B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "WeChat",
            "Time": "2024/10/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTS-Yi-1.5-9B-Chat",
            "key": 362
        },
        {
            "Overall": 81.4,
            "AR": 84.4,
            "CP": 86.1,
            "FP-C": 74.1,
            "FP-S": 86.9,
            "LR": 66.5,
            "RR": 77.7,
            "action_recognition": 93.2,
            "attribute_comparison": 78.2,
            "attribute_recognition": 97.0,
            "celebrity_recognition": 83.1,
            "function_reasoning": 87.7,
            "future_prediction": 75.0,
            "identity_reasoning": 98.8,
            "image_emotion": 74.7,
            "image_quality": 84.7,
            "image_scene": 92.2,
            "image_style": 77.6,
            "image_topic": 97.6,
            "nature_relation": 77.8,
            "object_localization": 75.0,
            "ocr": 96.1,
            "physical_property_reasoning": 69.0,
            "physical_relation": 67.3,
            "social_relation": 84.6,
            "spatial_relationship": 49.4,
            "structuralized_imagetext_understanding": 60.4,
            "Method": [
                "POINTS-Qwen2.5-7B",
                "https://huggingface.co/WePOINTS/POINTS-Qwen-2-5-7B-Chat"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen-2.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "WeChat",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTS-Qwen-2.5-7B-Chat",
            "key": 363
        },
        {
            "Overall": 1.1,
            "AR": 1.4,
            "CP": 1.7,
            "FP-C": 0.4,
            "FP-S": 0.8,
            "LR": 0.6,
            "RR": 1.4,
            "action_recognition": 0.0,
            "attribute_comparison": 0.0,
            "attribute_recognition": 1.0,
            "celebrity_recognition": 0.0,
            "function_reasoning": 0.0,
            "future_prediction": 0.0,
            "identity_reasoning": 1.2,
            "image_emotion": 0.0,
            "image_quality": 8.2,
            "image_scene": 0.0,
            "image_style": 1.2,
            "image_topic": 0.0,
            "nature_relation": 2.5,
            "object_localization": 1.0,
            "ocr": 1.3,
            "physical_property_reasoning": 3.0,
            "physical_relation": 1.9,
            "social_relation": 0.0,
            "spatial_relationship": 1.2,
            "structuralized_imagetext_understanding": 1.0,
            "Method": [
                "Kosmos2",
                "https://huggingface.co/microsoft/kosmos-2-patch14-224"
            ],
            "Parameters": "1.7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Microsoft",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kosmos2",
            "key": 364
        },
        {
            "Overall": 80.4,
            "AR": 82.6,
            "CP": 83.9,
            "FP-C": 71.3,
            "FP-S": 89.9,
            "LR": 61.8,
            "RR": 77.7,
            "action_recognition": 93.2,
            "attribute_comparison": 62.8,
            "attribute_recognition": 91.9,
            "celebrity_recognition": 92.4,
            "function_reasoning": 91.5,
            "future_prediction": 73.6,
            "identity_reasoning": 95.1,
            "image_emotion": 73.5,
            "image_quality": 76.5,
            "image_scene": 91.5,
            "image_style": 77.6,
            "image_topic": 96.5,
            "nature_relation": 79.0,
            "object_localization": 82.7,
            "ocr": 93.5,
            "physical_property_reasoning": 63.0,
            "physical_relation": 61.5,
            "social_relation": 87.2,
            "spatial_relationship": 55.6,
            "structuralized_imagetext_understanding": 53.5,
            "Method": [
                "Llama-3.2-90B-Vision-Instruct",
                "https://huggingface.co/meta-llama/Llama-3.2-90B-Vision-Instruct"
            ],
            "Parameters": "88.6B",
            "Language Model": "Llama-3.1-70B",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Llama-3.2-90B-Vision-Instruct",
            "key": 365
        },
        {
            "Overall": 80.4,
            "AR": 77.8,
            "CP": 82.2,
            "FP-C": 77.7,
            "FP-S": 85.7,
            "LR": 71.7,
            "RR": 80.6,
            "action_recognition": 94.3,
            "attribute_comparison": 71.8,
            "attribute_recognition": 91.9,
            "celebrity_recognition": 81.4,
            "function_reasoning": 82.1,
            "future_prediction": 76.4,
            "identity_reasoning": 95.1,
            "image_emotion": 69.9,
            "image_quality": 78.8,
            "image_scene": 86.8,
            "image_style": 76.5,
            "image_topic": 96.5,
            "nature_relation": 82.7,
            "object_localization": 76.9,
            "ocr": 96.1,
            "physical_property_reasoning": 59.0,
            "physical_relation": 71.2,
            "social_relation": 84.6,
            "spatial_relationship": 65.4,
            "structuralized_imagetext_understanding": 68.3,
            "Method": [
                "NVLM-D-72B",
                "https://huggingface.co/nvidia/NVLM-D-72B"
            ],
            "Parameters": "79.4B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "InternViT-6B",
            "Org": "Nvidia",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "NVLM",
            "key": 366
        },
        {
            "Overall": 70.0,
            "AR": 77.4,
            "CP": 81.6,
            "FP-C": 61.1,
            "FP-S": 68.6,
            "LR": 41.0,
            "RR": 71.1,
            "action_recognition": 89.8,
            "attribute_comparison": 59.0,
            "attribute_recognition": 77.8,
            "celebrity_recognition": 66.9,
            "function_reasoning": 81.1,
            "future_prediction": 72.2,
            "identity_reasoning": 97.6,
            "image_emotion": 73.5,
            "image_quality": 62.4,
            "image_scene": 97.7,
            "image_style": 69.4,
            "image_topic": 96.5,
            "nature_relation": 71.6,
            "object_localization": 46.2,
            "ocr": 89.6,
            "physical_property_reasoning": 57.0,
            "physical_relation": 40.4,
            "social_relation": 91.0,
            "spatial_relationship": 32.1,
            "structuralized_imagetext_understanding": 18.8,
            "Method": [
                "Moondream2",
                "https://huggingface.co/vikhyatk/moondream2"
            ],
            "Parameters": "1.9B",
            "Language Model": "SigLIP-400M",
            "Vision Model": "Phi-1.5",
            "Org": "Moondream",
            "Time": "2024/10/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Moondream2",
            "key": 356
        },
        {
            "Overall": 73.6,
            "AR": 75.0,
            "CP": 78.8,
            "FP-C": 65.6,
            "FP-S": 79.6,
            "LR": 58.4,
            "RR": 70.6,
            "action_recognition": 88.6,
            "attribute_comparison": 62.8,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 72.9,
            "function_reasoning": 75.5,
            "future_prediction": 61.1,
            "identity_reasoning": 92.7,
            "image_emotion": 57.8,
            "image_quality": 75.3,
            "image_scene": 91.5,
            "image_style": 64.7,
            "image_topic": 97.6,
            "nature_relation": 70.4,
            "object_localization": 67.3,
            "ocr": 92.2,
            "physical_property_reasoning": 60.0,
            "physical_relation": 71.2,
            "social_relation": 70.5,
            "spatial_relationship": 43.2,
            "structuralized_imagetext_understanding": 56.4,
            "Method": [
                "Molmo-7B-D",
                "https://huggingface.co/allenai/Molmo-7B-D-0924"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 361,
            "dir_name": "molmo-7B-D-0924"
        },
        {
            "Overall": 72.2,
            "AR": 72.9,
            "CP": 78.2,
            "FP-C": 66.8,
            "FP-S": 75.9,
            "LR": 53.2,
            "RR": 73.0,
            "action_recognition": 90.9,
            "attribute_comparison": 69.2,
            "attribute_recognition": 87.9,
            "celebrity_recognition": 72.0,
            "function_reasoning": 75.5,
            "future_prediction": 69.4,
            "identity_reasoning": 93.9,
            "image_emotion": 69.9,
            "image_quality": 75.3,
            "image_scene": 89.1,
            "image_style": 62.4,
            "image_topic": 88.2,
            "nature_relation": 72.8,
            "object_localization": 61.5,
            "ocr": 85.7,
            "physical_property_reasoning": 53.0,
            "physical_relation": 63.5,
            "social_relation": 79.5,
            "spatial_relationship": 38.3,
            "structuralized_imagetext_understanding": 41.6,
            "Method": [
                "Molmo-7B-O",
                "https://huggingface.co/allenai/Molmo-7B-O-0924"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 367,
            "dir_name": "molmo-7B-O-0924"
        },
        {
            "Overall": 64.6,
            "AR": 69.1,
            "CP": 73.7,
            "FP-C": 55.1,
            "FP-S": 69.1,
            "LR": 37.0,
            "RR": 64.0,
            "action_recognition": 88.6,
            "attribute_comparison": 47.4,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 64.4,
            "function_reasoning": 67.0,
            "future_prediction": 54.2,
            "identity_reasoning": 91.5,
            "image_emotion": 69.9,
            "image_quality": 41.2,
            "image_scene": 86.0,
            "image_style": 68.2,
            "image_topic": 96.5,
            "nature_relation": 54.3,
            "object_localization": 40.4,
            "ocr": 87.0,
            "physical_property_reasoning": 53.0,
            "physical_relation": 59.6,
            "social_relation": 76.9,
            "spatial_relationship": 25.9,
            "structuralized_imagetext_understanding": 24.8,
            "Method": [
                "MolmoE-1B",
                "https://huggingface.co/allenai/MolmoE-1B-0924"
            ],
            "Parameters": "7.2B",
            "Language Model": "OLMoE-1B-7B-0924",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "molmoE-1B-0924",
            "key": 368
        },
        {
            "Overall": 52.0,
            "AR": 60.8,
            "CP": 67.9,
            "FP-C": 38.5,
            "FP-S": 53.3,
            "LR": 24.3,
            "RR": 41.2,
            "action_recognition": 84.1,
            "attribute_comparison": 11.5,
            "attribute_recognition": 71.7,
            "celebrity_recognition": 41.5,
            "function_reasoning": 60.4,
            "future_prediction": 44.4,
            "identity_reasoning": 89.0,
            "image_emotion": 59.0,
            "image_quality": 32.9,
            "image_scene": 83.7,
            "image_style": 60.0,
            "image_topic": 95.3,
            "nature_relation": 27.2,
            "object_localization": 27.9,
            "ocr": 81.8,
            "physical_property_reasoning": 38.0,
            "physical_relation": 28.8,
            "social_relation": 64.1,
            "spatial_relationship": 14.8,
            "structuralized_imagetext_understanding": 9.9,
            "Method": [
                "Janus-1.3B",
                "https://huggingface.co/deepseek-ai/Janus-1.3B"
            ],
            "Parameters": "2.1B",
            "Language Model": "DeepSeek-1B",
            "Vision Model": "SigLIP-400M",
            "Org": "deepseek",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Janus-1.3B",
            "key": 370
        },
        {
            "Overall": 70.6,
            "AR": 79.9,
            "CP": 79.4,
            "FP-C": 62.8,
            "FP-S": 68.3,
            "LR": 54.9,
            "RR": 64.9,
            "action_recognition": 93.2,
            "attribute_comparison": 60.3,
            "attribute_recognition": 82.8,
            "celebrity_recognition": 64.4,
            "function_reasoning": 82.1,
            "future_prediction": 59.7,
            "identity_reasoning": 95.1,
            "image_emotion": 72.3,
            "image_quality": 54.1,
            "image_scene": 90.7,
            "image_style": 77.6,
            "image_topic": 96.5,
            "nature_relation": 54.3,
            "object_localization": 43.3,
            "ocr": 89.6,
            "physical_property_reasoning": 65.0,
            "physical_relation": 48.1,
            "social_relation": 87.2,
            "spatial_relationship": 32.1,
            "structuralized_imagetext_understanding": 51.5,
            "Method": [
                "Vintern-3B-beta",
                "https://huggingface.co/5CD-AI/Vintern-3B-beta"
            ],
            "Parameters": "3.7B",
            "Language Model": "Qwen-2.5-3B",
            "Vision Model": "InternViT-300M",
            "Org": "Fifth Civil Defender",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Vintern-3B-beta",
            "key": 371
        },
        {
            "Overall": 78.5,
            "AR": 83.0,
            "CP": 82.7,
            "FP-C": 68.4,
            "FP-S": 84.7,
            "LR": 60.1,
            "RR": 78.2,
            "action_recognition": 94.3,
            "attribute_comparison": 74.4,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 84.7,
            "function_reasoning": 85.8,
            "future_prediction": 73.6,
            "identity_reasoning": 97.6,
            "image_emotion": 77.1,
            "image_quality": 75.3,
            "image_scene": 90.7,
            "image_style": 70.6,
            "image_topic": 95.3,
            "nature_relation": 79.0,
            "object_localization": 71.2,
            "ocr": 94.8,
            "physical_property_reasoning": 68.0,
            "physical_relation": 67.3,
            "social_relation": 84.6,
            "spatial_relationship": 34.6,
            "structuralized_imagetext_understanding": 50.5,
            "Method": [
                "Ovis1.6-Llama3.2-3B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Llama3.2-3B"
            ],
            "Parameters": "4.1B",
            "Language Model": "Llama-3.2-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis1.6-Llama3.2-3B",
            "key": 372
        },
        {
            "Overall": 79.0,
            "AR": 85.4,
            "CP": 81.8,
            "FP-C": 72.5,
            "FP-S": 83.2,
            "LR": 61.8,
            "RR": 77.7,
            "action_recognition": 93.2,
            "attribute_comparison": 76.9,
            "attribute_recognition": 98.0,
            "celebrity_recognition": 74.6,
            "function_reasoning": 89.6,
            "future_prediction": 66.7,
            "identity_reasoning": 96.3,
            "image_emotion": 75.9,
            "image_quality": 64.7,
            "image_scene": 90.7,
            "image_style": 75.3,
            "image_topic": 97.6,
            "nature_relation": 80.2,
            "object_localization": 71.2,
            "ocr": 93.5,
            "physical_property_reasoning": 72.0,
            "physical_relation": 61.5,
            "social_relation": 85.9,
            "spatial_relationship": 45.7,
            "structuralized_imagetext_understanding": 58.4,
            "Method": [
                "Aquila-VL-2B",
                "https://huggingface.co/BAAI/Aquila-VL-2B-llava-qwen"
            ],
            "Parameters": "2.2B",
            "Language Model": "Qwen-2.5-1.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "BAAI",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Aquila-VL-2B",
            "key": 373
        },
        {
            "Overall": 86.9,
            "AR": 85.4,
            "CP": 87.4,
            "FP-C": 89.1,
            "FP-S": 92.2,
            "LR": 78.6,
            "RR": 82.0,
            "action_recognition": 95.5,
            "attribute_comparison": 89.7,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 97.5,
            "function_reasoning": 88.7,
            "future_prediction": 79.2,
            "identity_reasoning": 100.0,
            "image_emotion": 79.5,
            "image_quality": 83.5,
            "image_scene": 93.8,
            "image_style": 80.0,
            "image_topic": 96.5,
            "nature_relation": 86.4,
            "object_localization": 84.6,
            "ocr": 96.1,
            "physical_property_reasoning": 70.0,
            "physical_relation": 57.7,
            "social_relation": 93.6,
            "spatial_relationship": 81.5,
            "structuralized_imagetext_understanding": 78.2,
            "Method": [
                "Qwen2-VL-72B",
                "https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct"
            ],
            "Parameters": "73.4B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/10/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2-VL-72B-Instruct",
            "key": 378
        },
        {
            "Overall": 80.8,
            "AR": 84.7,
            "CP": 85.4,
            "FP-C": 73.7,
            "FP-S": 81.7,
            "LR": 71.1,
            "RR": 80.1,
            "action_recognition": 94.3,
            "attribute_comparison": 75.6,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 83.9,
            "function_reasoning": 88.7,
            "future_prediction": 83.3,
            "identity_reasoning": 96.3,
            "image_emotion": 74.7,
            "image_quality": 77.6,
            "image_scene": 92.2,
            "image_style": 82.4,
            "image_topic": 96.5,
            "nature_relation": 86.4,
            "object_localization": 61.5,
            "ocr": 94.8,
            "physical_property_reasoning": 71.0,
            "physical_relation": 65.4,
            "social_relation": 83.3,
            "spatial_relationship": 49.4,
            "structuralized_imagetext_understanding": 62.4,
            "Method": [
                "Bumblebee-7B-v2.2",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "Mono-Encoder",
            "Org": "Monolith Foundation",
            "Time": "2024/10/30",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 379
        },
        {
            "Overall": 84.1,
            "AR": 86.1,
            "CP": 86.5,
            "FP-C": 81.4,
            "FP-S": 87.2,
            "LR": 78.0,
            "RR": 78.7,
            "action_recognition": 90.9,
            "attribute_comparison": 84.6,
            "attribute_recognition": 94.9,
            "celebrity_recognition": 83.1,
            "function_reasoning": 87.7,
            "future_prediction": 76.4,
            "identity_reasoning": 96.3,
            "image_emotion": 73.5,
            "image_quality": 90.6,
            "image_scene": 93.0,
            "image_style": 75.3,
            "image_topic": 96.5,
            "nature_relation": 90.1,
            "object_localization": 78.8,
            "ocr": 94.8,
            "physical_property_reasoning": 76.0,
            "physical_relation": 63.5,
            "social_relation": 76.9,
            "spatial_relationship": 67.9,
            "structuralized_imagetext_understanding": 79.2,
            "Method": [
                "BlueLM-V-3B",
                "https://developers.vivo.com/product/ai/bluelm"
            ],
            "Parameters": "3B",
            "Language Model": "BlueLM-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "vivo",
            "Time": "2024/10/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 358,
            "dir_name": "BlueLM_V"
        },
        {
            "Overall": 70.7,
            "AR": 80.2,
            "CP": 79.0,
            "FP-C": 64.0,
            "FP-S": 71.1,
            "LR": 45.7,
            "RR": 67.3,
            "action_recognition": 93.2,
            "attribute_comparison": 66.7,
            "attribute_recognition": 78.8,
            "celebrity_recognition": 74.6,
            "function_reasoning": 82.1,
            "future_prediction": 61.1,
            "identity_reasoning": 96.3,
            "image_emotion": 75.9,
            "image_quality": 57.6,
            "image_scene": 91.5,
            "image_style": 67.1,
            "image_topic": 96.5,
            "nature_relation": 65.4,
            "object_localization": 49.0,
            "ocr": 85.7,
            "physical_property_reasoning": 65.0,
            "physical_relation": 44.2,
            "social_relation": 84.6,
            "spatial_relationship": 29.6,
            "structuralized_imagetext_understanding": 34.7,
            "Method": [
                "Falcon2-VLM-11B",
                "https://huggingface.co/tiiuae/falcon-11B-vlm"
            ],
            "Parameters": "11.4B",
            "Language Model": "Falcon2-11B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Technology Innovation Institute",
            "Time": "2024/10/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Falcon2-VLM-11B",
            "key": 380
        },
        {
            "Overall": 56.3,
            "AR": 67.4,
            "CP": 69.2,
            "FP-C": 42.1,
            "FP-S": 56.5,
            "LR": 29.5,
            "RR": 51.2,
            "action_recognition": 89.8,
            "attribute_comparison": 6.4,
            "attribute_recognition": 69.7,
            "celebrity_recognition": 60.2,
            "function_reasoning": 74.5,
            "future_prediction": 55.6,
            "identity_reasoning": 89.0,
            "image_emotion": 72.3,
            "image_quality": 10.6,
            "image_scene": 87.6,
            "image_style": 70.6,
            "image_topic": 95.3,
            "nature_relation": 37.0,
            "object_localization": 20.2,
            "ocr": 83.1,
            "physical_property_reasoning": 42.0,
            "physical_relation": 36.5,
            "social_relation": 75.6,
            "spatial_relationship": 24.7,
            "structuralized_imagetext_understanding": 10.9,
            "Method": [
                "H2OVL-800M",
                "https://huggingface.co/h2oai/h2ovl-mississippi-800m"
            ],
            "Parameters": "0.83B",
            "Language Model": "H2O-DANUBE3-500M",
            "Vision Model": "InternViT-300M",
            "Org": "H2O.ai",
            "Time": "2024/10/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "h2ovl-mississippi-1b",
            "key": 381
        },
        {
            "Overall": 72.1,
            "AR": 74.0,
            "CP": 83.1,
            "FP-C": 64.8,
            "FP-S": 73.9,
            "LR": 53.8,
            "RR": 65.9,
            "action_recognition": 92.0,
            "attribute_comparison": 64.1,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 61.0,
            "function_reasoning": 77.4,
            "future_prediction": 62.5,
            "identity_reasoning": 96.3,
            "image_emotion": 71.1,
            "image_quality": 75.3,
            "image_scene": 91.5,
            "image_style": 75.3,
            "image_topic": 97.6,
            "nature_relation": 56.8,
            "object_localization": 59.6,
            "ocr": 90.9,
            "physical_property_reasoning": 52.0,
            "physical_relation": 61.5,
            "social_relation": 78.2,
            "spatial_relationship": 35.8,
            "structuralized_imagetext_understanding": 47.5,
            "Method": [
                "H2OVL-2B",
                "https://huggingface.co/h2oai/h2ovl-mississippi-2b"
            ],
            "Parameters": "2.2B",
            "Language Model": "H2O-DANUBE2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "H2O.ai",
            "Time": "2024/10/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "h2ovl-mississippi-2b",
            "key": 382
        },
        {
            "Overall": 86.8,
            "AR": 85.4,
            "CP": 86.5,
            "FP-C": 89.5,
            "FP-S": 92.2,
            "LR": 79.8,
            "RR": 82.0,
            "action_recognition": 95.5,
            "attribute_comparison": 91.0,
            "attribute_recognition": 91.9,
            "celebrity_recognition": 96.6,
            "function_reasoning": 88.7,
            "future_prediction": 80.6,
            "identity_reasoning": 97.6,
            "image_emotion": 78.3,
            "image_quality": 83.5,
            "image_scene": 93.0,
            "image_style": 78.8,
            "image_topic": 95.3,
            "nature_relation": 86.4,
            "object_localization": 84.6,
            "ocr": 96.1,
            "physical_property_reasoning": 72.0,
            "physical_relation": 55.8,
            "social_relation": 94.9,
            "spatial_relationship": 81.5,
            "structuralized_imagetext_understanding": 79.2,
            "Method": [
                "Qwen-VL-Max-0809",
                "https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-qianwen-vl-plus-api"
            ],
            "Parameters": "72B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/09/12",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "Qwen-VL-Max-0809",
            "key": 384
        },
        {
            "Overall": 82.6,
            "AR": 81.2,
            "CP": 83.9,
            "FP-C": 79.8,
            "FP-S": 86.4,
            "LR": 81.5,
            "RR": 78.7,
            "action_recognition": 88.6,
            "attribute_comparison": 79.5,
            "attribute_recognition": 88.9,
            "celebrity_recognition": 86.4,
            "function_reasoning": 85.8,
            "future_prediction": 72.2,
            "identity_reasoning": 95.1,
            "image_emotion": 63.9,
            "image_quality": 77.6,
            "image_scene": 92.2,
            "image_style": 83.5,
            "image_topic": 97.6,
            "nature_relation": 85.2,
            "object_localization": 76.9,
            "ocr": 96.1,
            "physical_property_reasoning": 65.0,
            "physical_relation": 55.8,
            "social_relation": 87.2,
            "spatial_relationship": 70.4,
            "structuralized_imagetext_understanding": 88.1,
            "Method": [
                "Claude3.5-Sonnet-20241022",
                "https://docs.anthropic.com/en/docs/build-with-claude/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/11/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Claude3-5V_Sonnet_20241022",
            "key": 376
        },
        {
            "Overall": 84.6,
            "AR": 84.0,
            "CP": 86.5,
            "FP-C": 80.6,
            "FP-S": 88.7,
            "LR": 78.6,
            "RR": 83.4,
            "action_recognition": 94.3,
            "attribute_comparison": 80.8,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 83.9,
            "function_reasoning": 90.6,
            "future_prediction": 77.8,
            "identity_reasoning": 97.6,
            "image_emotion": 75.9,
            "image_quality": 85.9,
            "image_scene": 93.0,
            "image_style": 78.8,
            "image_topic": 95.3,
            "nature_relation": 88.9,
            "object_localization": 83.7,
            "ocr": 97.4,
            "physical_property_reasoning": 66.0,
            "physical_relation": 57.7,
            "social_relation": 94.9,
            "spatial_relationship": 65.4,
            "structuralized_imagetext_understanding": 79.2,
            "Method": [
                "RBDash-v1.5",
                "https://huggingface.co/RBDash-Team/RBDash-v1.5"
            ],
            "Parameters": "79B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "CLIP ViT-L/14\nInternViT-6B",
            "Org": "DLUT",
            "Time": "2024/11/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "RBDash_72b",
            "key": 388
        },
        {
            "Overall": 79.9,
            "AR": 77.1,
            "CP": 86.9,
            "FP-C": 74.4,
            "FP-S": 85.7,
            "LR": 54.3,
            "RR": 84.8,
            "action_recognition": 93.2,
            "attribute_comparison": 79.2,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 82.2,
            "function_reasoning": 84.0,
            "future_prediction": 76.4,
            "identity_reasoning": 97.6,
            "image_emotion": 75.9,
            "image_quality": 78.8,
            "image_scene": 93.0,
            "image_style": 85.9,
            "image_topic": 97.6,
            "nature_relation": 88.9,
            "object_localization": 77.9,
            "ocr": 90.9,
            "physical_property_reasoning": 53.0,
            "physical_relation": 69.2,
            "social_relation": 91.0,
            "spatial_relationship": 49.4,
            "structuralized_imagetext_understanding": 38.6,
            "Method": [
                "Puffin1-8B",
                "https://sereact.ai/products"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "sereact.ai",
            "Time": "2024/10/21",
            "Verified": "No",
            "OpenSource": "No",
            "key": 369
        },
        {
            "Overall": 84.9,
            "AR": 87.2,
            "CP": 87.6,
            "FP-C": 79.8,
            "FP-S": 88.9,
            "LR": 72.3,
            "RR": 84.8,
            "action_recognition": 95.5,
            "attribute_comparison": 85.9,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 95.8,
            "function_reasoning": 87.7,
            "future_prediction": 73.6,
            "identity_reasoning": 98.8,
            "image_emotion": 80.7,
            "image_quality": 82.4,
            "image_scene": 91.5,
            "image_style": 83.5,
            "image_topic": 97.6,
            "nature_relation": 91.4,
            "object_localization": 71.2,
            "ocr": 97.4,
            "physical_property_reasoning": 77.0,
            "physical_relation": 71.2,
            "social_relation": 87.2,
            "spatial_relationship": 56.8,
            "structuralized_imagetext_understanding": 71.3,
            "Method": [
                "Awaker2.5-VL",
                "https://github.com/MetabrainAGI/Awaker"
            ],
            "Parameters": "10.8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "QwenViT",
            "Org": "MetabrainAGI",
            "Time": "2024/11/23",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 389
        },
        {
            "Overall": 79.2,
            "AR": 80.2,
            "CP": 81.8,
            "FP-C": 72.1,
            "FP-S": 85.7,
            "LR": 65.3,
            "RR": 79.6,
            "action_recognition": 94.3,
            "attribute_comparison": 70.5,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 76.3,
            "function_reasoning": 87.7,
            "future_prediction": 68.1,
            "identity_reasoning": 96.3,
            "image_emotion": 69.9,
            "image_quality": 70.6,
            "image_scene": 91.5,
            "image_style": 74.1,
            "image_topic": 97.6,
            "nature_relation": 79.0,
            "object_localization": 80.8,
            "ocr": 93.5,
            "physical_property_reasoning": 59.0,
            "physical_relation": 69.2,
            "social_relation": 87.2,
            "spatial_relationship": 49.4,
            "structuralized_imagetext_understanding": 63.4,
            "Method": [
                "InternVL2-8B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/11/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2-8B-MPO",
            "key": 390
        },
        {
            "Overall": 78.3,
            "AR": 75.0,
            "CP": 81.4,
            "FP-C": 70.9,
            "FP-S": 85.7,
            "LR": 67.6,
            "RR": 79.1,
            "action_recognition": 95.5,
            "attribute_comparison": 67.9,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 78.8,
            "function_reasoning": 84.0,
            "future_prediction": 69.4,
            "identity_reasoning": 92.7,
            "image_emotion": 69.9,
            "image_quality": 69.4,
            "image_scene": 92.2,
            "image_style": 71.8,
            "image_topic": 97.6,
            "nature_relation": 80.2,
            "object_localization": 79.8,
            "ocr": 93.5,
            "physical_property_reasoning": 51.0,
            "physical_relation": 69.2,
            "social_relation": 84.6,
            "spatial_relationship": 46.9,
            "structuralized_imagetext_understanding": 66.3,
            "Method": [
                "InternVL2-8B-MPO-CoT",
                "https://huggingface.co/OpenGVLab/InternVL2-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/11/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2-8B-MPO-CoT",
            "key": 391
        },
        {
            "Overall": 80.0,
            "AR": 81.2,
            "CP": 85.0,
            "FP-C": 70.4,
            "FP-S": 84.9,
            "LR": 68.2,
            "RR": 78.7,
            "action_recognition": 92.0,
            "attribute_comparison": 66.7,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 82.2,
            "function_reasoning": 88.7,
            "future_prediction": 69.4,
            "identity_reasoning": 97.6,
            "image_emotion": 77.1,
            "image_quality": 74.1,
            "image_scene": 93.0,
            "image_style": 80.0,
            "image_topic": 96.5,
            "nature_relation": 80.2,
            "object_localization": 77.9,
            "ocr": 87.0,
            "physical_property_reasoning": 60.0,
            "physical_relation": 65.4,
            "social_relation": 85.9,
            "spatial_relationship": 50.6,
            "structuralized_imagetext_understanding": 67.3,
            "Method": [
                "Eagle-X5-34B-Chat",
                "https://huggingface.co/NVEagle/Eagle-X5-34B-Chat"
            ],
            "Parameters": "36.8B",
            "Language Model": "Yi-34B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/11/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Eagle-X5-34B-Chat",
            "key": 395
        },
        {
            "Overall": 84.8,
            "AR": 86.1,
            "CP": 85.7,
            "FP-C": 83.8,
            "FP-S": 88.9,
            "LR": 74.0,
            "RR": 83.4,
            "action_recognition": 94.3,
            "attribute_comparison": 87.2,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 83.9,
            "function_reasoning": 87.7,
            "future_prediction": 77.8,
            "identity_reasoning": 98.8,
            "image_emotion": 71.1,
            "image_quality": 83.5,
            "image_scene": 93.0,
            "image_style": 80.0,
            "image_topic": 96.5,
            "nature_relation": 90.1,
            "object_localization": 85.6,
            "ocr": 96.1,
            "physical_property_reasoning": 74.0,
            "physical_relation": 71.2,
            "social_relation": 84.6,
            "spatial_relationship": 69.1,
            "structuralized_imagetext_understanding": 71.3,
            "Method": [
                "Ovis1.6-Gemma2-27B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-27B"
            ],
            "Parameters": "28.9B",
            "Language Model": "Gemma2-27B",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/11/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis1.6-Gemma2-27B",
            "key": 396
        },
        {
            "Overall": 80.0,
            "AR": 85.4,
            "CP": 78.2,
            "FP-C": 71.3,
            "FP-S": 86.9,
            "LR": 72.8,
            "RR": 79.6,
            "action_recognition": 89.8,
            "attribute_comparison": 74.4,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 84.7,
            "function_reasoning": 88.7,
            "future_prediction": 73.6,
            "identity_reasoning": 96.3,
            "image_emotion": 47.0,
            "image_quality": 78.8,
            "image_scene": 91.5,
            "image_style": 68.2,
            "image_topic": 97.6,
            "nature_relation": 84.0,
            "object_localization": 76.0,
            "ocr": 96.1,
            "physical_property_reasoning": 73.0,
            "physical_relation": 69.2,
            "social_relation": 82.1,
            "spatial_relationship": 48.1,
            "structuralized_imagetext_understanding": 72.3,
            "Method": [
                "Aria",
                "https://huggingface.co/rhymes-ai/Aria"
            ],
            "Parameters": "25.3B",
            "Language Model": "Aria-MoE",
            "Vision Model": "SigLIP-400M",
            "Org": "Rhymes AI",
            "Time": "2024/12/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Aria",
            "key": 401
        },
        {
            "Overall": 82.8,
            "AR": 85.8,
            "CP": 85.7,
            "FP-C": 75.7,
            "FP-S": 87.9,
            "LR": 67.6,
            "RR": 83.9,
            "action_recognition": 92.0,
            "attribute_comparison": 79.5,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 89.0,
            "function_reasoning": 89.6,
            "future_prediction": 72.2,
            "identity_reasoning": 97.6,
            "image_emotion": 74.7,
            "image_quality": 78.8,
            "image_scene": 91.5,
            "image_style": 82.4,
            "image_topic": 97.6,
            "nature_relation": 90.1,
            "object_localization": 76.0,
            "ocr": 92.2,
            "physical_property_reasoning": 72.0,
            "physical_relation": 63.5,
            "social_relation": 91.0,
            "spatial_relationship": 54.3,
            "structuralized_imagetext_understanding": 64.4,
            "Method": [
                "POINTS1.5-Qwen2.5-7B",
                "https://huggingface.co/WePOINTS/POINTS-1-5-Qwen-2-5-7B-Chat"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen-2.5-7B",
            "Vision Model": "NaViT",
            "Org": "WeChat",
            "Time": "2024/12/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTSV15-Qwen-2.5-7B-Chat",
            "key": 403
        },
        {
            "Overall": 84.0,
            "AR": 86.8,
            "CP": 87.8,
            "FP-C": 76.5,
            "FP-S": 89.4,
            "LR": 73.4,
            "RR": 78.7,
            "action_recognition": 94.3,
            "attribute_comparison": 82.1,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 88.1,
            "function_reasoning": 90.6,
            "future_prediction": 70.8,
            "identity_reasoning": 96.3,
            "image_emotion": 78.3,
            "image_quality": 84.7,
            "image_scene": 95.3,
            "image_style": 78.8,
            "image_topic": 97.6,
            "nature_relation": 84.0,
            "object_localization": 82.7,
            "ocr": 94.8,
            "physical_property_reasoning": 75.0,
            "physical_relation": 67.3,
            "social_relation": 80.8,
            "spatial_relationship": 51.9,
            "structuralized_imagetext_understanding": 75.2,
            "Method": [
                "BailingMM-Lite-1203",
                "https://zxb.alipay.com/llm/landing"
            ],
            "Parameters": "21B",
            "Language Model": "Bailing-20B",
            "Vision Model": "SigLIP-400M",
            "Org": "Ant Group",
            "Time": "2024/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "bailingMM-Lite",
            "key": 404
        },
        {
            "Overall": 81.4,
            "AR": 84.4,
            "CP": 81.6,
            "FP-C": 83.0,
            "FP-S": 87.4,
            "LR": 74.6,
            "RR": 69.7,
            "action_recognition": 92.0,
            "attribute_comparison": 84.6,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 78.8,
            "function_reasoning": 89.6,
            "future_prediction": 70.8,
            "identity_reasoning": 95.1,
            "image_emotion": 48.2,
            "image_quality": 74.1,
            "image_scene": 94.6,
            "image_style": 85.9,
            "image_topic": 97.6,
            "nature_relation": 86.4,
            "object_localization": 80.8,
            "ocr": 98.7,
            "physical_property_reasoning": 70.0,
            "physical_relation": 69.2,
            "social_relation": 52.6,
            "spatial_relationship": 71.6,
            "structuralized_imagetext_understanding": 77.2,
            "Method": [
                "GLM-4v-Plus",
                "https://open.bigmodel.cn/dev/api/normal-model/glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GLM4V_PLUS",
            "key": 412
        },
        {
            "Overall": 18.1,
            "AR": 26.4,
            "CP": 14.8,
            "FP-C": 26.3,
            "FP-S": 5.3,
            "LR": 39.3,
            "RR": 11.4,
            "action_recognition": 3.4,
            "attribute_comparison": 69.2,
            "attribute_recognition": 11.1,
            "celebrity_recognition": 0.0,
            "function_reasoning": 9.4,
            "future_prediction": 70.8,
            "identity_reasoning": 7.3,
            "image_emotion": 0.0,
            "image_quality": 69.4,
            "image_scene": 4.7,
            "image_style": 0.0,
            "image_topic": 4.7,
            "nature_relation": 18.5,
            "object_localization": 5.8,
            "ocr": 5.2,
            "physical_property_reasoning": 60.0,
            "physical_relation": 17.3,
            "social_relation": 0.0,
            "spatial_relationship": 9.9,
            "structuralized_imagetext_understanding": 16.8,
            "Method": [
                "Step-1.5V-mini",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "StepFun",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Step1.5V-mini",
            "key": 413
        },
        {
            "Overall": 61.0,
            "AR": 66.3,
            "CP": 74.3,
            "FP-C": 45.7,
            "FP-S": 58.5,
            "LR": 52.0,
            "RR": 54.0,
            "action_recognition": 85.2,
            "attribute_comparison": 15.4,
            "attribute_recognition": 76.8,
            "celebrity_recognition": 36.4,
            "function_reasoning": 77.4,
            "future_prediction": 51.4,
            "identity_reasoning": 81.7,
            "image_emotion": 65.1,
            "image_quality": 52.9,
            "image_scene": 88.4,
            "image_style": 62.4,
            "image_topic": 95.3,
            "nature_relation": 58.0,
            "object_localization": 39.4,
            "ocr": 94.8,
            "physical_property_reasoning": 42.0,
            "physical_relation": 32.7,
            "social_relation": 64.1,
            "spatial_relationship": 32.1,
            "structuralized_imagetext_understanding": 52.5,
            "Method": [
                "abab6.5s",
                "https://www.minimaxi.com/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "MiniMax",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "abab6.5s",
            "key": 414
        },
        {
            "Overall": 84.5,
            "AR": 82.6,
            "CP": 85.9,
            "FP-C": 83.8,
            "FP-S": 88.9,
            "LR": 77.5,
            "RR": 82.0,
            "action_recognition": 92.0,
            "attribute_comparison": 84.6,
            "attribute_recognition": 94.9,
            "celebrity_recognition": 81.4,
            "function_reasoning": 89.6,
            "future_prediction": 75.0,
            "identity_reasoning": 89.0,
            "image_emotion": 72.3,
            "image_quality": 87.1,
            "image_scene": 91.5,
            "image_style": 77.6,
            "image_topic": 97.6,
            "nature_relation": 88.9,
            "object_localization": 85.6,
            "ocr": 97.4,
            "physical_property_reasoning": 70.0,
            "physical_relation": 65.4,
            "social_relation": 85.9,
            "spatial_relationship": 74.1,
            "structuralized_imagetext_understanding": 79.2,
            "Method": [
                "abab7-preview",
                "https://www.minimaxi.com/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "MiniMax",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "abab7-preview",
            "key": 415
        },
        {
            "Overall": 86.7,
            "AR": 86.8,
            "CP": 89.1,
            "FP-C": 81.8,
            "FP-S": 90.7,
            "LR": 78.0,
            "RR": 86.7,
            "action_recognition": 92.0,
            "attribute_comparison": 87.2,
            "attribute_recognition": 94.9,
            "celebrity_recognition": 92.4,
            "function_reasoning": 91.5,
            "future_prediction": 77.8,
            "identity_reasoning": 98.8,
            "image_emotion": 78.3,
            "image_quality": 88.2,
            "image_scene": 95.3,
            "image_style": 81.2,
            "image_topic": 98.8,
            "nature_relation": 91.4,
            "object_localization": 80.8,
            "ocr": 96.1,
            "physical_property_reasoning": 72.0,
            "physical_relation": 69.2,
            "social_relation": 93.6,
            "spatial_relationship": 65.4,
            "structuralized_imagetext_understanding": 78.2,
            "Method": [
                "Taiyi",
                "https://taiyi.megvii.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Megvii & StepFun",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Taiyi",
            "key": 383
        },
        {
            "Overall": 88.2,
            "AR": 85.4,
            "CP": 89.1,
            "FP-C": 85.8,
            "FP-S": 92.5,
            "LR": 82.1,
            "RR": 90.0,
            "action_recognition": 93.2,
            "attribute_comparison": 85.9,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 89.8,
            "function_reasoning": 92.5,
            "future_prediction": 80.6,
            "identity_reasoning": 98.8,
            "image_emotion": 79.5,
            "image_quality": 85.9,
            "image_scene": 95.3,
            "image_style": 83.5,
            "image_topic": 97.6,
            "nature_relation": 91.4,
            "object_localization": 88.5,
            "ocr": 97.4,
            "physical_property_reasoning": 67.0,
            "physical_relation": 78.8,
            "social_relation": 96.2,
            "spatial_relationship": 77.8,
            "structuralized_imagetext_understanding": 83.2,
            "Method": [
                "InternVL2.5-78B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-78B"
            ],
            "Parameters": "78B",
            "Language Model": "Qwen-2.5-72B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-78B",
            "key": 423
        },
        {
            "Overall": 79.0,
            "AR": 84.7,
            "CP": 84.6,
            "FP-C": 70.9,
            "FP-S": 82.2,
            "LR": 59.5,
            "RR": 78.7,
            "action_recognition": 95.5,
            "attribute_comparison": 79.5,
            "attribute_recognition": 97.0,
            "celebrity_recognition": 74.6,
            "function_reasoning": 84.9,
            "future_prediction": 62.5,
            "identity_reasoning": 97.6,
            "image_emotion": 74.7,
            "image_quality": 78.8,
            "image_scene": 91.5,
            "image_style": 77.6,
            "image_topic": 96.5,
            "nature_relation": 84.0,
            "object_localization": 67.3,
            "ocr": 94.8,
            "physical_property_reasoning": 74.0,
            "physical_relation": 61.5,
            "social_relation": 84.6,
            "spatial_relationship": 35.8,
            "structuralized_imagetext_understanding": 57.4,
            "Method": [
                "SAIL-VL-2B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL-2B"
            ],
            "Parameters": "2.1B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "InternViT-300M",
            "Org": "ByteDance",
            "Time": "2024/12/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL-2B",
            "key": 424
        },
        {
            "Overall": 70.1,
            "AR": 76.7,
            "CP": 81.8,
            "FP-C": 55.1,
            "FP-S": 74.6,
            "LR": 46.8,
            "RR": 63.0,
            "action_recognition": 89.8,
            "attribute_comparison": 44.9,
            "attribute_recognition": 88.9,
            "celebrity_recognition": 65.3,
            "function_reasoning": 80.2,
            "future_prediction": 52.8,
            "identity_reasoning": 91.5,
            "image_emotion": 79.5,
            "image_quality": 71.8,
            "image_scene": 89.9,
            "image_style": 65.9,
            "image_topic": 97.6,
            "nature_relation": 60.5,
            "object_localization": 58.7,
            "ocr": 92.2,
            "physical_property_reasoning": 61.0,
            "physical_relation": 46.2,
            "social_relation": 76.9,
            "spatial_relationship": 27.2,
            "structuralized_imagetext_understanding": 42.6,
            "Method": [
                "InternVL2.5-1B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-1B-MPO"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen-2.5-0.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-1B-MPO",
            "key": 425
        },
        {
            "Overall": 74.5,
            "AR": 72.9,
            "CP": 85.0,
            "FP-C": 62.8,
            "FP-S": 78.4,
            "LR": 57.2,
            "RR": 73.9,
            "action_recognition": 92.0,
            "attribute_comparison": 60.3,
            "attribute_recognition": 94.9,
            "celebrity_recognition": 72.0,
            "function_reasoning": 76.4,
            "future_prediction": 62.5,
            "identity_reasoning": 93.9,
            "image_emotion": 79.5,
            "image_quality": 75.3,
            "image_scene": 93.8,
            "image_style": 74.1,
            "image_topic": 97.6,
            "nature_relation": 61.7,
            "object_localization": 61.5,
            "ocr": 89.6,
            "physical_property_reasoning": 52.0,
            "physical_relation": 63.5,
            "social_relation": 93.6,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 53.5,
            "Method": [
                "InternVL2.5-2B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-2B-MPO"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2.5-1.8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-2B-MPO",
            "key": 426
        },
        {
            "Overall": 80.4,
            "AR": 81.6,
            "CP": 86.1,
            "FP-C": 73.7,
            "FP-S": 83.2,
            "LR": 70.5,
            "RR": 77.3,
            "action_recognition": 90.9,
            "attribute_comparison": 82.1,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 77.1,
            "function_reasoning": 83.0,
            "future_prediction": 76.4,
            "identity_reasoning": 96.3,
            "image_emotion": 74.7,
            "image_quality": 82.4,
            "image_scene": 92.2,
            "image_style": 78.8,
            "image_topic": 98.8,
            "nature_relation": 67.9,
            "object_localization": 71.2,
            "ocr": 94.8,
            "physical_property_reasoning": 68.0,
            "physical_relation": 71.2,
            "social_relation": 91.0,
            "spatial_relationship": 46.9,
            "structuralized_imagetext_understanding": 66.3,
            "Method": [
                "InternVL2.5-4B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-4B-MPO"
            ],
            "Parameters": "4B",
            "Language Model": "Qwen-2.5-3B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-4B-MPO",
            "key": 427
        },
        {
            "Overall": 83.9,
            "AR": 81.6,
            "CP": 87.4,
            "FP-C": 77.3,
            "FP-S": 88.9,
            "LR": 76.3,
            "RR": 83.4,
            "action_recognition": 92.0,
            "attribute_comparison": 84.6,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 84.7,
            "function_reasoning": 86.8,
            "future_prediction": 81.9,
            "identity_reasoning": 97.6,
            "image_emotion": 79.5,
            "image_quality": 80.0,
            "image_scene": 94.6,
            "image_style": 81.2,
            "image_topic": 97.6,
            "nature_relation": 85.2,
            "object_localization": 81.7,
            "ocr": 96.1,
            "physical_property_reasoning": 63.0,
            "physical_relation": 73.1,
            "social_relation": 88.5,
            "spatial_relationship": 54.3,
            "structuralized_imagetext_understanding": 72.3,
            "Method": [
                "InternVL2.5-8B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-8B-MPO",
            "key": 428
        },
        {
            "Overall": 85.6,
            "AR": 85.4,
            "CP": 87.6,
            "FP-C": 78.5,
            "FP-S": 90.7,
            "LR": 77.5,
            "RR": 86.7,
            "action_recognition": 92.0,
            "attribute_comparison": 85.9,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 88.1,
            "function_reasoning": 92.5,
            "future_prediction": 81.9,
            "identity_reasoning": 97.6,
            "image_emotion": 78.3,
            "image_quality": 81.2,
            "image_scene": 91.5,
            "image_style": 87.1,
            "image_topic": 97.6,
            "nature_relation": 88.9,
            "object_localization": 85.6,
            "ocr": 94.8,
            "physical_property_reasoning": 68.0,
            "physical_relation": 75.0,
            "social_relation": 92.3,
            "spatial_relationship": 56.8,
            "structuralized_imagetext_understanding": 74.3,
            "Method": [
                "InternVL2.5-26B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-26B-MPO"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2.5-20B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-26B-MPO",
            "key": 429
        },
        {
            "Overall": 86.4,
            "AR": 84.7,
            "CP": 87.4,
            "FP-C": 81.4,
            "FP-S": 91.2,
            "LR": 84.4,
            "RR": 84.8,
            "action_recognition": 94.3,
            "attribute_comparison": 79.5,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 88.1,
            "function_reasoning": 90.6,
            "future_prediction": 80.6,
            "identity_reasoning": 96.3,
            "image_emotion": 73.5,
            "image_quality": 80.0,
            "image_scene": 95.3,
            "image_style": 85.9,
            "image_topic": 97.6,
            "nature_relation": 88.9,
            "object_localization": 84.6,
            "ocr": 98.7,
            "physical_property_reasoning": 69.0,
            "physical_relation": 71.2,
            "social_relation": 89.7,
            "spatial_relationship": 69.1,
            "structuralized_imagetext_understanding": 87.1,
            "Method": [
                "InternVL2.5-38B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-38B-MPO"
            ],
            "Parameters": "38B",
            "Language Model": "Qwen-2.5-32B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-38B-MPO",
            "key": 430
        },
        {
            "Overall": 88.4,
            "AR": 85.1,
            "CP": 88.9,
            "FP-C": 87.0,
            "FP-S": 92.7,
            "LR": 83.2,
            "RR": 89.6,
            "action_recognition": 93.2,
            "attribute_comparison": 91.0,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 89.0,
            "function_reasoning": 91.5,
            "future_prediction": 81.9,
            "identity_reasoning": 98.8,
            "image_emotion": 77.1,
            "image_quality": 85.9,
            "image_scene": 94.6,
            "image_style": 85.9,
            "image_topic": 97.6,
            "nature_relation": 93.8,
            "object_localization": 90.4,
            "ocr": 97.4,
            "physical_property_reasoning": 67.0,
            "physical_relation": 75.0,
            "social_relation": 94.9,
            "spatial_relationship": 76.5,
            "structuralized_imagetext_understanding": 84.2,
            "Method": [
                "InternVL2.5-78B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-78B-MPO"
            ],
            "Parameters": "78B",
            "Language Model": "Qwen-2.5-72B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-78B-MPO",
            "key": 432
        },
        {
            "Overall": 74.6,
            "AR": 80.6,
            "CP": 83.1,
            "FP-C": 69.6,
            "FP-S": 79.4,
            "LR": 48.0,
            "RR": 65.9,
            "action_recognition": 92.0,
            "attribute_comparison": 74.4,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 78.0,
            "function_reasoning": 84.0,
            "future_prediction": 55.6,
            "identity_reasoning": 96.3,
            "image_emotion": 74.7,
            "image_quality": 61.2,
            "image_scene": 93.0,
            "image_style": 84.7,
            "image_topic": 96.5,
            "nature_relation": 58.0,
            "object_localization": 55.8,
            "ocr": 96.1,
            "physical_property_reasoning": 64.0,
            "physical_relation": 57.7,
            "social_relation": 79.5,
            "spatial_relationship": 40.7,
            "structuralized_imagetext_understanding": 42.6,
            "Method": [
                "DeepSeek-VL2-Tiny",
                "https://huggingface.co/deepseek-ai/deepseek-vl2-tiny"
            ],
            "Parameters": "3.4B",
            "Language Model": "DeepSeekMoE-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2_tiny",
            "key": 433
        },
        {
            "Overall": 82.8,
            "AR": 81.6,
            "CP": 89.1,
            "FP-C": 76.1,
            "FP-S": 87.7,
            "LR": 69.9,
            "RR": 79.6,
            "action_recognition": 93.2,
            "attribute_comparison": 85.9,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 87.3,
            "function_reasoning": 88.7,
            "future_prediction": 76.4,
            "identity_reasoning": 97.6,
            "image_emotion": 73.5,
            "image_quality": 88.2,
            "image_scene": 95.3,
            "image_style": 87.1,
            "image_topic": 97.6,
            "nature_relation": 85.2,
            "object_localization": 76.0,
            "ocr": 93.5,
            "physical_property_reasoning": 61.0,
            "physical_relation": 63.5,
            "social_relation": 84.6,
            "spatial_relationship": 48.1,
            "structuralized_imagetext_understanding": 65.3,
            "Method": [
                "DeepSeek-VL2-Small",
                "https://huggingface.co/deepseek-ai/deepseek-vl2-small"
            ],
            "Parameters": "16.1B",
            "Language Model": "DeepSeekMoE-16B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2_small",
            "key": 434
        },
        {
            "Overall": 85.1,
            "AR": 87.2,
            "CP": 85.9,
            "FP-C": 84.2,
            "FP-S": 89.9,
            "LR": 77.5,
            "RR": 79.1,
            "action_recognition": 92.0,
            "attribute_comparison": 93.6,
            "attribute_recognition": 98.0,
            "celebrity_recognition": 85.6,
            "function_reasoning": 89.6,
            "future_prediction": 76.4,
            "identity_reasoning": 97.6,
            "image_emotion": 74.7,
            "image_quality": 81.2,
            "image_scene": 93.8,
            "image_style": 77.6,
            "image_topic": 97.6,
            "nature_relation": 79.0,
            "object_localization": 83.7,
            "ocr": 94.8,
            "physical_property_reasoning": 76.0,
            "physical_relation": 71.2,
            "social_relation": 84.6,
            "spatial_relationship": 66.7,
            "structuralized_imagetext_understanding": 78.2,
            "Method": [
                "VARCO-VISION-14B",
                "https://huggingface.co/NCSOFT/VARCO-VISION-14B-HF"
            ],
            "Parameters": "15.2B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "SigLIP-400M",
            "Org": "NC Research",
            "Time": "2025/01/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "varco-vision-hf",
            "key": 437
        },
        {
            "Overall": 88.3,
            "AR": 86.8,
            "CP": 88.4,
            "FP-C": 85.4,
            "FP-S": 94.2,
            "LR": 81.5,
            "RR": 88.2,
            "action_recognition": 96.6,
            "attribute_comparison": 87.2,
            "attribute_recognition": 94.9,
            "celebrity_recognition": 100.0,
            "function_reasoning": 91.5,
            "future_prediction": 84.7,
            "identity_reasoning": 98.8,
            "image_emotion": 75.9,
            "image_quality": 84.7,
            "image_scene": 94.6,
            "image_style": 87.1,
            "image_topic": 96.5,
            "nature_relation": 91.4,
            "object_localization": 84.6,
            "ocr": 97.4,
            "physical_property_reasoning": 72.0,
            "physical_relation": 78.8,
            "social_relation": 91.0,
            "spatial_relationship": 71.6,
            "structuralized_imagetext_understanding": 79.2,
            "Method": [
                "Step-1o",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "StepFun",
            "Time": "2025/01/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Step1o",
            "key": 439
        },
        {
            "Overall": 86.4,
            "AR": 86.1,
            "CP": 86.9,
            "FP-C": 84.6,
            "FP-S": 91.2,
            "LR": 79.2,
            "RR": 84.4,
            "action_recognition": 97.7,
            "attribute_comparison": 75.6,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 94.9,
            "function_reasoning": 85.8,
            "future_prediction": 76.4,
            "identity_reasoning": 95.1,
            "image_emotion": 74.7,
            "image_quality": 81.2,
            "image_scene": 93.0,
            "image_style": 84.7,
            "image_topic": 97.6,
            "nature_relation": 86.4,
            "object_localization": 79.8,
            "ocr": 97.4,
            "physical_property_reasoning": 79.0,
            "physical_relation": 75.0,
            "social_relation": 88.5,
            "spatial_relationship": 79.0,
            "structuralized_imagetext_understanding": 81.2,
            "Method": [
                "HunYuan-Standard-Vision",
                "https://cloud.tencent.com/document/product/1729/104753"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Tencent",
            "Time": "2025/01/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "HunYuan-Standard-Vision",
            "key": 440
        },
        {
            "Overall": 80.5,
            "AR": 86.8,
            "CP": 85.4,
            "FP-C": 69.6,
            "FP-S": 82.4,
            "LR": 68.2,
            "RR": 80.1,
            "action_recognition": 92.0,
            "attribute_comparison": 79.5,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 82.2,
            "function_reasoning": 87.7,
            "future_prediction": 77.8,
            "identity_reasoning": 95.1,
            "image_emotion": 78.3,
            "image_quality": 74.1,
            "image_scene": 93.8,
            "image_style": 78.8,
            "image_topic": 97.6,
            "nature_relation": 79.0,
            "object_localization": 64.4,
            "ocr": 89.6,
            "physical_property_reasoning": 79.0,
            "physical_relation": 67.3,
            "social_relation": 89.7,
            "spatial_relationship": 35.8,
            "structuralized_imagetext_understanding": 61.4,
            "Method": [
                "Ross-Qwen2-7B",
                "https://huggingface.co/HaochenWang/ross-qwen2-7b"
            ],
            "Parameters": "8.2B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "CASIA",
            "Time": "2025/01/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "ross-qwen2-7b",
            "key": 441
        },
        {
            "Overall": 79.8,
            "AR": 82.6,
            "CP": 84.2,
            "FP-C": 72.1,
            "FP-S": 85.4,
            "LR": 65.9,
            "RR": 75.8,
            "action_recognition": 92.0,
            "attribute_comparison": 74.4,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 76.3,
            "function_reasoning": 82.1,
            "future_prediction": 70.8,
            "identity_reasoning": 96.3,
            "image_emotion": 72.3,
            "image_quality": 75.3,
            "image_scene": 91.5,
            "image_style": 80.0,
            "image_topic": 97.6,
            "nature_relation": 76.5,
            "object_localization": 75.0,
            "ocr": 100.0,
            "physical_property_reasoning": 72.0,
            "physical_relation": 65.4,
            "social_relation": 82.1,
            "spatial_relationship": 48.1,
            "structuralized_imagetext_understanding": 62.4,
            "Method": [
                "VITA-1.5",
                "https://huggingface.co/VITA-MLLM/VITA-1.5"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "InternViT-300M",
            "Org": "NJU",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "vita_qwen2",
            "key": 442
        },
        {
            "Overall": 83.4,
            "AR": 83.3,
            "CP": 86.3,
            "FP-C": 75.3,
            "FP-S": 89.9,
            "LR": 71.1,
            "RR": 84.4,
            "action_recognition": 90.9,
            "attribute_comparison": 82.1,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 89.8,
            "function_reasoning": 90.6,
            "future_prediction": 73.6,
            "identity_reasoning": 96.3,
            "image_emotion": 79.5,
            "image_quality": 82.4,
            "image_scene": 90.7,
            "image_style": 78.8,
            "image_topic": 97.6,
            "nature_relation": 88.9,
            "object_localization": 82.7,
            "ocr": 94.8,
            "physical_property_reasoning": 65.0,
            "physical_relation": 67.3,
            "social_relation": 91.0,
            "spatial_relationship": 51.9,
            "structuralized_imagetext_understanding": 69.3,
            "Method": [
                "MiniCPM-o-2.6",
                "https://huggingface.co/openbmb/MiniCPM-o-2_6"
            ],
            "Parameters": "8.67B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "OpenBMB",
            "Time": "2025/01/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MiniCPM-o-2_6",
            "key": 444
        },
        {
            "Overall": 87.1,
            "AR": 88.9,
            "CP": 87.6,
            "FP-C": 81.8,
            "FP-S": 92.5,
            "LR": 79.2,
            "RR": 85.8,
            "action_recognition": 94.3,
            "attribute_comparison": 82.1,
            "attribute_recognition": 94.9,
            "celebrity_recognition": 96.6,
            "function_reasoning": 93.4,
            "future_prediction": 77.8,
            "identity_reasoning": 95.1,
            "image_emotion": 74.7,
            "image_quality": 87.1,
            "image_scene": 93.8,
            "image_style": 87.1,
            "image_topic": 91.8,
            "nature_relation": 90.1,
            "object_localization": 84.6,
            "ocr": 93.5,
            "physical_property_reasoning": 79.0,
            "physical_relation": 69.2,
            "social_relation": 92.3,
            "spatial_relationship": 67.9,
            "structuralized_imagetext_understanding": 80.2,
            "Method": [
                "BailingMM-Pro-0120",
                "https://zxb.alipay.com/llm/landing"
            ],
            "Parameters": "81B",
            "Language Model": "Bailing-80B",
            "Vision Model": "SigLIP-400M",
            "Org": "Ant Group",
            "Time": "2025/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "BailingMM-Pro-0120",
            "key": 445
        },
        {
            "Overall": 88.9,
            "AR": 85.8,
            "CP": 87.6,
            "FP-C": 89.5,
            "FP-S": 94.0,
            "LR": 86.1,
            "RR": 88.2,
            "action_recognition": 93.2,
            "attribute_comparison": 91.0,
            "attribute_recognition": 98.0,
            "celebrity_recognition": 89.8,
            "function_reasoning": 88.7,
            "future_prediction": 79.2,
            "identity_reasoning": 96.3,
            "image_emotion": 75.9,
            "image_quality": 80.0,
            "image_scene": 94.6,
            "image_style": 85.9,
            "image_topic": 97.6,
            "nature_relation": 95.1,
            "object_localization": 90.4,
            "ocr": 100.0,
            "physical_property_reasoning": 74.0,
            "physical_relation": 67.3,
            "social_relation": 94.9,
            "spatial_relationship": 84.0,
            "structuralized_imagetext_understanding": 91.1,
            "Method": [
                "GLM-4v-Plus-20250111",
                "https://open.bigmodel.cn/dev/api/normal-model/glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2025/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GLM4V_PLUS_20250111",
            "key": 447
        },
        {
            "Overall": 63.8,
            "AR": 66.7,
            "CP": 71.5,
            "FP-C": 67.6,
            "FP-S": 66.8,
            "LR": 39.9,
            "RR": 52.1,
            "action_recognition": 92.0,
            "attribute_comparison": 65.4,
            "attribute_recognition": 84.8,
            "celebrity_recognition": 41.5,
            "function_reasoning": 58.5,
            "future_prediction": 50.0,
            "identity_reasoning": 84.1,
            "image_emotion": 60.2,
            "image_quality": 44.7,
            "image_scene": 86.0,
            "image_style": 64.7,
            "image_topic": 94.1,
            "nature_relation": 38.3,
            "object_localization": 61.5,
            "ocr": 89.6,
            "physical_property_reasoning": 61.0,
            "physical_relation": 55.8,
            "social_relation": 64.1,
            "spatial_relationship": 43.2,
            "structuralized_imagetext_understanding": 32.7,
            "Method": [
                "Emu3_chat",
                "https://huggingface.co/BAAI/Emu3-Chat"
            ],
            "Parameters": "8.49B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Beijing Academy of Artificial Intelligence",
            "Time": "2025/01/26",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "dir_name": "emu3_chat",
            "key": 448
        },
        {
            "Overall": 67.5,
            "AR": 78.1,
            "CP": 75.2,
            "FP-C": 51.8,
            "FP-S": 70.6,
            "LR": 48.0,
            "RR": 64.5,
            "action_recognition": 93.2,
            "attribute_comparison": 28.2,
            "attribute_recognition": 86.9,
            "celebrity_recognition": 72.9,
            "function_reasoning": 83.0,
            "future_prediction": 61.1,
            "identity_reasoning": 91.5,
            "image_emotion": 73.5,
            "image_quality": 43.5,
            "image_scene": 86.0,
            "image_style": 72.9,
            "image_topic": 94.1,
            "nature_relation": 60.5,
            "object_localization": 37.5,
            "ocr": 90.9,
            "physical_property_reasoning": 62.0,
            "physical_relation": 51.9,
            "social_relation": 76.9,
            "spatial_relationship": 29.6,
            "structuralized_imagetext_understanding": 38.6,
            "Method": [
                "SmolVLM-Instruct",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM",
            "key": 392
        },
        {
            "Overall": 65.0,
            "AR": 77.4,
            "CP": 71.9,
            "FP-C": 50.6,
            "FP-S": 67.6,
            "LR": 41.6,
            "RR": 63.5,
            "action_recognition": 94.3,
            "attribute_comparison": 25.6,
            "attribute_recognition": 81.8,
            "celebrity_recognition": 72.9,
            "function_reasoning": 80.2,
            "future_prediction": 58.3,
            "identity_reasoning": 92.7,
            "image_emotion": 73.5,
            "image_quality": 36.5,
            "image_scene": 82.9,
            "image_style": 67.1,
            "image_topic": 94.1,
            "nature_relation": 59.3,
            "object_localization": 29.8,
            "ocr": 92.2,
            "physical_property_reasoning": 62.0,
            "physical_relation": 50.0,
            "social_relation": 76.9,
            "spatial_relationship": 27.2,
            "structuralized_imagetext_understanding": 29.7,
            "Method": [
                "SmolVLM-Instruct-DPO",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct-DPO"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-DPO",
            "key": 393
        },
        {
            "Overall": 53.7,
            "AR": 68.1,
            "CP": 65.5,
            "FP-C": 38.5,
            "FP-S": 56.0,
            "LR": 28.9,
            "RR": 41.7,
            "action_recognition": 85.2,
            "attribute_comparison": 12.8,
            "attribute_recognition": 66.7,
            "celebrity_recognition": 62.7,
            "function_reasoning": 79.2,
            "future_prediction": 45.8,
            "identity_reasoning": 90.2,
            "image_emotion": 71.1,
            "image_quality": 7.1,
            "image_scene": 81.4,
            "image_style": 69.4,
            "image_topic": 90.6,
            "nature_relation": 43.2,
            "object_localization": 14.4,
            "ocr": 88.3,
            "physical_property_reasoning": 38.0,
            "physical_relation": 21.2,
            "social_relation": 53.8,
            "spatial_relationship": 12.3,
            "structuralized_imagetext_understanding": 16.8,
            "Method": [
                "SmolVLM-Synthetic",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Synthetic"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-Synthetic",
            "key": 394
        },
        {
            "Overall": 41.7,
            "AR": 46.9,
            "CP": 54.0,
            "FP-C": 30.4,
            "FP-S": 46.7,
            "LR": 10.4,
            "RR": 37.0,
            "action_recognition": 72.7,
            "attribute_comparison": 6.4,
            "attribute_recognition": 66.7,
            "celebrity_recognition": 28.8,
            "function_reasoning": 38.7,
            "future_prediction": 13.9,
            "identity_reasoning": 74.4,
            "image_emotion": 54.2,
            "image_quality": 4.7,
            "image_scene": 73.6,
            "image_style": 36.5,
            "image_topic": 90.6,
            "nature_relation": 30.9,
            "object_localization": 20.2,
            "ocr": 84.4,
            "physical_property_reasoning": 33.0,
            "physical_relation": 28.8,
            "social_relation": 48.7,
            "spatial_relationship": 7.4,
            "structuralized_imagetext_understanding": 7.9,
            "Method": [
                "SmolVLM-256M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct"
            ],
            "Parameters": "0.26B",
            "Language Model": "SmolLM2-135M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-256M",
            "key": 449
        },
        {
            "Overall": 53.8,
            "AR": 66.0,
            "CP": 65.7,
            "FP-C": 41.7,
            "FP-S": 53.3,
            "LR": 27.7,
            "RR": 47.4,
            "action_recognition": 87.5,
            "attribute_comparison": 16.7,
            "attribute_recognition": 78.8,
            "celebrity_recognition": 33.1,
            "function_reasoning": 62.3,
            "future_prediction": 50.0,
            "identity_reasoning": 81.7,
            "image_emotion": 63.9,
            "image_quality": 8.2,
            "image_scene": 83.7,
            "image_style": 67.1,
            "image_topic": 96.5,
            "nature_relation": 46.9,
            "object_localization": 28.8,
            "ocr": 84.4,
            "physical_property_reasoning": 57.0,
            "physical_relation": 44.2,
            "social_relation": 50.0,
            "spatial_relationship": 16.0,
            "structuralized_imagetext_understanding": 11.9,
            "Method": [
                "SmolVLM-500M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-500M-Instruct"
            ],
            "Parameters": "0.51B",
            "Language Model": "SmolLM2-360M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-500M",
            "key": 450
        },
        {
            "Overall": 62.6,
            "AR": 71.2,
            "CP": 70.2,
            "FP-C": 53.8,
            "FP-S": 64.3,
            "LR": 39.3,
            "RR": 59.7,
            "action_recognition": 86.4,
            "attribute_comparison": 41.0,
            "attribute_recognition": 87.9,
            "celebrity_recognition": 51.7,
            "function_reasoning": 67.0,
            "future_prediction": 51.4,
            "identity_reasoning": 93.9,
            "image_emotion": 55.4,
            "image_quality": 35.3,
            "image_scene": 89.1,
            "image_style": 74.1,
            "image_topic": 87.1,
            "nature_relation": 55.6,
            "object_localization": 40.4,
            "ocr": 85.7,
            "physical_property_reasoning": 57.0,
            "physical_relation": 51.9,
            "social_relation": 69.2,
            "spatial_relationship": 30.9,
            "structuralized_imagetext_understanding": 30.7,
            "Method": [
                "Janus-Pro-7B",
                "https://huggingface.co/deepseek-ai/Janus-Pro-7B"
            ],
            "Parameters": "7.42B",
            "Language Model": "DeepSeek-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "deepseek",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Janus-Pro-7B",
            "key": 454
        },
        {
            "Overall": 87.4,
            "AR": 91.3,
            "CP": 87.6,
            "FP-C": 85.0,
            "FP-S": 90.2,
            "LR": 78.0,
            "RR": 86.7,
            "action_recognition": 93.2,
            "attribute_comparison": 87.2,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 89.0,
            "function_reasoning": 91.5,
            "future_prediction": 83.3,
            "identity_reasoning": 98.8,
            "image_emotion": 77.1,
            "image_quality": 78.8,
            "image_scene": 93.8,
            "image_style": 85.9,
            "image_topic": 98.8,
            "nature_relation": 95.1,
            "object_localization": 81.7,
            "ocr": 96.1,
            "physical_property_reasoning": 85.0,
            "physical_relation": 73.1,
            "social_relation": 87.2,
            "spatial_relationship": 74.1,
            "structuralized_imagetext_understanding": 74.3,
            "Method": [
                "Ola-7b",
                "https://huggingface.co/THUdyh/Ola-7b"
            ],
            "Parameters": "8.88B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "Oryx-ViT",
            "Org": "THU",
            "Time": "2025/02/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "ola",
            "key": 455
        },
        {
            "Overall": 71.6,
            "AR": 80.6,
            "CP": 80.3,
            "FP-C": 59.9,
            "FP-S": 75.4,
            "LR": 46.8,
            "RR": 67.3,
            "action_recognition": 94.3,
            "attribute_comparison": 53.8,
            "attribute_recognition": 87.9,
            "celebrity_recognition": 65.3,
            "function_reasoning": 83.0,
            "future_prediction": 62.5,
            "identity_reasoning": 92.7,
            "image_emotion": 67.5,
            "image_quality": 71.8,
            "image_scene": 90.7,
            "image_style": 69.4,
            "image_topic": 96.5,
            "nature_relation": 64.2,
            "object_localization": 60.6,
            "ocr": 94.8,
            "physical_property_reasoning": 68.0,
            "physical_relation": 55.8,
            "social_relation": 78.2,
            "spatial_relationship": 28.4,
            "structuralized_imagetext_understanding": 35.6,
            "Method": [
                "Ovis2-1B",
                "https://huggingface.co/AIDC-AI/Ovis2-1B"
            ],
            "Parameters": "1.27B",
            "Language Model": "Qwen2.5-0.5B",
            "Vision Model": "AIMv2 Large",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-1B",
            "key": 456
        },
        {
            "Overall": 78.6,
            "AR": 82.3,
            "CP": 84.2,
            "FP-C": 72.9,
            "FP-S": 79.4,
            "LR": 65.9,
            "RR": 77.3,
            "action_recognition": 92.0,
            "attribute_comparison": 83.3,
            "attribute_recognition": 88.9,
            "celebrity_recognition": 67.8,
            "function_reasoning": 84.0,
            "future_prediction": 73.6,
            "identity_reasoning": 98.8,
            "image_emotion": 74.7,
            "image_quality": 75.3,
            "image_scene": 93.0,
            "image_style": 76.5,
            "image_topic": 96.5,
            "nature_relation": 77.8,
            "object_localization": 72.1,
            "ocr": 94.8,
            "physical_property_reasoning": 67.0,
            "physical_relation": 69.2,
            "social_relation": 82.1,
            "spatial_relationship": 42.0,
            "structuralized_imagetext_understanding": 60.4,
            "Method": [
                "Ovis2-2B",
                "https://huggingface.co/AIDC-AI/Ovis2-2B"
            ],
            "Parameters": "2.46B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "AIMv2 Large",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-2B",
            "key": 457
        },
        {
            "Overall": 83.6,
            "AR": 86.1,
            "CP": 88.2,
            "FP-C": 79.4,
            "FP-S": 86.4,
            "LR": 73.4,
            "RR": 77.7,
            "action_recognition": 95.5,
            "attribute_comparison": 89.7,
            "attribute_recognition": 91.9,
            "celebrity_recognition": 79.7,
            "function_reasoning": 88.7,
            "future_prediction": 80.6,
            "identity_reasoning": 97.6,
            "image_emotion": 77.1,
            "image_quality": 85.9,
            "image_scene": 92.2,
            "image_style": 85.9,
            "image_topic": 97.6,
            "nature_relation": 79.0,
            "object_localization": 81.7,
            "ocr": 96.1,
            "physical_property_reasoning": 74.0,
            "physical_relation": 71.2,
            "social_relation": 80.8,
            "spatial_relationship": 51.9,
            "structuralized_imagetext_understanding": 68.3,
            "Method": [
                "Ovis2-4B",
                "https://huggingface.co/AIDC-AI/Ovis2-4B"
            ],
            "Parameters": "4.62B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-4B",
            "key": 458
        },
        {
            "Overall": 84.8,
            "AR": 88.2,
            "CP": 86.7,
            "FP-C": 81.0,
            "FP-S": 87.4,
            "LR": 74.0,
            "RR": 84.4,
            "action_recognition": 95.5,
            "attribute_comparison": 91.0,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 83.1,
            "function_reasoning": 89.6,
            "future_prediction": 80.6,
            "identity_reasoning": 98.8,
            "image_emotion": 80.7,
            "image_quality": 83.5,
            "image_scene": 92.2,
            "image_style": 77.6,
            "image_topic": 96.5,
            "nature_relation": 90.1,
            "object_localization": 79.8,
            "ocr": 97.4,
            "physical_property_reasoning": 78.0,
            "physical_relation": 73.1,
            "social_relation": 85.9,
            "spatial_relationship": 55.6,
            "structuralized_imagetext_understanding": 69.3,
            "Method": [
                "Ovis2-8B",
                "https://huggingface.co/AIDC-AI/Ovis2-8B"
            ],
            "Parameters": "8.94B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-8B",
            "key": 459
        },
        {
            "Overall": 87.2,
            "AR": 89.2,
            "CP": 88.0,
            "FP-C": 88.3,
            "FP-S": 89.2,
            "LR": 80.3,
            "RR": 82.9,
            "action_recognition": 94.3,
            "attribute_comparison": 94.9,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 85.6,
            "function_reasoning": 90.6,
            "future_prediction": 80.6,
            "identity_reasoning": 96.3,
            "image_emotion": 79.5,
            "image_quality": 87.1,
            "image_scene": 94.6,
            "image_style": 78.8,
            "image_topic": 96.5,
            "nature_relation": 86.4,
            "object_localization": 83.7,
            "ocr": 100.0,
            "physical_property_reasoning": 82.0,
            "physical_relation": 75.0,
            "social_relation": 84.6,
            "spatial_relationship": 75.3,
            "structuralized_imagetext_understanding": 80.2,
            "Method": [
                "Ovis2-16B",
                "https://huggingface.co/AIDC-AI/Ovis2-16B"
            ],
            "Parameters": "16.2B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-16B",
            "key": 460
        },
        {
            "Overall": 87.6,
            "AR": 88.9,
            "CP": 87.2,
            "FP-C": 88.7,
            "FP-S": 89.9,
            "LR": 80.3,
            "RR": 87.2,
            "action_recognition": 94.3,
            "attribute_comparison": 91.0,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 84.7,
            "function_reasoning": 91.5,
            "future_prediction": 81.9,
            "identity_reasoning": 98.8,
            "image_emotion": 74.7,
            "image_quality": 83.5,
            "image_scene": 94.6,
            "image_style": 82.4,
            "image_topic": 96.5,
            "nature_relation": 95.1,
            "object_localization": 85.6,
            "ocr": 98.7,
            "physical_property_reasoning": 78.0,
            "physical_relation": 75.0,
            "social_relation": 87.2,
            "spatial_relationship": 80.2,
            "structuralized_imagetext_understanding": 79.2,
            "Method": [
                "Ovis2-34B",
                "https://huggingface.co/AIDC-AI/Ovis2-34B"
            ],
            "Parameters": "34.9B",
            "Language Model": "Qwen2.5-32B",
            "Vision Model": "AIMv2-1B",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-34B",
            "key": 461
        },
        {
            "Overall": 79.1,
            "AR": 82.6,
            "CP": 82.2,
            "FP-C": 69.6,
            "FP-S": 85.2,
            "LR": 71.1,
            "RR": 73.9,
            "action_recognition": 90.9,
            "attribute_comparison": 75.6,
            "attribute_recognition": 85.9,
            "celebrity_recognition": 92.4,
            "function_reasoning": 89.6,
            "future_prediction": 70.8,
            "identity_reasoning": 97.6,
            "image_emotion": 68.7,
            "image_quality": 72.9,
            "image_scene": 91.5,
            "image_style": 76.5,
            "image_topic": 96.5,
            "nature_relation": 72.8,
            "object_localization": 69.2,
            "ocr": 94.8,
            "physical_property_reasoning": 63.0,
            "physical_relation": 44.2,
            "social_relation": 94.9,
            "spatial_relationship": 40.7,
            "structuralized_imagetext_understanding": 71.3,
            "Method": [
                "Qwen2.5-VL-3B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct"
            ],
            "Parameters": "3.75B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-3B-Instruct",
            "key": 462
        },
        {
            "Overall": 83.2,
            "AR": 82.6,
            "CP": 86.1,
            "FP-C": 80.2,
            "FP-S": 89.7,
            "LR": 72.3,
            "RR": 78.2,
            "action_recognition": 92.0,
            "attribute_comparison": 85.9,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 92.4,
            "function_reasoning": 88.7,
            "future_prediction": 76.4,
            "identity_reasoning": 96.3,
            "image_emotion": 75.9,
            "image_quality": 82.4,
            "image_scene": 91.5,
            "image_style": 81.2,
            "image_topic": 96.5,
            "nature_relation": 87.7,
            "object_localization": 78.8,
            "ocr": 96.1,
            "physical_property_reasoning": 65.0,
            "physical_relation": 51.9,
            "social_relation": 85.9,
            "spatial_relationship": 61.7,
            "structuralized_imagetext_understanding": 69.3,
            "Method": [
                "Qwen2.5-VL-7B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct"
            ],
            "Parameters": "8.29B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-7B-Instruct",
            "key": 463
        },
        {
            "Overall": 88.3,
            "AR": 84.0,
            "CP": 89.1,
            "FP-C": 87.4,
            "FP-S": 95.2,
            "LR": 85.5,
            "RR": 82.9,
            "action_recognition": 92.0,
            "attribute_comparison": 89.7,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 97.5,
            "function_reasoning": 90.6,
            "future_prediction": 77.8,
            "identity_reasoning": 97.6,
            "image_emotion": 78.3,
            "image_quality": 88.2,
            "image_scene": 94.6,
            "image_style": 84.7,
            "image_topic": 96.5,
            "nature_relation": 91.4,
            "object_localization": 90.4,
            "ocr": 100.0,
            "physical_property_reasoning": 66.0,
            "physical_relation": 57.7,
            "social_relation": 91.0,
            "spatial_relationship": 80.2,
            "structuralized_imagetext_understanding": 91.1,
            "Method": [
                "Qwen2.5-VL-72B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct"
            ],
            "Parameters": "73.4B",
            "Language Model": "Qwen2.5-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-72B-Instruct",
            "key": 464
        },
        {
            "Overall": 84.3,
            "AR": 82.6,
            "CP": 83.9,
            "FP-C": 84.2,
            "FP-S": 91.5,
            "LR": 76.3,
            "RR": 80.6,
            "action_recognition": 95.5,
            "attribute_comparison": 80.8,
            "attribute_recognition": 91.9,
            "celebrity_recognition": 97.5,
            "function_reasoning": 88.7,
            "future_prediction": 73.6,
            "identity_reasoning": 96.3,
            "image_emotion": 74.7,
            "image_quality": 76.5,
            "image_scene": 89.9,
            "image_style": 82.4,
            "image_topic": 92.9,
            "nature_relation": 88.9,
            "object_localization": 79.8,
            "ocr": 97.4,
            "physical_property_reasoning": 65.0,
            "physical_relation": 57.7,
            "social_relation": 87.2,
            "spatial_relationship": 75.3,
            "structuralized_imagetext_understanding": 78.2,
            "Method": [
                "Gemini-2.0-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2025/02/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GeminiPro2-0",
            "key": 465
        },
        {
            "Overall": 81.4,
            "AR": 81.6,
            "CP": 83.5,
            "FP-C": 83.4,
            "FP-S": 81.4,
            "LR": 79.2,
            "RR": 75.8,
            "action_recognition": 89.8,
            "attribute_comparison": 88.5,
            "attribute_recognition": 91.9,
            "celebrity_recognition": 61.0,
            "function_reasoning": 86.8,
            "future_prediction": 63.9,
            "identity_reasoning": 96.3,
            "image_emotion": 68.7,
            "image_quality": 75.3,
            "image_scene": 92.2,
            "image_style": 78.8,
            "image_topic": 97.6,
            "nature_relation": 90.1,
            "object_localization": 81.7,
            "ocr": 98.7,
            "physical_property_reasoning": 64.0,
            "physical_relation": 48.1,
            "social_relation": 79.5,
            "spatial_relationship": 71.6,
            "structuralized_imagetext_understanding": 90.1,
            "Method": [
                "Claude3.7-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2025/02/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Claude3-7V_Sonnet",
            "key": 466
        },
        {
            "Overall": 79.3,
            "AR": 77.1,
            "CP": 84.6,
            "FP-C": 72.1,
            "FP-S": 85.7,
            "LR": 69.9,
            "RR": 74.4,
            "action_recognition": 86.4,
            "attribute_comparison": 74.4,
            "attribute_recognition": 92.9,
            "celebrity_recognition": 79.7,
            "function_reasoning": 86.8,
            "future_prediction": 66.7,
            "identity_reasoning": 95.1,
            "image_emotion": 69.9,
            "image_quality": 78.8,
            "image_scene": 93.0,
            "image_style": 80.0,
            "image_topic": 96.5,
            "nature_relation": 85.2,
            "object_localization": 77.9,
            "ocr": 96.1,
            "physical_property_reasoning": 52.0,
            "physical_relation": 57.7,
            "social_relation": 74.4,
            "spatial_relationship": 54.3,
            "structuralized_imagetext_understanding": 72.3,
            "Method": [
                "moonshot-v1-8k",
                "https://platform.moonshot.cn/docs/api/chat"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Moonshot AI",
            "Time": "2025/03/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "moonshot-v1-8k",
            "key": 467
        },
        {
            "Overall": 85.3,
            "AR": 85.4,
            "CP": 85.2,
            "FP-C": 82.6,
            "FP-S": 91.5,
            "LR": 80.3,
            "RR": 81.0,
            "action_recognition": 94.3,
            "attribute_comparison": 80.8,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 91.5,
            "function_reasoning": 91.5,
            "future_prediction": 79.2,
            "identity_reasoning": 97.6,
            "image_emotion": 73.5,
            "image_quality": 77.6,
            "image_scene": 93.8,
            "image_style": 80.0,
            "image_topic": 96.5,
            "nature_relation": 92.6,
            "object_localization": 82.7,
            "ocr": 100.0,
            "physical_property_reasoning": 69.0,
            "physical_relation": 57.7,
            "social_relation": 84.6,
            "spatial_relationship": 71.6,
            "structuralized_imagetext_understanding": 81.2,
            "Method": [
                "grok-2-vision-1212",
                "https://docs.x.ai/docs/overview"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "xAI",
            "Time": "2025/03/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "grok-2-vision-1212",
            "key": 468
        },
        {
            "Overall": 84.1,
            "AR": 87.5,
            "CP": 88.4,
            "FP-C": 77.3,
            "FP-S": 87.7,
            "LR": 71.1,
            "RR": 82.0,
            "action_recognition": 93.2,
            "attribute_comparison": 88.5,
            "attribute_recognition": 97.0,
            "celebrity_recognition": 87.3,
            "function_reasoning": 90.6,
            "future_prediction": 75.0,
            "identity_reasoning": 97.6,
            "image_emotion": 74.7,
            "image_quality": 85.9,
            "image_scene": 93.8,
            "image_style": 87.1,
            "image_topic": 97.6,
            "nature_relation": 85.2,
            "object_localization": 74.0,
            "ocr": 94.8,
            "physical_property_reasoning": 76.0,
            "physical_relation": 71.2,
            "social_relation": 85.9,
            "spatial_relationship": 49.4,
            "structuralized_imagetext_understanding": 68.3,
            "Method": [
                "DeepSeek-VL2",
                "https://huggingface.co/deepseek-ai/deepseek-vl2"
            ],
            "Parameters": "27.5B",
            "Language Model": "DeepSeekMoE-27B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2",
            "key": 469
        },
        {
            "Overall": 71.4,
            "AR": 79.2,
            "CP": 80.5,
            "FP-C": 61.5,
            "FP-S": 73.4,
            "LR": 53.2,
            "RR": 63.5,
            "action_recognition": 93.2,
            "attribute_comparison": 52.6,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 72.9,
            "function_reasoning": 82.1,
            "future_prediction": 58.3,
            "identity_reasoning": 93.9,
            "image_emotion": 71.1,
            "image_quality": 65.9,
            "image_scene": 89.9,
            "image_style": 75.3,
            "image_topic": 95.3,
            "nature_relation": 54.3,
            "object_localization": 45.2,
            "ocr": 90.9,
            "physical_property_reasoning": 64.0,
            "physical_relation": 59.6,
            "social_relation": 75.6,
            "spatial_relationship": 35.8,
            "structuralized_imagetext_understanding": 49.5,
            "Method": [
                "SmolVLM2",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct"
            ],
            "Parameters": "2.25B",
            "Language Model": "SmolLM2-1.7M",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2",
            "key": 470
        },
        {
            "Overall": 11.9,
            "AR": 19.4,
            "CP": 16.7,
            "FP-C": 2.4,
            "FP-S": 15.1,
            "LR": 5.2,
            "RR": 1.4,
            "action_recognition": 3.4,
            "attribute_comparison": 3.8,
            "attribute_recognition": 27.3,
            "celebrity_recognition": 5.1,
            "function_reasoning": 10.4,
            "future_prediction": 9.7,
            "identity_reasoning": 30.5,
            "image_emotion": 0.0,
            "image_quality": 5.9,
            "image_scene": 26.4,
            "image_style": 1.2,
            "image_topic": 44.7,
            "nature_relation": 1.2,
            "object_localization": 4.8,
            "ocr": 28.6,
            "physical_property_reasoning": 20.0,
            "physical_relation": 0.0,
            "social_relation": 2.6,
            "spatial_relationship": 0.0,
            "structuralized_imagetext_understanding": 2.0,
            "Method": [
                "SmolVLM2-256M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-256M-Video-Instruct"
            ],
            "Parameters": "0.26B",
            "Language Model": "SmolLM2-135M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2-256M",
            "key": 471
        },
        {
            "Overall": 53.1,
            "AR": 70.1,
            "CP": 63.4,
            "FP-C": 38.9,
            "FP-S": 51.8,
            "LR": 29.5,
            "RR": 46.0,
            "action_recognition": 83.0,
            "attribute_comparison": 17.9,
            "attribute_recognition": 75.8,
            "celebrity_recognition": 35.6,
            "function_reasoning": 71.7,
            "future_prediction": 59.7,
            "identity_reasoning": 90.2,
            "image_emotion": 61.4,
            "image_quality": 4.7,
            "image_scene": 81.4,
            "image_style": 67.1,
            "image_topic": 92.9,
            "nature_relation": 34.6,
            "object_localization": 23.1,
            "ocr": 84.4,
            "physical_property_reasoning": 52.0,
            "physical_relation": 38.5,
            "social_relation": 62.8,
            "spatial_relationship": 11.1,
            "structuralized_imagetext_understanding": 7.9,
            "Method": [
                "SmolVLM2-500M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
            ],
            "Parameters": "0.51B",
            "Language Model": "SmolLM2-360M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2-500M",
            "key": 472
        },
        {
            "Overall": 83.4,
            "AR": 84.0,
            "CP": 87.2,
            "FP-C": 75.7,
            "FP-S": 88.9,
            "LR": 75.7,
            "RR": 79.1,
            "action_recognition": 92.0,
            "attribute_comparison": 83.3,
            "attribute_recognition": 94.9,
            "celebrity_recognition": 87.3,
            "function_reasoning": 91.5,
            "future_prediction": 77.8,
            "identity_reasoning": 92.7,
            "image_emotion": 75.9,
            "image_quality": 81.2,
            "image_scene": 93.8,
            "image_style": 83.5,
            "image_topic": 97.6,
            "nature_relation": 87.7,
            "object_localization": 80.8,
            "ocr": 94.8,
            "physical_property_reasoning": 69.0,
            "physical_relation": 55.8,
            "social_relation": 85.9,
            "spatial_relationship": 50.6,
            "structuralized_imagetext_understanding": 74.3,
            "Method": [
                "Phi-4-MultiModal",
                "https://huggingface.co/microsoft/Phi-4-multimodal-instruct"
            ],
            "Parameters": "5.57B",
            "Language Model": "Phi-4-Mini",
            "Vision Model": "SigLIP-400M",
            "Org": "Microsoft",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Phi-4-Vision",
            "key": 473
        },
        {
            "Overall": 83.9,
            "AR": 82.6,
            "CP": 86.1,
            "FP-C": 78.1,
            "FP-S": 89.4,
            "LR": 76.3,
            "RR": 82.9,
            "action_recognition": 94.3,
            "attribute_comparison": 85.9,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 83.9,
            "function_reasoning": 85.8,
            "future_prediction": 81.9,
            "identity_reasoning": 97.6,
            "image_emotion": 79.5,
            "image_quality": 81.2,
            "image_scene": 92.2,
            "image_style": 76.5,
            "image_topic": 97.6,
            "nature_relation": 84.0,
            "object_localization": 83.7,
            "ocr": 97.4,
            "physical_property_reasoning": 67.0,
            "physical_relation": 67.3,
            "social_relation": 92.3,
            "spatial_relationship": 53.1,
            "structuralized_imagetext_understanding": 72.3,
            "Method": [
                "MUG-U-7B",
                "https://github.com/Shopee-MUG/MUG-U"
            ],
            "Parameters": "7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Shopee",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MUG-U-7B",
            "key": 474
        },
        {
            "Overall": 69.6,
            "AR": 78.1,
            "CP": 79.4,
            "FP-C": 56.3,
            "FP-S": 67.1,
            "LR": 53.8,
            "RR": 69.7,
            "action_recognition": 94.3,
            "attribute_comparison": 43.6,
            "attribute_recognition": 83.8,
            "celebrity_recognition": 79.7,
            "function_reasoning": 84.0,
            "future_prediction": 73.6,
            "identity_reasoning": 95.1,
            "image_emotion": 74.7,
            "image_quality": 54.1,
            "image_scene": 89.1,
            "image_style": 77.6,
            "image_topic": 96.5,
            "nature_relation": 66.7,
            "object_localization": 17.3,
            "ocr": 93.5,
            "physical_property_reasoning": 58.0,
            "physical_relation": 40.4,
            "social_relation": 92.3,
            "spatial_relationship": 27.2,
            "structuralized_imagetext_understanding": 39.6,
            "Method": [
                "Gemma3-4B",
                "https://huggingface.co/google/gemma-3-4b-it"
            ],
            "Parameters": "4.3B",
            "Language Model": "Gemma3-4B",
            "Vision Model": "SigLIP-400M",
            "Org": "Google",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Gemma3-4B",
            "key": 475
        },
        {
            "Overall": 77.5,
            "AR": 80.6,
            "CP": 82.2,
            "FP-C": 70.4,
            "FP-S": 80.9,
            "LR": 70.5,
            "RR": 70.6,
            "action_recognition": 93.2,
            "attribute_comparison": 69.2,
            "attribute_recognition": 88.9,
            "celebrity_recognition": 88.1,
            "function_reasoning": 87.7,
            "future_prediction": 75.0,
            "identity_reasoning": 93.9,
            "image_emotion": 69.9,
            "image_quality": 71.8,
            "image_scene": 89.9,
            "image_style": 77.6,
            "image_topic": 97.6,
            "nature_relation": 81.5,
            "object_localization": 53.8,
            "ocr": 96.1,
            "physical_property_reasoning": 62.0,
            "physical_relation": 46.2,
            "social_relation": 75.6,
            "spatial_relationship": 46.9,
            "structuralized_imagetext_understanding": 67.3,
            "Method": [
                "Gemma3-12B",
                "https://huggingface.co/google/gemma-3-12b-it"
            ],
            "Parameters": "12.2B",
            "Language Model": "Gemma3-12B",
            "Vision Model": "SigLIP-400M",
            "Org": "Google",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Gemma3-12B",
            "key": 476
        },
        {
            "Overall": 68.8,
            "AR": 78.1,
            "CP": 77.1,
            "FP-C": 56.3,
            "FP-S": 70.4,
            "LR": 40.5,
            "RR": 73.0,
            "action_recognition": 92.0,
            "attribute_comparison": 38.5,
            "attribute_recognition": 88.9,
            "celebrity_recognition": 74.6,
            "function_reasoning": 83.0,
            "future_prediction": 61.1,
            "identity_reasoning": 97.6,
            "image_emotion": 79.5,
            "image_quality": 30.6,
            "image_scene": 92.2,
            "image_style": 77.6,
            "image_topic": 97.6,
            "nature_relation": 76.5,
            "object_localization": 38.5,
            "ocr": 83.1,
            "physical_property_reasoning": 57.0,
            "physical_relation": 55.8,
            "social_relation": 80.8,
            "spatial_relationship": 34.6,
            "structuralized_imagetext_understanding": 25.7,
            "Method": [
                "AKI-4B",
                "https://huggingface.co/Sony/AKI-4B-phi-3.5-mini"
            ],
            "Parameters": "4.33B",
            "Language Model": "Phi-3.5",
            "Vision Model": "SigLIP-400M",
            "Org": "Sony",
            "Time": "2025/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "AKI",
            "key": 478
        },
        {
            "Overall": 82.1,
            "AR": 85.1,
            "CP": 84.4,
            "FP-C": 73.3,
            "FP-S": 89.4,
            "LR": 69.9,
            "RR": 79.6,
            "action_recognition": 92.0,
            "attribute_comparison": 85.9,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 89.0,
            "function_reasoning": 90.6,
            "future_prediction": 70.8,
            "identity_reasoning": 97.6,
            "image_emotion": 73.5,
            "image_quality": 80.0,
            "image_scene": 93.0,
            "image_style": 74.1,
            "image_topic": 96.5,
            "nature_relation": 77.8,
            "object_localization": 80.8,
            "ocr": 96.1,
            "physical_property_reasoning": 69.0,
            "physical_relation": 73.1,
            "social_relation": 85.9,
            "spatial_relationship": 40.7,
            "structuralized_imagetext_understanding": 69.3,
            "Method": [
                "Kimi-VL-A3B-Instruct",
                "https://huggingface.co/moonshotai/Kimi-VL-A3B-Instruct"
            ],
            "Parameters": "16.4B",
            "Language Model": "Moonlight-16B-A3B",
            "Vision Model": "MoonViT",
            "Org": "moonshot.ai",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kimi-VL-A3B-Instruct",
            "key": 483
        },
        {
            "Overall": 72.3,
            "AR": 76.4,
            "CP": 82.4,
            "FP-C": 58.7,
            "FP-S": 78.1,
            "LR": 50.3,
            "RR": 66.8,
            "action_recognition": 93.2,
            "attribute_comparison": 51.3,
            "attribute_recognition": 91.9,
            "celebrity_recognition": 72.0,
            "function_reasoning": 76.4,
            "future_prediction": 61.1,
            "identity_reasoning": 93.9,
            "image_emotion": 77.1,
            "image_quality": 71.8,
            "image_scene": 89.9,
            "image_style": 71.8,
            "image_topic": 97.6,
            "nature_relation": 54.3,
            "object_localization": 62.5,
            "ocr": 90.9,
            "physical_property_reasoning": 62.0,
            "physical_relation": 57.7,
            "social_relation": 85.9,
            "spatial_relationship": 28.4,
            "structuralized_imagetext_understanding": 42.6,
            "Method": [
                "InternVL3-1B",
                "https://huggingface.co/OpenGVLab/InternVL3-1B"
            ],
            "Parameters": "0.94B",
            "Language Model": "Qwen2.5-0.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-1B",
            "key": 484
        },
        {
            "Overall": 80.8,
            "AR": 82.6,
            "CP": 85.0,
            "FP-C": 73.7,
            "FP-S": 83.7,
            "LR": 65.9,
            "RR": 84.4,
            "action_recognition": 94.3,
            "attribute_comparison": 84.6,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 77.1,
            "function_reasoning": 89.6,
            "future_prediction": 69.4,
            "identity_reasoning": 97.6,
            "image_emotion": 72.3,
            "image_quality": 76.5,
            "image_scene": 93.0,
            "image_style": 81.2,
            "image_topic": 97.6,
            "nature_relation": 87.7,
            "object_localization": 73.1,
            "ocr": 94.8,
            "physical_property_reasoning": 63.0,
            "physical_relation": 67.3,
            "social_relation": 92.3,
            "spatial_relationship": 40.7,
            "structuralized_imagetext_understanding": 63.4,
            "Method": [
                "InternVL3-2B",
                "https://huggingface.co/OpenGVLab/InternVL3-2B"
            ],
            "Parameters": "2.09B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-2B",
            "key": 485
        },
        {
            "Overall": 83.6,
            "AR": 83.3,
            "CP": 86.3,
            "FP-C": 79.4,
            "FP-S": 88.2,
            "LR": 73.4,
            "RR": 82.5,
            "action_recognition": 95.5,
            "attribute_comparison": 84.6,
            "attribute_recognition": 94.9,
            "celebrity_recognition": 84.7,
            "function_reasoning": 85.8,
            "future_prediction": 75.0,
            "identity_reasoning": 98.8,
            "image_emotion": 75.9,
            "image_quality": 81.2,
            "image_scene": 90.7,
            "image_style": 82.4,
            "image_topic": 98.8,
            "nature_relation": 85.2,
            "object_localization": 79.8,
            "ocr": 96.1,
            "physical_property_reasoning": 68.0,
            "physical_relation": 73.1,
            "social_relation": 85.9,
            "spatial_relationship": 56.8,
            "structuralized_imagetext_understanding": 72.3,
            "Method": [
                "InternVL3-8B",
                "https://huggingface.co/OpenGVLab/InternVL3-8B"
            ],
            "Parameters": "7.94B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-8B",
            "key": 486
        },
        {
            "Overall": 83.9,
            "AR": 80.6,
            "CP": 87.4,
            "FP-C": 81.4,
            "FP-S": 88.2,
            "LR": 75.1,
            "RR": 82.5,
            "action_recognition": 94.3,
            "attribute_comparison": 91.0,
            "attribute_recognition": 97.0,
            "celebrity_recognition": 82.2,
            "function_reasoning": 88.7,
            "future_prediction": 77.8,
            "identity_reasoning": 97.6,
            "image_emotion": 77.1,
            "image_quality": 81.2,
            "image_scene": 94.6,
            "image_style": 82.4,
            "image_topic": 97.6,
            "nature_relation": 87.7,
            "object_localization": 81.7,
            "ocr": 94.8,
            "physical_property_reasoning": 58.0,
            "physical_relation": 65.4,
            "social_relation": 88.5,
            "spatial_relationship": 58.0,
            "structuralized_imagetext_understanding": 73.3,
            "Method": [
                "InternVL3-9B",
                "https://huggingface.co/OpenGVLab/InternVL3-9B"
            ],
            "Parameters": "9.14B",
            "Language Model": "InternLM3-8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-9B",
            "key": 487
        },
        {
            "Overall": 85.7,
            "AR": 85.4,
            "CP": 87.4,
            "FP-C": 81.4,
            "FP-S": 88.7,
            "LR": 83.2,
            "RR": 83.9,
            "action_recognition": 90.9,
            "attribute_comparison": 79.5,
            "attribute_recognition": 93.9,
            "celebrity_recognition": 82.2,
            "function_reasoning": 88.7,
            "future_prediction": 79.2,
            "identity_reasoning": 97.6,
            "image_emotion": 73.5,
            "image_quality": 81.2,
            "image_scene": 93.8,
            "image_style": 87.1,
            "image_topic": 97.6,
            "nature_relation": 86.4,
            "object_localization": 84.6,
            "ocr": 97.4,
            "physical_property_reasoning": 72.0,
            "physical_relation": 73.1,
            "social_relation": 88.5,
            "spatial_relationship": 72.8,
            "structuralized_imagetext_understanding": 86.1,
            "Method": [
                "InternVL3-14B",
                "https://huggingface.co/OpenGVLab/InternVL3-14B"
            ],
            "Parameters": "15.1B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-14B",
            "key": 488
        },
        {
            "Overall": 87.7,
            "AR": 85.4,
            "CP": 87.2,
            "FP-C": 85.8,
            "FP-S": 93.5,
            "LR": 85.5,
            "RR": 84.8,
            "action_recognition": 95.5,
            "attribute_comparison": 87.2,
            "attribute_recognition": 97.0,
            "celebrity_recognition": 91.5,
            "function_reasoning": 89.6,
            "future_prediction": 81.9,
            "identity_reasoning": 96.3,
            "image_emotion": 75.9,
            "image_quality": 81.2,
            "image_scene": 92.2,
            "image_style": 85.9,
            "image_topic": 97.6,
            "nature_relation": 87.7,
            "object_localization": 89.4,
            "ocr": 97.4,
            "physical_property_reasoning": 72.0,
            "physical_relation": 71.2,
            "social_relation": 91.0,
            "spatial_relationship": 74.1,
            "structuralized_imagetext_understanding": 88.1,
            "Method": [
                "InternVL3-38B",
                "https://huggingface.co/OpenGVLab/InternVL3-38B"
            ],
            "Parameters": "38.4B",
            "Language Model": "Qwen2.5-32B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-38B",
            "key": 489
        },
        {
            "Overall": 88.8,
            "AR": 86.1,
            "CP": 87.4,
            "FP-C": 89.5,
            "FP-S": 93.5,
            "LR": 83.8,
            "RR": 90.0,
            "action_recognition": 94.3,
            "attribute_comparison": 89.7,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 91.5,
            "function_reasoning": 90.6,
            "future_prediction": 81.9,
            "identity_reasoning": 98.8,
            "image_emotion": 77.1,
            "image_quality": 82.4,
            "image_scene": 93.8,
            "image_style": 83.5,
            "image_topic": 96.5,
            "nature_relation": 92.6,
            "object_localization": 89.4,
            "ocr": 98.7,
            "physical_property_reasoning": 71.0,
            "physical_relation": 78.8,
            "social_relation": 94.9,
            "spatial_relationship": 84.0,
            "structuralized_imagetext_understanding": 85.1,
            "Method": [
                "InternVL3-78B",
                "https://huggingface.co/OpenGVLab/InternVL3-78B"
            ],
            "Parameters": "78.4B",
            "Language Model": "Qwen2.5-72B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-78B",
            "key": 490
        },
        {
            "Overall": 86.9,
            "AR": 88.2,
            "CP": 88.4,
            "FP-C": 87.0,
            "FP-S": 85.2,
            "LR": 90.2,
            "RR": 82.0,
            "action_recognition": 97.7,
            "attribute_comparison": 89.7,
            "attribute_recognition": 91.9,
            "celebrity_recognition": 68.6,
            "function_reasoning": 88.7,
            "future_prediction": 84.7,
            "identity_reasoning": 98.8,
            "image_emotion": 77.1,
            "image_quality": 84.7,
            "image_scene": 93.8,
            "image_style": 85.9,
            "image_topic": 97.6,
            "nature_relation": 93.8,
            "object_localization": 86.5,
            "ocr": 100.0,
            "physical_property_reasoning": 79.0,
            "physical_relation": 61.5,
            "social_relation": 83.3,
            "spatial_relationship": 72.8,
            "structuralized_imagetext_understanding": 94.1,
            "Method": [
                "GPT-4.1-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-2025-04-14",
            "key": 491
        },
        {
            "Overall": 86.9,
            "AR": 84.4,
            "CP": 87.2,
            "FP-C": 87.9,
            "FP-S": 87.9,
            "LR": 89.6,
            "RR": 84.4,
            "action_recognition": 94.3,
            "attribute_comparison": 93.6,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 86.4,
            "function_reasoning": 87.7,
            "future_prediction": 81.9,
            "identity_reasoning": 97.6,
            "image_emotion": 75.9,
            "image_quality": 83.5,
            "image_scene": 91.5,
            "image_style": 85.9,
            "image_topic": 96.5,
            "nature_relation": 90.1,
            "object_localization": 77.9,
            "ocr": 100.0,
            "physical_property_reasoning": 70.0,
            "physical_relation": 71.2,
            "social_relation": 87.2,
            "spatial_relationship": 75.3,
            "structuralized_imagetext_understanding": 95.0,
            "Method": [
                "GPT-4.1-mini-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-mini-2025-04-14",
            "key": 492
        },
        {
            "Overall": 68.2,
            "AR": 77.1,
            "CP": 76.7,
            "FP-C": 60.3,
            "FP-S": 65.1,
            "LR": 61.8,
            "RR": 57.3,
            "action_recognition": 85.2,
            "attribute_comparison": 62.8,
            "attribute_recognition": 83.8,
            "celebrity_recognition": 45.8,
            "function_reasoning": 81.1,
            "future_prediction": 68.1,
            "identity_reasoning": 90.2,
            "image_emotion": 65.1,
            "image_quality": 61.2,
            "image_scene": 88.4,
            "image_style": 70.6,
            "image_topic": 91.8,
            "nature_relation": 51.9,
            "object_localization": 49.0,
            "ocr": 92.2,
            "physical_property_reasoning": 62.0,
            "physical_relation": 44.2,
            "social_relation": 71.8,
            "spatial_relationship": 30.9,
            "structuralized_imagetext_understanding": 57.4,
            "Method": [
                "GPT-4.1-nano-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-nano-2025-04-14",
            "key": 493
        },
        {
            "Overall": 78.1,
            "AR": 80.2,
            "CP": 85.2,
            "FP-C": 69.2,
            "FP-S": 83.2,
            "LR": 63.6,
            "RR": 72.5,
            "action_recognition": 95.5,
            "attribute_comparison": 76.9,
            "attribute_recognition": 96.0,
            "celebrity_recognition": 76.3,
            "function_reasoning": 84.0,
            "future_prediction": 65.3,
            "identity_reasoning": 96.3,
            "image_emotion": 79.5,
            "image_quality": 76.5,
            "image_scene": 92.2,
            "image_style": 76.5,
            "image_topic": 97.6,
            "nature_relation": 66.7,
            "object_localization": 72.1,
            "ocr": 92.2,
            "physical_property_reasoning": 63.0,
            "physical_relation": 61.5,
            "social_relation": 85.9,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 62.4,
            "Method": [
                "granite-vision-3.2-2b",
                "https://huggingface.co/ibm-granite/granite-vision-3.2-2b"
            ],
            "Parameters": "2.98B",
            "Language Model": "granite-3.1-2b-instruct",
            "Vision Model": "SigLip",
            "Org": "IBM",
            "Time": "2025/06/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "granite_vision_3.2_2b",
            "key": 509
        },
        {
            "Overall": 73.5,
            "AR": 76.7,
            "CP": 79.4,
            "FP-C": 66.0,
            "FP-S": 77.4,
            "LR": 58.4,
            "RR": 69.7,
            "action_recognition": 93.2,
            "attribute_comparison": 78.2,
            "attribute_recognition": 90.9,
            "celebrity_recognition": 66.1,
            "function_reasoning": 80.2,
            "future_prediction": 62.5,
            "identity_reasoning": 97.6,
            "image_emotion": 68.7,
            "image_quality": 62.4,
            "image_scene": 91.5,
            "image_style": 70.6,
            "image_topic": 97.6,
            "nature_relation": 59.3,
            "object_localization": 64.4,
            "ocr": 94.8,
            "physical_property_reasoning": 56.0,
            "physical_relation": 63.5,
            "social_relation": 84.6,
            "spatial_relationship": 24.7,
            "structuralized_imagetext_understanding": 55.4,
            "Method": [
                "granite-vision-3.3-2b",
                "https://huggingface.co/ibm-granite/granite-vision-3.3-2b"
            ],
            "Parameters": "2.98B",
            "Language Model": "granite-3.1-2b-instruct",
            "Vision Model": "SigLIP2-400M",
            "Org": "IBM",
            "Time": "2025/06/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "granite_vision_3.3_2b",
            "key": 510
        }
    ],
    "META_MAP": {
        "yuntiantianshu-3.0V": {
            "Method": [
                "yuntiantianshu-3.0V",
                "https://www.intellif.com/"
            ],
            "Parameters": "",
            "Language Model": "tianshu-v3",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "yuntianlifei",
            "Time": "2024/05/13",
            "Verified": "No",
            "OpenSource": "No",
            "key": 259
        },
        "InternVL-Chat-V1.2-Plus": {
            "Method": [
                "InternVL-Chat-V1.2-Plus",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "40B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/03/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 196
        },
        "GPT-4o (0513, detail-high)": {
            "Method": [
                "GPT-4o (0513, detail-high)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 270,
            "dir_name": "GPT4o_HIGH"
        },
        "GPT-4o (0513, detail-low)": {
            "Method": [
                "GPT-4o (0513, detail-low)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 260,
            "dir_name": "GPT4o"
        },
        "Qwen-VL-Plus Base": {
            "Method": [
                "Qwen-VL-Plus Base",
                "https://github.com/QwenLM/Qwen-VL?tab=readme-ov-file#qwen-vl-plus"
            ],
            "Parameters": "",
            "Language Model": "QwenLM",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2023/12/15",
            "OpenSource": "No",
            "Verified": "No",
            "key": 54
        },
        "Skywork-VL": {
            "Method": [
                "Skywork-VL",
                "https://github.com/SkyworkAI/Skywork"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Skywork AI",
            "Time": "2024/05/31",
            "Verified": "No",
            "OpenSource": "No",
            "key": 272
        },
        "InternVL-Chat-V1.2": {
            "Method": [
                "InternVL-Chat-V1.2",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "40B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/02/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 195
        },
        "InternVL-Chat-V1.5": {
            "Method": [
                "InternVL-Chat-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/04/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 241,
            "dir_name": "InternVL-Chat-V1-5"
        },
        "TransCore-M": {
            "Method": [
                "TransCore-M",
                "https://github.com/PCIResearch/TransCore-M"
            ],
            "Parameters": "13.4B",
            "Language Model": "PCITransGPT-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "PCI Research",
            "Time": "2024/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 236,
            "dir_name": "TransCore_M"
        },
        "GLM-4v": {
            "Method": [
                "GLM-4v",
                "https://open.bigmodel.cn/dev/api#glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2024/05/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 263,
            "dir_name": "GLM4V"
        },
        "Weitu-VL-1.0": {
            "Method": [
                "Weitu-VL-1.0",
                ""
            ],
            "Parameters": "15B",
            "Vision Model": "",
            "Language Model": "",
            "Org": "Weitu AI",
            "Time": "2024/04/03",
            "Verified": "No",
            "OpenSource": "No",
            "key": 223
        },
        "LLaVA-Next-Yi-34B": {
            "Method": [
                "LLaVA-Next-Yi-34B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "34.8B",
            "Language Model": "Yi-34B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 213,
            "dir_name": "llava_next_yi_34b"
        },
        "GPT-4v (0409, detail-high)": {
            "Method": [
                "GPT-4v (0409, detail-high)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 246,
            "dir_name": "GPT4V_20240409_HIGH"
        },
        "GPT-4v (0409, detail-low)": {
            "Method": [
                "GPT-4v (0409, detail-low)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 244,
            "dir_name": "GPT4V_20240409"
        },
        "InternLM-XComposer2": {
            "Method": [
                "InternLM-XComposer2",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 132,
            "dir_name": "XComposer2"
        },
        "InternLM-XComposer2-4KHD": {
            "Method": [
                "InternLM-XComposer2-4KHD",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 276,
            "dir_name": "XComposer2_4KHD"
        },
        "WeMM": {
            "Method": [
                "WeMM",
                "https://github.com/scenarios/WeMM/tree/main"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "WechatCV",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 273,
            "dir_name": "WeMM"
        },
        "360VL-70B": {
            "Method": [
                "360VL-70B",
                "https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5"
            ],
            "Parameters": "70B",
            "Language Model": "Llama-3-70B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "QiHoo360",
            "Time": "2024/05/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 264,
            "dir_name": "360VL-70B"
        },
        "Marco-VL-Plus": {
            "Method": [
                "Marco-VL-Plus",
                ""
            ],
            "Parameters": "",
            "Vision Model": "CLIP ViT-L/14",
            "Language Model": "Marco-Chat",
            "Org": "Alibaba",
            "Time": "2024/04/09",
            "Verified": "No",
            "OpenSource": "No",
            "key": 224
        },
        "Marco-VL-34B": {
            "Method": [
                "Marco-VL-34B",
                ""
            ],
            "Parameters": "34.2B",
            "Language Model": "Marco-Chat-34B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Alibaba",
            "Time": "2023/12/14",
            "OpenSource": "No",
            "Verified": "No",
            "key": 48
        },
        "MiniCPM-Llama3-V2.5": {
            "Method": [
                "MiniCPM-Llama3-V2.5",
                "https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "OpenBMB",
            "Time": "2024/05/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 265,
            "dir_name": "MiniCPM-Llama3-V-2_5"
        },
        "Qwen-VL-Max": {
            "Method": [
                "Qwen-VL-Max",
                "https://huggingface.co/spaces/Qwen/Qwen-VL-Max"
            ],
            "Parameters": "",
            "Language Model": "QwenLM",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 136,
            "dir_name": "QwenVLMax"
        },
        "EmbodiedGPT": {
            "Method": [
                "EmbodiedGPT",
                "https://github.com/OpenGVLab/EmbodiedGPT"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-7B",
            "Vision Model": "EVA-G",
            "Org": "The University of Hong Kong",
            "Time": "2024/02/06",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 139
        },
        "AntGMM-Chat": {
            "Method": [
                "AntGMM-Chat",
                ""
            ],
            "Parameters": "8B",
            "Language Model": "Llama-2-7B-ZH",
            "Vision Model": "AntGMM-Encoder-1B",
            "Org": "Ant Group",
            "Time": "2023/11/30",
            "Verified": "No",
            "OpenSource": "No",
            "key": 39
        },
        "GPT-4v (1106, detail-low)": {
            "Method": [
                "GPT-4v (1106, detail-low)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2023/12/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 242,
            "dir_name": "GPT4V"
        },
        "RekaFlash": {
            "Method": [
                "RekaFlash",
                "https://www.reka.ai"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Reka AI",
            "Time": "2024/05/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 262,
            "dir_name": "RekaFlash"
        },
        "Bumblebee-14B": {
            "Method": [
                "Bumblebee-14B",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "14B",
            "Language Model": "Qwen2-14B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Monolith Foundation",
            "Time": "2024/04/26",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 249
        },
        "BlackSwan": {
            "Method": [
                "BlackSwan",
                ""
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "China Mobile (Suzhou) Software Technology Co., Ltd.",
            "Time": "2024/03/24",
            "Verified": "No",
            "OpenSource": "No",
            "key": 221
        },
        "Pink": {
            "Method": [
                "Pink",
                "https://github.com/SY-Xuan/Pink"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Peking University, Ant Group",
            "Time": "2023/10/16",
            "key": 28,
            "Verified": "No",
            "OpenSource": "No"
        },
        "IDEFICS2-8B": {
            "Method": [
                "IDEFICS2-8B",
                "https://huggingface.co/HuggingFaceM4/idefics2-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Mistral-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Hugging Face",
            "Time": "2024/04/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 248,
            "dir_name": "idefics2_8b"
        },
        "PureMM": {
            "Method": [
                "PureMM",
                "https://github.com/Q-MM/PureMM"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Tencent",
            "Time": "2024/01/16",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 116
        },
        "XVERSE-V-13B": {
            "Method": [
                "XVERSE-V-13B",
                "https://github.com/xverse-ai/XVERSE-V-13B"
            ],
            "Parameters": "13B",
            "Language Model": "XVERSE-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "XVERSE",
            "Time": "2024/05/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 256,
            "dir_name": "VXVERSE"
        },
        "AllSeeing-v2": {
            "Method": [
                "AllSeeing-v2",
                "https://github.com/OpenGVLab/all-seeing"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/03/19",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 198
        },
        "LLaVA-InternLM2-20B (QLoRA)": {
            "Method": [
                "LLaVA-InternLM2-20B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "20.2B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 92,
            "dir_name": "llava-internlm2-20b"
        },
        "InternVL-Chat-V1.1": {
            "Method": [
                "InternVL-Chat-V1.1",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "19B",
            "Language Model": "Llama-2-13B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/03/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 194
        },
        "Kanva-14B": {
            "Method": [
                "Kanva-14B",
                "https://github.com/llp1992/Kanva"
            ],
            "Parameters": "14.2B",
            "Language Model": "Qwen-14B",
            "Vision Model": "EVA-CLIP-L/336",
            "Org": "KaLM",
            "Time": "2023/11/24",
            "Verified": "No",
            "OpenSource": "No",
            "key": 38
        },
        "InternLM-XComposer": {
            "key": 22,
            "Method": [
                "InternLM-XComposer",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM-7B",
            "Vision Model": "EVA-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/9/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "XComposer"
        },
        "HoneyBee": {
            "Method": [
                "HoneyBee",
                "https://github.com/kakaobrain/honeybee"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Kakao Brain",
            "Time": "2024/01/15",
            "OpenSource": "Yes",
            "Verified": "No",
            "key": 81
        },
        "CogVLM2-19B-Chat": {
            "Method": [
                "CogVLM2-19B-Chat",
                "https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B"
            ],
            "Parameters": "19B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "EVA2-CLIP-E",
            "Org": "Zhipu AI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 269,
            "dir_name": "cogvlm2-llama3-chat-19B"
        },
        "DeepSeek-VL-7B": {
            "Method": [
                "DeepSeek-VL-7B",
                "https://github.com/deepseek-ai/DeepSeek-VL"
            ],
            "Parameters": "7.3B",
            "Language Model": "DeekSeek-7B",
            "Vision Model": "SAM-B\nSigLIP-L",
            "Org": "DeepSeek",
            "Time": "2024/03/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 202,
            "dir_name": "deepseek_vl_7b"
        },
        "mPLUG-Owl2.1": {
            "Method": [
                "mPLUG-Owl2.1",
                ""
            ],
            "Parameters": "9.8B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-G/16",
            "Org": "Alibaba",
            "Time": "2024/01/26",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 113
        },
        "Phi-3-Vision": {
            "Method": [
                "Phi-3-Vision",
                "https://huggingface.co/microsoft/Phi-3-vision-128k-instruct"
            ],
            "Parameters": "4.2B",
            "Language Model": "Phi-3",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Microsoft",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 268,
            "dir_name": "Phi-3-Vision"
        },
        "Gemini-1.0-Pro": {
            "Method": [
                "Gemini-1.0-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2023/12/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 101,
            "dir_name": "GeminiPro1-0"
        },
        "LLaVA-InternLM2-7B (QLoRA)": {
            "Method": [
                "LLaVA-InternLM2-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "8.1B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 91,
            "dir_name": "llava-internlm2-7b"
        },
        "Marco-VL-13B": {
            "Method": [
                "Marco-VL-13B",
                ""
            ],
            "Parameters": "13.2B",
            "Language Model": "Marco-Chat-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Alibaba",
            "Time": "2023/12/14",
            "OpenSource": "No",
            "Verified": "No",
            "key": 47
        },
        "InternLM-XComposer2-1.8B": {
            "Method": [
                "InternLM-XComposer2-1.8B",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 275,
            "dir_name": "XComposer2_1.8b"
        },
        "Marco-VL-6B": {
            "Method": [
                "Marco-VL-6B",
                ""
            ],
            "Parameters": "6.2B",
            "Language Model": "Marco-Chat-6B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Alibaba",
            "Time": "2023/12/14",
            "OpenSource": "No",
            "Verified": "No",
            "key": 46
        },
        "Yi-VL-34B": {
            "Method": [
                "Yi-VL-34B",
                "https://huggingface.co/01-ai/Yi-VL-34B"
            ],
            "Parameters": "34.6B",
            "Language Model": "Yi-34B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "01-AI",
            "Time": "2024/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 190,
            "dir_name": "Yi_VL_34B"
        },
        "Monkey-Chat": {
            "Method": [
                "Monkey-Chat",
                "https://github.com/Yuliang-Liu/Monkey"
            ],
            "Parameters": "9.8B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-BigHuge",
            "Org": "Huazhong University of Science and Technology",
            "Time": "2024/01/16",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 97,
            "dir_name": "monkey-chat"
        },
        "Bumblebee-7B": {
            "Method": [
                "Bumblebee-7B",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen-1.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Monolith Foundation",
            "Time": "2024/05/07",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 250
        },
        "JiuTian": {
            "key": 13,
            "Method": [
                "JiuTian",
                "https://github.com/rshaojimmy/JiuTian"
            ],
            "Parameters": "12.3B",
            "Language Model": "FLANT5-XXL",
            "Vision Model": "EVA-G",
            "Org": "HIT-Ruoyu",
            "Time": "2023/9/6",
            "Verified": "No",
            "OpenSource": "No"
        },
        "LLaVA-LLaMA-3-8B": {
            "Method": [
                "LLaVA-LLaMA-3-8B",
                "https://huggingface.co/xtuner/llava-llama-3-8b-v1_1"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/05/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 254,
            "dir_name": "llava-llama-3-8b"
        },
        "OmniLMM-12B": {
            "Method": [
                "OmniLMM-12B",
                "https://huggingface.co/openbmb/OmniLMM-12B"
            ],
            "Parameters": "12B",
            "Language Model": "Zephyr-7B-β",
            "Vision Model": "EVA-02-5B",
            "Org": "OpenBMB",
            "Time": "2024/02/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 145,
            "dir_name": "OmniLMM_12B"
        },
        "RBDash-v1-13B": {
            "Method": [
                "RBDash-v1-13B",
                "https://huggingface.co/RBDash-Team/rbdash-v1-13b/tree/main"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "RBDash Team",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "No",
            "key": 73
        },
        "PaliGemma-3B-mix-448": {
            "Method": [
                "PaliGemma-3B-mix-448",
                "https://github.com/google-research/big_vision/blob/main/big_vision/configs/proj/paligemma/README.md"
            ],
            "Parameters": "3B",
            "Language Model": "Gemma-2B",
            "Vision Model": "SigLIP-400M",
            "Org": "Google",
            "Time": "2024/05/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 261,
            "dir_name": "paligemma-3b-mix-448"
        },
        "Sphinx-V2": {
            "Method": [
                "Sphinx-V2",
                "https://github.com/Alpha-VLLM/LLaMA2-Accessory/tree/main/SPHINX"
            ],
            "Parameters": "16.5B",
            "Language Model": "Llama-2-13B",
            "Vision Model": "CLIP ViT-L/14\nCLIP ConvNeXT\nConvNeXT-XXLarge\nDinov2-VIT-G/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/11/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 34
        },
        "CatVision": {
            "Method": [
                "CatVision",
                ""
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "4paradigm.Inc",
            "Time": "2024/01/23",
            "Verified": "No",
            "OpenSource": "No",
            "key": 103
        },
        "Prompt Highlighter": {
            "Method": [
                "Prompt Highlighter",
                "https://github.com/dvlab-research/Prompt-Highlighter"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "The Chinese University of Hong Kong",
            "Time": "2023/12/11",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 45
        },
        "LLaVA-Next-Vicuna-13B": {
            "Method": [
                "LLaVA-Next-Vicuna-13B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 212,
            "dir_name": "llava_next_vicuna_13b"
        },
        "ShareGPT4V-13B": {
            "Method": [
                "ShareGPT4V-13B",
                "https://sharegpt4v.github.io"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 185,
            "dir_name": "sharegpt4v_13b"
        },
        "LLaVA-Next-Mistral-7B": {
            "Method": [
                "LLaVA-Next-Mistral-7B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "7.6B",
            "Language Model": "Mistral-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 211,
            "dir_name": "llava_next_mistral_7b"
        },
        "LLaVA-Next-Vicuna-7B": {
            "Method": [
                "LLaVA-Next-Vicuna-7B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "7.1B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 210,
            "dir_name": "llava_next_vicuna_7b"
        },
        "LLaVA-v1.5-13B": {
            "Method": [
                "LLaVA-v1.5-13B",
                "https://arxiv.org/abs/2310.03744"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2023/10/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 188,
            "dir_name": "llava_v1.5_13b"
        },
        "Bunny-3B": {
            "Method": [
                "Bunny-3B",
                "https://github.com/BAAI-DCAI/Bunny"
            ],
            "Parameters": "3B",
            "Language Model": "Phi-2",
            "Vision Model": "SigLIP-400M",
            "Org": "Beijing Academy of Artificial Intelligence",
            "Time": "2024/02/13",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 155
        },
        "EasyGen": {
            "Method": [
                "EasyGen",
                "https://github.com/zxy556677/EasyGen"
            ],
            "Parameters": "14.5B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14\nUniDiffuser",
            "Org": "The Hong Kong Polytechnic University",
            "Time": "2023/12/14",
            "OpenSource": "Yes",
            "Verified": "No",
            "key": 49
        },
        "MiniCPM-V-2": {
            "Method": [
                "MiniCPM-V-2",
                "https://huggingface.co/openbmb/MiniCPM-V-2"
            ],
            "Parameters": "2.8B",
            "Vision Model": "SigLIP-400M",
            "Language Model": "MiniCPM-2.4B",
            "Org": "OpenBMB",
            "Time": "2024/04/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 231,
            "dir_name": "MiniCPM-V-2"
        },
        "LLaVA-InternLM-7B (QLoRA)": {
            "Method": [
                "LLaVA-InternLM-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "7.6B",
            "Language Model": "InternLM-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 70,
            "dir_name": "llava-internlm-7b"
        },
        "StableLLaVA-13B": {
            "Method": [
                "StableLLaVA-13B",
                "https://github.com/icoz69/StableLLAVA"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Tencent",
            "Time": "2023/12/22",
            "OpenSource": "Yes",
            "Verified": "No",
            "key": 55
        },
        "LLaVA-v1.5-13B (QLoRA)": {
            "Method": [
                "LLaVA-v1.5-13B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 72,
            "dir_name": "llava-v1.5-13b-xtuner"
        },
        "CodeFuse-VLM": {
            "Method": [
                "CodeFuse-VLM",
                "https://huggingface.co/codefuse-ai/CodeFuse-VLM-14B"
            ],
            "Parameters": "14B",
            "Language Model": "Qwen-14B",
            "Vision Model": "Qwen-VL Vision Encoder",
            "Org": "Ant Group",
            "Time": "2024/01/29",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 129
        },
        "Yi-VL-6B": {
            "Method": [
                "Yi-VL-6B",
                "https://huggingface.co/01-ai/Yi-VL-6B"
            ],
            "Parameters": "6.6B",
            "Language Model": "Yi-6B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "01-AI",
            "Time": "2024/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 189,
            "dir_name": "Yi_VL_6B"
        },
        "Claude3-Sonnet": {
            "Method": [
                "Claude3-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 218,
            "dir_name": "Claude3V_Sonnet"
        },
        "LLaVA-v1.5-7B (QLoRA)": {
            "Method": [
                "LLaVA-v1.5-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 71,
            "dir_name": "llava-v1.5-7b-xtuner"
        },
        "Kanva-7B": {
            "Method": [
                "Kanva-7B",
                "https://github.com/llp1992/Kanva"
            ],
            "Parameters": "7.2B",
            "Language Model": "Baichuan2-7B",
            "Vision Model": "EVA-CLIP-L/336",
            "Org": "KaLM",
            "Time": "2023/11/21",
            "Verified": "No",
            "OpenSource": "No",
            "key": 37
        },
        "ShareGPT4V-7B": {
            "Method": [
                "ShareGPT4V-7B",
                "https://sharegpt4v.github.io"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 184,
            "dir_name": "sharegpt4v_7b"
        },
        "Sphinx": {
            "Method": [
                "Sphinx",
                "https://github.com/Alpha-VLLM/LLaMA2-Accessory/tree/main/SPHINX"
            ],
            "Parameters": "16.5B",
            "Language Model": "Llama-2-13B",
            "Vision Model": "CLIP ViT-L/14\nCLIP ConvNeXT\nConvNeXT-XXLarge\nDinov2-VIT-G/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/10/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 33
        },
        "Qwen-VL-Plus": {
            "Method": [
                "Qwen-VL-Plus",
                "https://github.com/QwenLM/Qwen-VL?tab=readme-ov-file#qwen-vl-plus"
            ],
            "Parameters": "",
            "Language Model": "QwenLM",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/01/10",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 77,
            "dir_name": "QwenVLPlus"
        },
        "ShareCaptioner": {
            "Method": [
                "ShareCaptioner",
                "https://huggingface.co/Lin-Chen/ShareCaptioner/"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM-7B",
            "Vision Model": "EVA-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 245,
            "dir_name": "sharecaptioner"
        },
        "LLaVA-v1.5-7B": {
            "Method": [
                "LLaVA-v1.5-7B",
                "https://arxiv.org/abs/2310.03744"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2023/10/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 186,
            "dir_name": "llava_v1.5_7b"
        },
        "SharedCaptioner": {
            "Method": [
                "SharedCaptioner",
                "https://huggingface.co/Lin-Chen/ShareCaptioner/"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM-7B",
            "Vision Model": "EVA-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/03",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 74
        },
        "RekaEdge": {
            "Method": [
                "RekaEdge",
                "https://www.reka.ai"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Reka AI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 271,
            "dir_name": "RekaEdge"
        },
        "DeepSeek-VL-1.3B": {
            "Method": [
                "DeepSeek-VL-1.3B",
                "https://github.com/deepseek-ai/DeepSeek-VL"
            ],
            "Parameters": "2.0B",
            "Language Model": "DeekSeek-1B",
            "Vision Model": "SAM-B\nSigLIP-L",
            "Org": "DeepSeek",
            "Time": "2024/03/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 201,
            "dir_name": "deepseek_vl_1.3b"
        },
        "mPLUG-Owl2": {
            "Method": [
                "mPLUG-Owl2",
                "https://github.com/X-PLUG/mPLUG-Owl/tree/main/mPLUG-Owl2"
            ],
            "Parameters": "8.2B",
            "Language Model": "Llama-2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "DAMO Academy",
            "Time": "2023/11/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 32,
            "dir_name": "mPLUG-Owl2"
        },
        "CogVLM-17B-Chat": {
            "Method": [
                "CogVLM-17B-Chat",
                "https://huggingface.co/THUDM/cogvlm-chat-hf"
            ],
            "Parameters": "17B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "EVA2-CLIP-E",
            "Org": "Zhipu AI",
            "Time": "2024/01/03",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 75,
            "dir_name": "cogvlm-chat"
        },
        "LLaVA-InternLM2-1.8B": {
            "Method": [
                "LLaVA-InternLM2-1.8B",
                "https://huggingface.co/StarCycle/llava-siglip-internlm2-1_8b-v1"
            ],
            "Parameters": "2.2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "SigLIP-400M",
            "Org": "Exponential Deep Space",
            "Time": "2024/03/10",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 167
        },
        "GPT-4v (1106, detail-high)": {
            "Method": [
                "GPT-4v (1106, detail-high)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/04/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 243,
            "dir_name": "GPT4V_HIGH"
        },
        "MMICL": {
            "key": 14,
            "Method": [
                "MMICL",
                "https://huggingface.co/BleachNick/MMICL-Instructblip-T5-xxl"
            ],
            "Parameters": "12.3B",
            "Language Model": "FLANT5-XXL",
            "Vision Model": "EVA-G",
            "Org": "Peking University",
            "Time": "2023/8/18",
            "Verified": "No",
            "OpenSource": "Yes"
        },
        "MiniCPM-V": {
            "Method": [
                "MiniCPM-V",
                "https://huggingface.co/openbmb/MiniCPM-V"
            ],
            "Parameters": "3B",
            "Language Model": "MiniCPM-2.4B",
            "Vision Model": "SigLIP-400M",
            "Org": "OpenBMB",
            "Time": "2024/02/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 146,
            "dir_name": "MiniCPM-V"
        },
        "LLaVA-DINOv2": {
            "Method": [
                "LLaVA-DINOv2",
                "https://huggingface.co/StarCycle/llava-dinov2-internlm2-7b-v1"
            ],
            "Parameters": "8.1B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "DINOv2 ViT-L/13",
            "Org": "Exponential Deep Space",
            "Time": "2024/02/13",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 152
        },
        "Emu2_chat": {
            "Method": [
                "Emu2_chat",
                "https://github.com/baaivision/Emu/tree/main/Emu2"
            ],
            "Parameters": "37B",
            "Language Model": "Llama-33B",
            "Vision Model": "EVA-02-CLIP-E-plus",
            "Org": "Beijing Academy of Artificial Intelligence",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 86,
            "dir_name": "emu2_chat"
        },
        "Claude3-Opus": {
            "Method": [
                "Claude3-Opus",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 219,
            "dir_name": "Claude3V_Opus"
        },
        "LMEye": {
            "Method": [
                "LMEye",
                "https://arxiv.org/pdf/2305.03701.pdf"
            ],
            "Parameters": "4.4B",
            "Language Model": "FLANT5-XL",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Harbin Institute of Technology",
            "Time": "2023/10/16",
            "key": 29,
            "Verified": "No",
            "OpenSource": "Yes"
        },
        "Qwen-VL-Chat": {
            "key": 24,
            "Method": [
                "Qwen-VL-Chat",
                "https://github.com/QwenLM/Qwen-VL"
            ],
            "Parameters": "9.6B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-G/16",
            "Org": "Alibaba",
            "Time": "2023/8/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "qwen_chat"
        },
        "JiuTian-Tiny": {
            "key": 16,
            "Method": [
                "JiuTian-Tiny",
                "https://github.com/rshaojimmy/JiuTian"
            ],
            "Parameters": "4.1B",
            "Language Model": "FLANT5-XL",
            "Vision Model": "EVA-G",
            "Org": "HIT-Ruoyu",
            "Time": "2023/8/9",
            "Verified": "No",
            "OpenSource": "No"
        },
        "Claude3-Haiku": {
            "Method": [
                "Claude3-Haiku",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 217,
            "dir_name": "Claude3V_Haiku"
        },
        "Shikra": {
            "key": 15,
            "Method": [
                "Shikra",
                "https://arxiv.org/abs/2306.15195"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Sensetime Research",
            "Time": "2023/7/3",
            "Verified": "No",
            "OpenSource": "Yes"
        },
        "Monkey": {
            "Method": [
                "Monkey",
                "https://github.com/Yuliang-Liu/Monkey"
            ],
            "Parameters": "9.8B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-BigHuge",
            "Org": "Huazhong University of Science and Technology",
            "Time": "2024/01/11",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 79,
            "dir_name": "monkey"
        },
        "MMAlaya": {
            "Method": [
                "MMAlaya",
                "https://huggingface.co/DataCanvas/MMAlaya"
            ],
            "Parameters": "7.8B",
            "Language Model": "Alaya-7B-Chat",
            "Vision Model": "EVA-G",
            "Org": "DataCanvas",
            "Time": "2024/01/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 134,
            "dir_name": "MMAlaya"
        },
        "IDEFICS-80B-Instruct": {
            "key": 19,
            "Method": [
                "IDEFICS-80B-Instruct",
                "https://huggingface.co/HuggingFaceM4/idefics-80b-instruct"
            ],
            "Language Model": "Llama-65B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "Hugging Face",
            "Time": "2023/7/25",
            "Parameters": "80B",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "idefics_80b_instruct"
        },
        "Otter-I": {
            "key": 6,
            "Method": [
                "Otter-I",
                "https://arxiv.org/abs/2305.03726"
            ],
            "Parameters": "9B",
            "Language Model": "Llama-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Nanyang Technological University",
            "Time": "2023/6/8",
            "Verified": "No",
            "OpenSource": "Yes"
        },
        "IDEFICS-9B-Instruct": {
            "key": 18,
            "Method": [
                "IDEFICS-9B-Instruct",
                "https://huggingface.co/HuggingFaceM4/idefics-9b-instruct"
            ],
            "Language Model": "Llama-7B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "Hugging Face",
            "Time": "2023/7/25",
            "Parameters": "9B",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "idefics_9b_instruct"
        },
        "LLaVA-v1-7B": {
            "Method": [
                "LLaVA-v1-7B",
                "https://arxiv.org/abs/2304.08485"
            ],
            "Parameters": "7.2B",
            "Language Model": "Llama-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin-Madison",
            "Time": "2023/4/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 187,
            "dir_name": "llava_v1_7b"
        },
        "PandaGPT-13B": {
            "Method": [
                "PandaGPT-13B",
                "https://arxiv.org/abs/2305.16355"
            ],
            "Parameters": "14B",
            "Language Model": "Vicuna-13B",
            "Vision Model": "ImageBind ViT-H/14",
            "Org": "Tencent AI Lab",
            "Time": "2023/5/25",
            "key": 25,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "PandaGPT_13B"
        },
        "G2PT": {
            "key": 10,
            "Method": [
                "G2PT",
                ""
            ],
            "Parameters": "7B",
            "Language Model": "Llama-7B",
            "Vision Model": "ViT-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "",
            "Verified": "No",
            "OpenSource": "No"
        },
        "LLaMA-Adapter-v2": {
            "key": 9,
            "Method": [
                "LLaMA-Adapter-v2",
                "https://arxiv.org/abs/2304.15010"
            ],
            "Parameters": "7.2B",
            "Language Model": "Llama-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/4/28",
            "Verified": "No",
            "OpenSource": "Yes"
        },
        "VisualGLM": {
            "Method": [
                "VisualGLM",
                "https://github.com/THUDM/VisualGLM-6B"
            ],
            "Parameters": "8B",
            "Language Model": "ChatGLM 6B",
            "Vision Model": "EVA-CLIP",
            "Org": "Tsinghua University",
            "Time": "2023/5/17",
            "key": 41,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "VisualGLM_6b"
        },
        "InstructBLIP-7B": {
            "key": 7,
            "Method": [
                "InstructBLIP-7B",
                "https://arxiv.org/abs/2305.06500"
            ],
            "Parameters": "8B",
            "Language Model": "Vicuna-7B",
            "Vision Model": "EVA-G",
            "Org": "Salesforce Research",
            "Time": "2023/5/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "instructblip_7b"
        },
        "Qwen-VL": {
            "key": 23,
            "Method": [
                "Qwen-VL",
                "https://github.com/QwenLM/Qwen-VL"
            ],
            "Parameters": "9.6B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-G/16",
            "Org": "Alibaba",
            "Time": "2023/8/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "qwen_base"
        },
        "LAMM": {
            "key": 17,
            "Method": [
                "LAMM",
                "https://arxiv.org/abs/2306.06687"
            ],
            "Language Model": "Llama-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Parameters": "7.2B",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/8/31",
            "Verified": "No",
            "OpenSource": "Yes"
        },
        "MiniGPT-4-v1-7B": {
            "key": 3,
            "Method": [
                "MiniGPT-4-v1-7B",
                "https://arxiv.org/abs/2304.10592"
            ],
            "Parameters": "8B",
            "Language Model": "Vicuna-7B",
            "Vision Model": "EVA-G",
            "Org": "King Abdullah University of Science and Technology",
            "Time": "2023/4/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MiniGPT-4-v1-7B"
        },
        "MMGPT": {
            "key": 2,
            "Method": [
                "MMGPT",
                "https://arxiv.org/abs/2305.04790"
            ],
            "Parameters": "9B",
            "Language Model": "Llama-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/5/8",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        "MiniGPT-4-v2": {
            "Method": [
                "MiniGPT-4-v2",
                "https://minigpt-v2.github.io"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-2-13B",
            "Vision Model": "EVA-G",
            "Org": "King Abdullah University of Science and Technology",
            "Time": "2023/10/27",
            "key": 31,
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MiniGPT-4-v2"
        },
        "OpenFlamingo v2": {
            "key": 1,
            "Method": [
                "OpenFlamingo v2",
                "https://github.com/mlfoundations/open_flamingo"
            ],
            "Parameters": "9B",
            "Language Model": "MPT 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "The University of Washington",
            "Time": "2023/6/28",
            "Verified": "No",
            "OpenSource": "Yes",
            "dir_name": "flamingov2"
        },
        "OpenFlamingo": {
            "key": 0,
            "Method": [
                "OpenFlamingo",
                "https://github.com/mlfoundations/open_flamingo"
            ],
            "Parameters": "9B",
            "Language Model": "Llama-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "The University of Washington",
            "Time": "2023/3/29",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        "Mini-InternVL-Chat-2B-V1.5": {
            "Method": [
                "Mini-InternVL-Chat-2B-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 277,
            "dir_name": "Mini-InternVL-Chat-2B-V1-5"
        },
        "Mini-InternVL-Chat-4B-V1.5": {
            "Method": [
                "Mini-InternVL-Chat-4B-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 278,
            "dir_name": "Mini-InternVL-Chat-4B-V1-5"
        },
        "Gemini-1.5-Pro": {
            "Method": [
                "Gemini-1.5-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 279,
            "dir_name": "GeminiPro1-5"
        },
        "Bumblebee-7B-v1.5": {
            "Method": [
                "Bumblebee-7B-v1.5",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Monolith Foundation",
            "Time": "2024/06/12",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 280
        },
        "GLM-4v-9B": {
            "Method": [
                "GLM-4v-9B",
                "https://huggingface.co/THUDM/glm-4v-9b"
            ],
            "Parameters": "9B",
            "Language Model": "GLM-4-9B",
            "Vision Model": "EVA-02-5B",
            "Org": "Zhipu AI",
            "Time": "2024/06/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 281,
            "dir_name": "glm-4v-9b"
        },
        "LLaVA-InternLM2-7B (QMoSLoRA)": {
            "Method": [
                "LLaVA-InternLM2-7B (QMoSLoRA)",
                "https://arxiv.org/abs/2406.11909"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "HKU",
            "Time": "2024/06/23",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 283
        },
        "Claude3.5-Sonnet": {
            "Method": [
                "Claude3.5-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/06/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 284,
            "dir_name": "Claude3-5V_Sonnet"
        },
        "CongRong": {
            "Method": [
                "CongRong",
                "https://mllm.cloudwalk.com/web/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "CloudWalk",
            "Time": "2024/06/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 285,
            "dir_name": "CloudWalk"
        },
        "Bumblebee-7B-v1.6": {
            "Method": [
                "Bumblebee-7B-v1.6",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Monolith Foundation",
            "Time": "2024/06/27",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 286
        },
        "bailingMM-Chat": {
            "Method": [
                "bailingMM-Chat",
                "https://github.com/JKBox/bailingMM-Chat"
            ],
            "Parameters": "11B",
            "Language Model": "bailing-10B",
            "Vision Model": "bailingMM-Encoder-1B",
            "Org": "Ant Group",
            "Time": "2024/06/28",
            "Verified": "No",
            "OpenSource": "No",
            "key": 287
        },
        "Llama-3-MixSense": {
            "Method": [
                "Llama-3-MixSense",
                "https://huggingface.co/Zero-Vision/Llama-3-MixSense"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "ZeroVision",
            "Time": "2024/07/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 288
        },
        "InternVL-2.0-Pro": {
            "Method": [
                "InternVL-2.0-Pro",
                "https://huggingface.co/spaces/OpenGVLab/InternVL/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/08",
            "Verified": "Yes",
            "OpenSource": "No",
            "key": 290
        },
        "InternVL2-1B": {
            "Method": [
                "InternVL2-1B",
                "https://huggingface.co/OpenGVLab/InternVL2-1B"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 292,
            "dir_name": "InternVL2-1B"
        },
        "InternVL2-2B": {
            "Method": [
                "InternVL2-2B",
                "https://huggingface.co/OpenGVLab/InternVL2-2B"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 293,
            "dir_name": "InternVL2-2B"
        },
        "InternVL2-4B": {
            "Method": [
                "InternVL2-4B",
                "https://huggingface.co/OpenGVLab/InternVL2-4B"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 294,
            "dir_name": "InternVL2-4B"
        },
        "InternVL2-8B": {
            "Method": [
                "InternVL2-8B",
                "https://huggingface.co/OpenGVLab/InternVL2-8B"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 295,
            "dir_name": "InternVL2-8B"
        },
        "InternVL2-26B": {
            "Method": [
                "InternVL2-26B",
                "https://huggingface.co/OpenGVLab/InternVL2-26B"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 296,
            "dir_name": "InternVL2-26B"
        },
        "InternVL2-40B": {
            "Method": [
                "InternVL2-40B",
                "https://huggingface.co/OpenGVLab/InternVL2-40B"
            ],
            "Parameters": "40B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 297,
            "dir_name": "InternVL2-40B"
        },
        "Cambrian-8B": {
            "Method": [
                "Cambrian-8B",
                "https://huggingface.co/nyu-visionx/cambrian-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "NYU",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 298,
            "dir_name": "cambrian_8b"
        },
        "InternLM-XComposer2.5": {
            "Method": [
                "InternLM-XComposer2.5",
                "https://huggingface.co/internlm/internlm-xcomposer2d5-7b"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 299,
            "dir_name": "XComposer2d5"
        },
        "Bumblebee-7B-v2.0": {
            "Method": [
                "Bumblebee-7B-v2.0",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Monolith Foundation",
            "Time": "2024/07/11",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 300
        },
        "XinYuan-VL": {
            "Method": [
                "XinYuan-VL",
                "https://cece.com"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Cylingo Group",
            "Time": "2024/07/18",
            "Verified": "No",
            "OpenSource": "No",
            "key": 301
        },
        "Cambrian-34B": {
            "Method": [
                "Cambrian-34B",
                "https://huggingface.co/nyu-visionx/cambrian-34b"
            ],
            "Parameters": "34B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "NYU",
            "Time": "2024/07/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 302,
            "dir_name": "cambrian_34b"
        },
        "Bunny-Llama3-8B": {
            "Method": [
                "Bunny-Llama3-8B",
                "https://huggingface.co/BAAI/Bunny-v1_1-Llama-3-8B-V"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "BAAI",
            "Time": "2024/07/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 303,
            "dir_name": "Bunny-llama3-8B"
        },
        "InternVL2-Llama3-76B": {
            "Method": [
                "InternVL2-Llama3-76B",
                "https://huggingface.co/OpenGVLab/InternVL2-Llama3-76B"
            ],
            "Parameters": "76B",
            "Language Model": "Llama-3-70B-Instruct",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 304,
            "dir_name": "InternVL2-76B"
        },
        "GPT-4o-mini (0718, detail-high)": {
            "Method": [
                "GPT-4o-mini (0718, detail-high)",
                "https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/07/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 305,
            "dir_name": "GPT4o_MINI"
        },
        "Ovis1.5-Llama3-8B": {
            "Method": [
                "Ovis1.5-Llama3-8B",
                "https://huggingface.co/AIDC-AI/Ovis1.5-Llama3-8B"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 306,
            "dir_name": "Ovis1.5-Llama3-8B"
        },
        "LLaVA-Next-Llama3": {
            "Method": [
                "LLaVA-Next-Llama3",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "ByteDance",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 307,
            "dir_name": "llava_next_llama3"
        },
        "LLaVA-Next-Interleave-7B-DPO": {
            "Method": [
                "LLaVA-Next-Interleave-7B-DPO",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen-1.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 308,
            "dir_name": "llava_next_interleave_7b_dpo"
        },
        "Chameleon-7B": {
            "Method": [
                "Chameleon-7B",
                "https://huggingface.co/facebook/chameleon-7b"
            ],
            "Parameters": "7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 309,
            "dir_name": "chameleon_7b"
        },
        "Chameleon-30B": {
            "Method": [
                "Chameleon-30B",
                "https://huggingface.co/facebook/chameleon-30b"
            ],
            "Parameters": "30B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 310,
            "dir_name": "chameleon_30b"
        },
        "Cambrian-13B": {
            "Method": [
                "Cambrian-13B",
                "https://huggingface.co/nyu-visionx/cambrian-13b"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "NYU",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 311,
            "dir_name": "cambrian_13b"
        },
        "Yi-Vision": {
            "Method": [
                "Yi-Vision",
                "https://platform.lingyiwanwu.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "01-AI",
            "Time": "2024/08/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 312,
            "dir_name": "Yi-Vision"
        },
        "Ovis1.5-Gemma2-9B": {
            "Method": [
                "Ovis1.5-Gemma2-9B",
                "https://huggingface.co/AIDC-AI/Ovis1.5-Gemma2-9B"
            ],
            "Parameters": "11.4B",
            "Language Model": "Gemma2-9B-It",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/08/04",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 313,
            "dir_name": "Ovis1.5-Gemma2-9B"
        },
        "LLaVA-Next-Interleave-7B": {
            "Method": [
                "LLaVA-Next-Interleave-7B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen-1.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 314,
            "dir_name": "llava_next_interleave_7b"
        },
        "LLaVA-Next-Qwen-32B": {
            "Method": [
                "LLaVA-Next-Qwen-32B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "33B",
            "Language Model": "Qwen-1.5-32B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 315,
            "dir_name": "llava_next_qwen_32b"
        },
        "Mantis-8B-clip-llama3": {
            "Method": [
                "Mantis-8B-clip-llama3",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-clip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 316,
            "dir_name": "Mantis-8B-clip-llama3"
        },
        "Mantis-8B-siglip-llama3": {
            "Method": [
                "Mantis-8B-siglip-llama3",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-siglip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 317,
            "dir_name": "Mantis-8B-siglip-llama3"
        },
        "Mantis-8B-Idefics2": {
            "Method": [
                "Mantis-8B-Idefics2",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-Idefics2"
            ],
            "Parameters": "8B",
            "Language Model": "Mistral-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 318,
            "dir_name": "Mantis-8B-Idefics2"
        },
        "MiniCPM-V-2.6": {
            "Method": [
                "MiniCPM-V-2.6",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-siglip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "OpenBMB",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 319,
            "dir_name": "MiniCPM-V-2_6"
        },
        "GPT-4o (0806, detail-high)": {
            "Method": [
                "GPT-4o (0806, detail-high)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 320,
            "dir_name": "GPT4o_20240806"
        },
        "Llama-3-MixSense-v1.1": {
            "Method": [
                "Llama-3-MixSense-v1.1",
                "https://huggingface.co/Zero-Vision/Llama-3-MixSenseV1_1"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "Florence-2-Large-FT",
            "Org": "ZeroVision",
            "Time": "2024/08/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 321,
            "dir_name": "Llama-3-MixSenseV1_1"
        },
        "Step-1.5V": {
            "Method": [
                "Step-1.5V",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "Step-1.5",
            "Vision Model": "stepencoder",
            "Org": "StepFun",
            "Time": "2024/10/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 322,
            "dir_name": "Step1V"
        },
        "OmChat-v2.0-13B": {
            "Method": [
                "OmChat-v2.0-13B",
                "https://huggingface.co/omlab/omchat-v2.0-13B-single-beta_hf"
            ],
            "Parameters": "13B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "InternViT-6B",
            "Org": "Om AI",
            "Time": "2024/08/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 323,
            "dir_name": "OmChat"
        },
        "Parrot-7B": {
            "Method": [
                "Parrot-7B",
                "https://huggingface.co/AIDC-AI/Parrot-7B"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Alibaba",
            "Time": "2024/08/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 324,
            "dir_name": "Parrot"
        },
        "VILA1.5-3B": {
            "Method": [
                "VILA1.5-3B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-3b"
            ],
            "Parameters": "3B",
            "Language Model": "Sheared-LLaMA-2.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 325,
            "dir_name": "VILA1.5-3b"
        },
        "Llama-3-VILA1.5-8B": {
            "Method": [
                "Llama-3-VILA1.5-8B",
                "https://huggingface.co/Efficient-Large-Model/Llama-3-VILA1.5-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 326,
            "dir_name": "Llama-3-VILA1.5-8b"
        },
        "VILA1.5-13B": {
            "Method": [
                "VILA1.5-13B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-13b"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 327,
            "dir_name": "VILA1.5-13b"
        },
        "VILA1.5-40B": {
            "Method": [
                "VILA1.5-40B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-40b"
            ],
            "Parameters": "40B",
            "Language Model": "Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 328,
            "dir_name": "VILA1.5-40b"
        },
        "MMAlaya2": {
            "Org": "DataCanvas",
            "Time": "2024/08/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "MMAlaya2",
                "https://huggingface.co/DataCanvas/MMAlaya2"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "key": 329,
            "dir_name": "MMAlaya2"
        },
        "Idefics3-8B-Llama3": {
            "Org": "HuggingFace",
            "Time": "2024/08/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "Idefics3-8B-Llama3",
                "https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "key": 330,
            "dir_name": "Idefics3-8B-Llama3"
        },
        "Phi-3.5-Vision": {
            "Org": "Microsoft",
            "Time": "2024/08/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "Phi-3.5-Vision",
                "https://huggingface.co/microsoft/Phi-3.5-vision-instruct"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3.5",
            "Vision Model": "CLIP ViT-L/14",
            "key": 331,
            "dir_name": "Phi-3.5-Vision"
        },
        "Mirage-12B-v2.0": {
            "Org": "Monolith Foundation",
            "Time": "2024/08/30",
            "Verified": "No",
            "OpenSource": "Yes",
            "Method": [
                "Mirage-12B-v2.0",
                "https://huggingface.co/MonolithFoundation/Mirage-12B"
            ],
            "Parameters": "12B",
            "Language Model": "Mistral-12B",
            "Vision Model": "SigLIP-400M",
            "key": 332
        },
        "XGen-MM-Instruct-Interleave-v1.5": {
            "Method": [
                "XGen-MM-Instruct-Interleave-v1.5",
                "https://huggingface.co/Salesforce/xgen-mm-phi3-mini-instruct-interleave-r-v1.5"
            ],
            "Parameters": "4.4B",
            "Language Model": "Phi-3",
            "Vision Model": "SigLIP-400M",
            "Org": "Salesforce",
            "Time": "2024/09/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 333,
            "dir_name": "xgen-mm-phi3-interleave-r-v1.5"
        },
        "XGen-MM-Instruct-DPO-v1.5": {
            "Method": [
                "XGen-MM-Instruct-DPO-v1.5",
                "https://huggingface.co/Salesforce/xgen-mm-phi3-mini-instruct-dpo-r-v1.5"
            ],
            "Parameters": "4.4B",
            "Language Model": "Phi-3",
            "Vision Model": "SigLIP-400M",
            "Org": "Salesforce",
            "Time": "2024/09/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 334,
            "dir_name": "xgen-mm-phi3-dpo-r-v1.5"
        },
        "Qwen2-VL-7B": {
            "Method": [
                "Qwen2-VL-7B",
                "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/09/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 336,
            "dir_name": "Qwen2-VL-7B-Instruct"
        },
        "Qwen2-VL-2B": {
            "Method": [
                "Qwen2-VL-2B",
                "https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct"
            ],
            "Parameters": "2B",
            "Language Model": "Qwen2-1.5B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/09/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 337,
            "dir_name": "Qwen2-VL-2B-Instruct"
        },
        "Mantis-8B-Fuyu": {
            "Method": [
                "Mantis-8B-Fuyu",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-Fuyu"
            ],
            "Parameters": "8B",
            "Language Model": "Fuyu-8B",
            "Vision Model": "",
            "Org": "TIGER Lab",
            "Time": "2024/09/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 339,
            "dir_name": "Mantis-8B-Fuyu"
        },
        "Slime-7B": {
            "Method": [
                "Slime-7B",
                "https://huggingface.co/yifanzhang114/SliME-vicuna-7B"
            ],
            "Parameters": "7B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 340,
            "dir_name": "Slime-7B"
        },
        "Slime-8B": {
            "Method": [
                "Slime-8B",
                "https://huggingface.co/yifanzhang114/SliME-Llama3-8B"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 341,
            "dir_name": "Slime-8B"
        },
        "Slime-13B": {
            "Method": [
                "Slime-13B",
                "https://huggingface.co/yifanzhang114/SliME-vicuna-13B"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 342,
            "dir_name": "Slime-13B"
        },
        "Pixtral-12B": {
            "Method": [
                "Pixtral-12B",
                "https://huggingface.co/mistralai/Pixtral-12B-2409"
            ],
            "Parameters": "13B",
            "Language Model": "Nemo-12B",
            "Vision Model": "ViT-400M",
            "Org": "Mistral AI",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 343,
            "dir_name": "Pixtral-12B"
        },
        "Gemini-1.5-Flash": {
            "Method": [
                "Gemini-1.5-Flash",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 344,
            "dir_name": "GeminiFlash1-5"
        },
        "LLaVA-OneVision-0.5B": {
            "Method": [
                "LLaVA-OneVision-0.5B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-0.5b-ov"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 345,
            "dir_name": "llava_onevision_qwen2_0.5b_ov"
        },
        "LLaVA-OneVision-7B": {
            "Method": [
                "LLaVA-OneVision-7B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-7b-ov"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 346,
            "dir_name": "llava_onevision_qwen2_7b_ov"
        },
        "LLaVA-OneVision-0.5B (SI)": {
            "Method": [
                "LLaVA-OneVision-0.5B (SI)",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-0.5b-si"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 347,
            "dir_name": "llava_onevision_qwen2_0.5b_si"
        },
        "LLaVA-OneVision-7B (SI)": {
            "Method": [
                "LLaVA-OneVision-7B (SI)",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-7b-si"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 348,
            "dir_name": "llava_onevision_qwen2_7b_si"
        },
        "Qwen-VL-Plus-0809": {
            "Method": [
                "Qwen-VL-Plus-0809",
                "https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-qianwen-vl-plus-api"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 349,
            "dir_name": "Qwen-VL-Plus-0809"
        },
        "LLaVA-OneVision-72B (SI)": {
            "Method": [
                "LLaVA-OneVision-72B (SI)",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-72b-si"
            ],
            "Parameters": "73B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 350,
            "dir_name": "llava_onevision_qwen2_72b_si"
        },
        "LLaVA-OneVision-72B": {
            "Method": [
                "LLaVA-OneVision-72B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-72b-ov"
            ],
            "Parameters": "73B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 351,
            "dir_name": "llava_onevision_qwen2_72b_ov"
        },
        "Ovis1.6-Gemma2-9B": {
            "Method": [
                "Ovis1.6-Gemma2-9B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B"
            ],
            "Parameters": "10.2B",
            "Language Model": "Gemma2-9B-It",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/09/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 352,
            "dir_name": "Ovis1.6-Gemma2-9B"
        },
        "Eagle-X5-7B": {
            "Method": [
                "Eagle-X5-7B",
                "https://huggingface.co/NVEagle/Eagle-X5-7B"
            ],
            "Parameters": "9B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 353,
            "dir_name": "Eagle-X5-7B"
        },
        "Eagle-X5-13B": {
            "Method": [
                "Eagle-X5-13B",
                "https://huggingface.co/NVEagle/Eagle-X5-13B"
            ],
            "Parameters": "15B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 354,
            "dir_name": "Eagle-X5-13B"
        },
        "Moondream1": {
            "Method": [
                "Moondream1",
                "https://huggingface.co/vikhyatk/moondream1"
            ],
            "Parameters": "1.9B",
            "Language Model": "SigLIP-400M",
            "Vision Model": "Phi-1.5",
            "Org": "Moondream",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 355,
            "dir_name": "Moondream1"
        },
        "Moondream2": {
            "Method": [
                "Moondream2",
                "https://huggingface.co/vikhyatk/moondream2"
            ],
            "Parameters": "1.9B",
            "Language Model": "SigLIP-400M",
            "Vision Model": "Phi-1.5",
            "Org": "Moondream",
            "Time": "2024/10/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Moondream2",
            "key": 356
        },
        "MiniMonkey": {
            "Method": [
                "MiniMonkey",
                "https://huggingface.co/mx262/MiniMonkey"
            ],
            "Parameters": "2.2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "HUST",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 357,
            "dir_name": "minimonkey"
        },
        "BlueLM-V-3B": {
            "Method": [
                "BlueLM-V-3B",
                "https://developers.vivo.com/product/ai/bluelm"
            ],
            "Parameters": "3B",
            "Language Model": "BlueLM-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "vivo",
            "Time": "2024/10/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 358,
            "dir_name": "BlueLM_V"
        },
        "XinYuan-VL-2B-Instruct": {
            "Method": [
                "XinYuan-VL-2B-Instruct",
                "https://huggingface.co/Cylingo/Xinyuan-VL-2B"
            ],
            "Parameters": "2B",
            "Language Model": "Qwen2-1.5B",
            "Vision Model": "QwenViT",
            "Org": "Cylingo",
            "Time": "2024/09/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 359,
            "dir_name": "XinYuan-VL-2B-Instruct"
        },
        "Llama-3.2-11B-Vision-Instruct": {
            "Method": [
                "Llama-3.2-11B-Vision-Instruct",
                "https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct"
            ],
            "Parameters": "11B",
            "Language Model": "Llama-3.1-8B",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/10/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 360,
            "dir_name": "Llama-3.2-11B-Vision-Instruct"
        },
        "Molmo-7B-D": {
            "Method": [
                "Molmo-7B-D",
                "https://huggingface.co/allenai/Molmo-7B-D-0924"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 361,
            "dir_name": "molmo-7B-D-0924"
        },
        "POINTS-Yi-1.5-9B": {
            "Method": [
                "POINTS-Yi-1.5-9B",
                "https://huggingface.co/WePOINTS/POINTS-Yi-1-5-9B-Chat"
            ],
            "Parameters": "9.5B",
            "Language Model": "Yi-1.5-9B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "WeChat",
            "Time": "2024/10/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTS-Yi-1.5-9B-Chat",
            "key": 362
        },
        "POINTS-Qwen2.5-7B": {
            "Method": [
                "POINTS-Qwen2.5-7B",
                "https://huggingface.co/WePOINTS/POINTS-Qwen-2-5-7B-Chat"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen-2.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "WeChat",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTS-Qwen-2.5-7B-Chat",
            "key": 363
        },
        "Kosmos2": {
            "Method": [
                "Kosmos2",
                "https://huggingface.co/microsoft/kosmos-2-patch14-224"
            ],
            "Parameters": "1.7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Microsoft",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kosmos2",
            "key": 364
        },
        "Llama-3.2-90B-Vision-Instruct": {
            "Method": [
                "Llama-3.2-90B-Vision-Instruct",
                "https://huggingface.co/meta-llama/Llama-3.2-90B-Vision-Instruct"
            ],
            "Parameters": "88.6B",
            "Language Model": "Llama-3.1-70B",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Llama-3.2-90B-Vision-Instruct",
            "key": 365
        },
        "NVLM-D-72B": {
            "Method": [
                "NVLM-D-72B",
                "https://huggingface.co/nvidia/NVLM-D-72B"
            ],
            "Parameters": "79.4B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "InternViT-6B",
            "Org": "Nvidia",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "NVLM",
            "key": 366
        },
        "Molmo-7B-O": {
            "Method": [
                "Molmo-7B-O",
                "https://huggingface.co/allenai/Molmo-7B-O-0924"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 367,
            "dir_name": "molmo-7B-O-0924"
        },
        "MolmoE-1B": {
            "Method": [
                "MolmoE-1B",
                "https://huggingface.co/allenai/MolmoE-1B-0924"
            ],
            "Parameters": "7.2B",
            "Language Model": "OLMoE-1B-7B-0924",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "molmoE-1B-0924",
            "key": 368
        },
        "Puffin1-8B": {
            "Method": [
                "Puffin1-8B",
                "https://sereact.ai/products"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "sereact.ai",
            "Time": "2024/10/21",
            "Verified": "No",
            "OpenSource": "No",
            "key": 369
        },
        "Janus-1.3B": {
            "Method": [
                "Janus-1.3B",
                "https://huggingface.co/deepseek-ai/Janus-1.3B"
            ],
            "Parameters": "2.1B",
            "Language Model": "DeepSeek-1B",
            "Vision Model": "SigLIP-400M",
            "Org": "deepseek",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Janus-1.3B",
            "key": 370
        },
        "Vintern-3B-beta": {
            "Method": [
                "Vintern-3B-beta",
                "https://huggingface.co/5CD-AI/Vintern-3B-beta"
            ],
            "Parameters": "3.7B",
            "Language Model": "Qwen-2.5-3B",
            "Vision Model": "InternViT-300M",
            "Org": "Fifth Civil Defender",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Vintern-3B-beta",
            "key": 371
        },
        "Ovis1.6-Llama3.2-3B": {
            "Method": [
                "Ovis1.6-Llama3.2-3B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Llama3.2-3B"
            ],
            "Parameters": "4.1B",
            "Language Model": "Llama-3.2-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis1.6-Llama3.2-3B",
            "key": 372
        },
        "Aquila-VL-2B": {
            "Method": [
                "Aquila-VL-2B",
                "https://huggingface.co/BAAI/Aquila-VL-2B-llava-qwen"
            ],
            "Parameters": "2.2B",
            "Language Model": "Qwen-2.5-1.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "BAAI",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Aquila-VL-2B",
            "key": 373
        },
        "Claude3.5-Sonnet-20241022": {
            "Method": [
                "Claude3.5-Sonnet-20241022",
                "https://docs.anthropic.com/en/docs/build-with-claude/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/11/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Claude3-5V_Sonnet_20241022",
            "key": 376
        },
        "Molmo-72B": {
            "Method": [
                "Molmo-72B",
                "https://huggingface.co/allenai/Molmo-72B-0924"
            ],
            "Parameters": "73.3B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "molmo-72B-0924",
            "key": 377
        },
        "Qwen2-VL-72B": {
            "Method": [
                "Qwen2-VL-72B",
                "https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct"
            ],
            "Parameters": "73.4B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/10/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2-VL-72B-Instruct",
            "key": 378
        },
        "Bumblebee-7B-v2.2": {
            "Method": [
                "Bumblebee-7B-v2.2",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "Mono-Encoder",
            "Org": "Monolith Foundation",
            "Time": "2024/10/30",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 379
        },
        "Falcon2-VLM-11B": {
            "Method": [
                "Falcon2-VLM-11B",
                "https://huggingface.co/tiiuae/falcon-11B-vlm"
            ],
            "Parameters": "11.4B",
            "Language Model": "Falcon2-11B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Technology Innovation Institute",
            "Time": "2024/10/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Falcon2-VLM-11B",
            "key": 380
        },
        "H2OVL-800M": {
            "Method": [
                "H2OVL-800M",
                "https://huggingface.co/h2oai/h2ovl-mississippi-800m"
            ],
            "Parameters": "0.83B",
            "Language Model": "H2O-DANUBE3-500M",
            "Vision Model": "InternViT-300M",
            "Org": "H2O.ai",
            "Time": "2024/10/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "h2ovl-mississippi-1b",
            "key": 381
        },
        "H2OVL-2B": {
            "Method": [
                "H2OVL-2B",
                "https://huggingface.co/h2oai/h2ovl-mississippi-2b"
            ],
            "Parameters": "2.2B",
            "Language Model": "H2O-DANUBE2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "H2O.ai",
            "Time": "2024/10/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "h2ovl-mississippi-2b",
            "key": 382
        },
        "Taiyi": {
            "Method": [
                "Taiyi",
                "https://taiyi.megvii.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Megvii & StepFun",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Taiyi",
            "key": 383
        },
        "Qwen-VL-Max-0809": {
            "Method": [
                "Qwen-VL-Max-0809",
                "https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-qianwen-vl-plus-api"
            ],
            "Parameters": "72B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/09/12",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "Qwen-VL-Max-0809",
            "key": 384
        },
        "bailingMM-mini": {
            "Method": [
                "bailingMM-mini",
                "https://bailingmm.alipay.com/llm/landing"
            ],
            "Parameters": "17B",
            "Language Model": "bailing-mini",
            "Vision Model": "bailingMM-encoder-1B\nInternViT-6B",
            "Org": "Ant Group",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "bailingMM",
            "key": 385
        },
        "JT-VL-Chat-V3.0": {
            "Method": [
                "JT-VL-Chat-V3.0",
                "https://github.com/jiutiancv/JT-VL-Chat/tree/main"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "China Mobile",
            "Time": "2025/08/04",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "JTVL-V3",
            "key": 386
        },
        "Vintern-1B-v2": {
            "Method": [
                "Vintern-1B-v2",
                "https://huggingface.co/5CD-AI/Vintern-1B-v2"
            ],
            "Parameters": "3.7B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "InternViT-300M",
            "Org": "Fifth Civil Defender",
            "Time": "2024/11/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Vintern-1B-v2",
            "key": 387
        },
        "RBDash-v1.5": {
            "Method": [
                "RBDash-v1.5",
                "https://huggingface.co/RBDash-Team/RBDash-v1.5"
            ],
            "Parameters": "79B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "CLIP ViT-L/14\nInternViT-6B",
            "Org": "DLUT",
            "Time": "2024/11/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "RBDash_72b",
            "key": 388
        },
        "Awaker2.5-VL": {
            "Method": [
                "Awaker2.5-VL",
                "https://github.com/MetabrainAGI/Awaker"
            ],
            "Parameters": "10.8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "QwenViT",
            "Org": "MetabrainAGI",
            "Time": "2024/11/23",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 389
        },
        "InternVL2-8B-MPO": {
            "Method": [
                "InternVL2-8B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/11/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2-8B-MPO",
            "key": 390
        },
        "InternVL2-8B-MPO-CoT": {
            "Method": [
                "InternVL2-8B-MPO-CoT",
                "https://huggingface.co/OpenGVLab/InternVL2-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/11/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2-8B-MPO-CoT",
            "key": 391
        },
        "SmolVLM-Instruct": {
            "Method": [
                "SmolVLM-Instruct",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM",
            "key": 392
        },
        "SmolVLM-Instruct-DPO": {
            "Method": [
                "SmolVLM-Instruct-DPO",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct-DPO"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-DPO",
            "key": 393
        },
        "SmolVLM-Synthetic": {
            "Method": [
                "SmolVLM-Synthetic",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Synthetic"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-Synthetic",
            "key": 394
        },
        "Eagle-X5-34B-Chat": {
            "Method": [
                "Eagle-X5-34B-Chat",
                "https://huggingface.co/NVEagle/Eagle-X5-34B-Chat"
            ],
            "Parameters": "36.8B",
            "Language Model": "Yi-34B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/11/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Eagle-X5-34B-Chat",
            "key": 395
        },
        "Ovis1.6-Gemma2-27B": {
            "Method": [
                "Ovis1.6-Gemma2-27B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-27B"
            ],
            "Parameters": "28.9B",
            "Language Model": "Gemma2-27B",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/11/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis1.6-Gemma2-27B",
            "key": 396
        },
        "TeleMM": {
            "Method": [
                "TeleMM",
                "https://docs.siliconflow.cn/api-reference/chat-completions/chat-completions"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "China Telecom",
            "Time": "2024/12/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "TeleMM",
            "key": 397
        },
        "Gemini-1.5-Pro-002": {
            "Method": [
                "Gemini-1.5-Pro-002",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/12/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GeminiPro1-5-002",
            "key": 398
        },
        "Gemini-1.5-Flash-002": {
            "Method": [
                "Gemini-1.5-Flash-002",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/12/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GeminiFlash1-5-002",
            "key": 399
        },
        "GPT-4o (1120, detail-high)": {
            "Method": [
                "GPT-4o (1120, detail-high)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/12/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GPT4o_20241120",
            "key": 400
        },
        "Aria": {
            "Method": [
                "Aria",
                "https://huggingface.co/rhymes-ai/Aria"
            ],
            "Parameters": "25.3B",
            "Language Model": "Aria-MoE",
            "Vision Model": "SigLIP-400M",
            "Org": "Rhymes AI",
            "Time": "2024/12/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Aria",
            "key": 401
        },
        "LLaVA-CoT": {
            "Method": [
                "LLaVA-CoT",
                "https://huggingface.co/Xkev/Llama-3.2V-11B-cot"
            ],
            "Parameters": "11B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Peking University",
            "Time": "2025/01/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "LLaVA-CoT",
            "key": 402
        },
        "POINTS1.5-Qwen2.5-7B": {
            "Method": [
                "POINTS1.5-Qwen2.5-7B",
                "https://huggingface.co/WePOINTS/POINTS-1-5-Qwen-2-5-7B-Chat"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen-2.5-7B",
            "Vision Model": "NaViT",
            "Org": "WeChat",
            "Time": "2024/12/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTSV15-Qwen-2.5-7B-Chat",
            "key": 403
        },
        "BailingMM-Lite-1203": {
            "Method": [
                "BailingMM-Lite-1203",
                "https://zxb.alipay.com/llm/landing"
            ],
            "Parameters": "21B",
            "Language Model": "Bailing-20B",
            "Vision Model": "SigLIP-400M",
            "Org": "Ant Group",
            "Time": "2024/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "bailingMM-Lite",
            "key": 404
        },
        "GLM-4v-Plus": {
            "Method": [
                "GLM-4v-Plus",
                "https://open.bigmodel.cn/dev/api/normal-model/glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GLM4V_PLUS",
            "key": 412
        },
        "Step-1.5V-mini": {
            "Method": [
                "Step-1.5V-mini",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "StepFun",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Step1.5V-mini",
            "key": 413
        },
        "abab6.5s": {
            "Method": [
                "abab6.5s",
                "https://www.minimaxi.com/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "MiniMax",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "abab6.5s",
            "key": 414
        },
        "abab7-preview": {
            "Method": [
                "abab7-preview",
                "https://www.minimaxi.com/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "MiniMax",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "abab7-preview",
            "key": 415
        },
        "SenseNova": {
            "Method": [
                "SenseNova",
                "https://platform.sensenova.cn/home"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "SenseTime",
            "Time": "2024/12/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SenseChat-Vision",
            "key": 416
        },
        "InternVL2.5-1B": {
            "Method": [
                "InternVL2.5-1B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-1B"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen-2.5-0.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-1B",
            "key": 417
        },
        "InternVL2.5-2B": {
            "Method": [
                "InternVL2.5-2B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-2B"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2.5-1.8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-2B",
            "key": 418
        },
        "InternVL2.5-4B": {
            "Method": [
                "InternVL2.5-4B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-4B"
            ],
            "Parameters": "4B",
            "Language Model": "Qwen-2.5-3B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-4B",
            "key": 419
        },
        "InternVL2.5-8B": {
            "Method": [
                "InternVL2.5-8B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-8B"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-8B",
            "key": 420
        },
        "InternVL2.5-26B": {
            "Method": [
                "InternVL2.5-26B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-26B"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2.5-20B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-26B",
            "key": 421
        },
        "InternVL2.5-38B": {
            "Method": [
                "InternVL2.5-38B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-38B"
            ],
            "Parameters": "38B",
            "Language Model": "Qwen-2.5-32B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-38B",
            "key": 422
        },
        "InternVL2.5-78B": {
            "Method": [
                "InternVL2.5-78B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-78B"
            ],
            "Parameters": "78B",
            "Language Model": "Qwen-2.5-72B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-78B",
            "key": 423
        },
        "SAIL-VL-2B": {
            "Method": [
                "SAIL-VL-2B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL-2B"
            ],
            "Parameters": "2.1B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "InternViT-300M",
            "Org": "ByteDance",
            "Time": "2024/12/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL-2B",
            "key": 424
        },
        "InternVL2.5-1B-MPO": {
            "Method": [
                "InternVL2.5-1B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-1B-MPO"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen-2.5-0.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-1B-MPO",
            "key": 425
        },
        "InternVL2.5-2B-MPO": {
            "Method": [
                "InternVL2.5-2B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-2B-MPO"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2.5-1.8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-2B-MPO",
            "key": 426
        },
        "InternVL2.5-4B-MPO": {
            "Method": [
                "InternVL2.5-4B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-4B-MPO"
            ],
            "Parameters": "4B",
            "Language Model": "Qwen-2.5-3B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-4B-MPO",
            "key": 427
        },
        "InternVL2.5-8B-MPO": {
            "Method": [
                "InternVL2.5-8B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-8B-MPO",
            "key": 428
        },
        "InternVL2.5-26B-MPO": {
            "Method": [
                "InternVL2.5-26B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-26B-MPO"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2.5-20B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-26B-MPO",
            "key": 429
        },
        "InternVL2.5-38B-MPO": {
            "Method": [
                "InternVL2.5-38B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-38B-MPO"
            ],
            "Parameters": "38B",
            "Language Model": "Qwen-2.5-32B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-38B-MPO",
            "key": 430
        },
        "Valley-Eagle": {
            "Method": [
                "Valley-Eagle",
                "https://huggingface.co/bytedance-research/Valley-Eagle-7B"
            ],
            "Parameters": "8.9B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "Qwen-ViT\nSigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/12/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "valley_eagle",
            "key": 431
        },
        "InternVL2.5-78B-MPO": {
            "Method": [
                "InternVL2.5-78B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-78B-MPO"
            ],
            "Parameters": "78B",
            "Language Model": "Qwen-2.5-72B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-78B-MPO",
            "key": 432
        },
        "DeepSeek-VL2-Tiny": {
            "Method": [
                "DeepSeek-VL2-Tiny",
                "https://huggingface.co/deepseek-ai/deepseek-vl2-tiny"
            ],
            "Parameters": "3.4B",
            "Language Model": "DeepSeekMoE-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2_tiny",
            "key": 433
        },
        "DeepSeek-VL2-Small": {
            "Method": [
                "DeepSeek-VL2-Small",
                "https://huggingface.co/deepseek-ai/deepseek-vl2-small"
            ],
            "Parameters": "16.1B",
            "Language Model": "DeepSeekMoE-16B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2_small",
            "key": 434
        },
        "VARCO-VISION-14B": {
            "Method": [
                "VARCO-VISION-14B",
                "https://huggingface.co/NCSOFT/VARCO-VISION-14B-HF"
            ],
            "Parameters": "15.2B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "SigLIP-400M",
            "Org": "NC Research",
            "Time": "2025/01/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "varco-vision-hf",
            "key": 437
        },
        "Gemini-2.0-Flash": {
            "Method": [
                "Gemini-2.0-Flash",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2025/01/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GeminiFlash2-0",
            "key": 438
        },
        "Step-1o": {
            "Method": [
                "Step-1o",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "StepFun",
            "Time": "2025/01/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Step1o",
            "key": 439
        },
        "HunYuan-Standard-Vision": {
            "Method": [
                "HunYuan-Standard-Vision",
                "https://cloud.tencent.com/document/product/1729/104753"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Tencent",
            "Time": "2025/01/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "HunYuan-Standard-Vision",
            "key": 440
        },
        "Ross-Qwen2-7B": {
            "Method": [
                "Ross-Qwen2-7B",
                "https://huggingface.co/HaochenWang/ross-qwen2-7b"
            ],
            "Parameters": "8.2B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "CASIA",
            "Time": "2025/01/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "ross-qwen2-7b",
            "key": 441
        },
        "VITA-1.5": {
            "Method": [
                "VITA-1.5",
                "https://huggingface.co/VITA-MLLM/VITA-1.5"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "InternViT-300M",
            "Org": "NJU",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "vita_qwen2",
            "key": 442
        },
        "VITA": {
            "Method": [
                "VITA",
                "https://huggingface.co/VITA-MLLM/VITA"
            ],
            "Parameters": "47B",
            "Language Model": "Mixtral-8x7B",
            "Vision Model": "InternViT-300M",
            "Org": "NJU",
            "Time": "2025/01/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "vita",
            "key": 443
        },
        "MiniCPM-o-2.6": {
            "Method": [
                "MiniCPM-o-2.6",
                "https://huggingface.co/openbmb/MiniCPM-o-2_6"
            ],
            "Parameters": "8.67B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "OpenBMB",
            "Time": "2025/01/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MiniCPM-o-2_6",
            "key": 444
        },
        "BailingMM-Pro-0120": {
            "Method": [
                "BailingMM-Pro-0120",
                "https://zxb.alipay.com/llm/landing"
            ],
            "Parameters": "81B",
            "Language Model": "Bailing-80B",
            "Vision Model": "SigLIP-400M",
            "Org": "Ant Group",
            "Time": "2025/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "BailingMM-Pro-0120",
            "key": 445
        },
        "Doubao-1.5-Pro": {
            "Method": [
                "Doubao-1.5-Pro",
                "https://team.doubao.com/zh/special/doubao_1_5_pro"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "ByteDance",
            "Time": "2025/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "DoubaoVL",
            "key": 446
        },
        "GLM-4v-Plus-20250111": {
            "Method": [
                "GLM-4v-Plus-20250111",
                "https://open.bigmodel.cn/dev/api/normal-model/glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2025/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GLM4V_PLUS_20250111",
            "key": 447
        },
        "Emu3_chat": {
            "Method": [
                "Emu3_chat",
                "https://huggingface.co/BAAI/Emu3-Chat"
            ],
            "Parameters": "8.49B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Beijing Academy of Artificial Intelligence",
            "Time": "2025/01/26",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "dir_name": "emu3_chat",
            "key": 448
        },
        "SmolVLM-256M": {
            "Method": [
                "SmolVLM-256M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct"
            ],
            "Parameters": "0.26B",
            "Language Model": "SmolLM2-135M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-256M",
            "key": 449
        },
        "SmolVLM-500M": {
            "Method": [
                "SmolVLM-500M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-500M-Instruct"
            ],
            "Parameters": "0.51B",
            "Language Model": "SmolLM2-360M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-500M",
            "key": 450
        },
        "Janus-Pro-7B": {
            "Method": [
                "Janus-Pro-7B",
                "https://huggingface.co/deepseek-ai/Janus-Pro-7B"
            ],
            "Parameters": "7.42B",
            "Language Model": "DeepSeek-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "deepseek",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Janus-Pro-7B",
            "key": 454
        },
        "Ola-7b": {
            "Method": [
                "Ola-7b",
                "https://huggingface.co/THUdyh/Ola-7b"
            ],
            "Parameters": "8.88B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "Oryx-ViT",
            "Org": "THU",
            "Time": "2025/02/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "ola",
            "key": 455
        },
        "Ovis2-1B": {
            "Method": [
                "Ovis2-1B",
                "https://huggingface.co/AIDC-AI/Ovis2-1B"
            ],
            "Parameters": "1.27B",
            "Language Model": "Qwen2.5-0.5B",
            "Vision Model": "AIMv2 Large",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-1B",
            "key": 456
        },
        "Ovis2-2B": {
            "Method": [
                "Ovis2-2B",
                "https://huggingface.co/AIDC-AI/Ovis2-2B"
            ],
            "Parameters": "2.46B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "AIMv2 Large",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-2B",
            "key": 457
        },
        "Ovis2-4B": {
            "Method": [
                "Ovis2-4B",
                "https://huggingface.co/AIDC-AI/Ovis2-4B"
            ],
            "Parameters": "4.62B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-4B",
            "key": 458
        },
        "Ovis2-8B": {
            "Method": [
                "Ovis2-8B",
                "https://huggingface.co/AIDC-AI/Ovis2-8B"
            ],
            "Parameters": "8.94B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-8B",
            "key": 459
        },
        "Ovis2-16B": {
            "Method": [
                "Ovis2-16B",
                "https://huggingface.co/AIDC-AI/Ovis2-16B"
            ],
            "Parameters": "16.2B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-16B",
            "key": 460
        },
        "Ovis2-34B": {
            "Method": [
                "Ovis2-34B",
                "https://huggingface.co/AIDC-AI/Ovis2-34B"
            ],
            "Parameters": "34.9B",
            "Language Model": "Qwen2.5-32B",
            "Vision Model": "AIMv2-1B",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-34B",
            "key": 461
        },
        "Qwen2.5-VL-3B": {
            "Method": [
                "Qwen2.5-VL-3B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct"
            ],
            "Parameters": "3.75B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-3B-Instruct",
            "key": 462
        },
        "Qwen2.5-VL-7B": {
            "Method": [
                "Qwen2.5-VL-7B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct"
            ],
            "Parameters": "8.29B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-7B-Instruct",
            "key": 463
        },
        "Qwen2.5-VL-72B": {
            "Method": [
                "Qwen2.5-VL-72B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct"
            ],
            "Parameters": "73.4B",
            "Language Model": "Qwen2.5-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-72B-Instruct",
            "key": 464
        },
        "Gemini-2.0-Pro": {
            "Method": [
                "Gemini-2.0-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2025/02/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GeminiPro2-0",
            "key": 465
        },
        "Claude3.7-Sonnet": {
            "Method": [
                "Claude3.7-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2025/02/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Claude3-7V_Sonnet",
            "key": 466
        },
        "moonshot-v1-8k": {
            "Method": [
                "moonshot-v1-8k",
                "https://platform.moonshot.cn/docs/api/chat"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Moonshot AI",
            "Time": "2025/03/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "moonshot-v1-8k",
            "key": 467
        },
        "grok-2-vision-1212": {
            "Method": [
                "grok-2-vision-1212",
                "https://docs.x.ai/docs/overview"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "xAI",
            "Time": "2025/03/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "grok-2-vision-1212",
            "key": 468
        },
        "DeepSeek-VL2": {
            "Method": [
                "DeepSeek-VL2",
                "https://huggingface.co/deepseek-ai/deepseek-vl2"
            ],
            "Parameters": "27.5B",
            "Language Model": "DeepSeekMoE-27B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2",
            "key": 469
        },
        "SmolVLM2": {
            "Method": [
                "SmolVLM2",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct"
            ],
            "Parameters": "2.25B",
            "Language Model": "SmolLM2-1.7M",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2",
            "key": 470
        },
        "SmolVLM2-256M": {
            "Method": [
                "SmolVLM2-256M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-256M-Video-Instruct"
            ],
            "Parameters": "0.26B",
            "Language Model": "SmolLM2-135M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2-256M",
            "key": 471
        },
        "SmolVLM2-500M": {
            "Method": [
                "SmolVLM2-500M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
            ],
            "Parameters": "0.51B",
            "Language Model": "SmolLM2-360M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2-500M",
            "key": 472
        },
        "Phi-4-MultiModal": {
            "Method": [
                "Phi-4-MultiModal",
                "https://huggingface.co/microsoft/Phi-4-multimodal-instruct"
            ],
            "Parameters": "5.57B",
            "Language Model": "Phi-4-Mini",
            "Vision Model": "SigLIP-400M",
            "Org": "Microsoft",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Phi-4-Vision",
            "key": 473
        },
        "MUG-U-7B": {
            "Method": [
                "MUG-U-7B",
                "https://github.com/Shopee-MUG/MUG-U"
            ],
            "Parameters": "7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Shopee",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MUG-U-7B",
            "key": 474
        },
        "Gemma3-4B": {
            "Method": [
                "Gemma3-4B",
                "https://huggingface.co/google/gemma-3-4b-it"
            ],
            "Parameters": "4.3B",
            "Language Model": "Gemma3-4B",
            "Vision Model": "SigLIP-400M",
            "Org": "Google",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Gemma3-4B",
            "key": 475
        },
        "Gemma3-12B": {
            "Method": [
                "Gemma3-12B",
                "https://huggingface.co/google/gemma-3-12b-it"
            ],
            "Parameters": "12.2B",
            "Language Model": "Gemma3-12B",
            "Vision Model": "SigLIP-400M",
            "Org": "Google",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Gemma3-12B",
            "key": 476
        },
        "Gemma3-27B": {
            "Method": [
                "Gemma3-27B",
                "https://huggingface.co/google/gemma-3-27b-it"
            ],
            "Parameters": "27.4B",
            "Language Model": "Gemma3-27B",
            "Vision Model": "SigLIP-400M",
            "Org": "Google",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Gemma3-27B",
            "key": 477
        },
        "AKI-4B": {
            "Method": [
                "AKI-4B",
                "https://huggingface.co/Sony/AKI-4B-phi-3.5-mini"
            ],
            "Parameters": "4.33B",
            "Language Model": "Phi-3.5",
            "Vision Model": "SigLIP-400M",
            "Org": "Sony",
            "Time": "2025/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "AKI",
            "key": 478
        },
        "GPT-4.5": {
            "Method": [
                "GPT-4.5",
                "https://openai.com/index/introducing-gpt-4-5/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/03/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GPT4.5",
            "key": 479
        },
        "Ristretto-3B": {
            "Method": [
                "Ristretto-3B",
                "https://huggingface.co/LiAutoAD/Ristretto-3B"
            ],
            "Parameters": "3.84B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "LiAutoAD",
            "Time": "2025/04/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ristretto-3B",
            "key": 480
        },
        "ChatGPT-4o-latest": {
            "Method": [
                "ChatGPT-4o-latest",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "ChatGPT4o",
            "key": 481
        },
        "Gemini-2.5-Pro": {
            "Method": [
                "Gemini-2.5-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2025/04/07",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "GeminiPro2-5",
            "key": 482
        },
        "Kimi-VL-A3B-Instruct": {
            "Method": [
                "Kimi-VL-A3B-Instruct",
                "https://huggingface.co/moonshotai/Kimi-VL-A3B-Instruct"
            ],
            "Parameters": "16.4B",
            "Language Model": "Moonlight-16B-A3B",
            "Vision Model": "MoonViT",
            "Org": "moonshot.ai",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kimi-VL-A3B-Instruct",
            "key": 483
        },
        "InternVL3-1B": {
            "Method": [
                "InternVL3-1B",
                "https://huggingface.co/OpenGVLab/InternVL3-1B"
            ],
            "Parameters": "0.94B",
            "Language Model": "Qwen2.5-0.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-1B",
            "key": 484
        },
        "InternVL3-2B": {
            "Method": [
                "InternVL3-2B",
                "https://huggingface.co/OpenGVLab/InternVL3-2B"
            ],
            "Parameters": "2.09B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-2B",
            "key": 485
        },
        "InternVL3-8B": {
            "Method": [
                "InternVL3-8B",
                "https://huggingface.co/OpenGVLab/InternVL3-8B"
            ],
            "Parameters": "7.94B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-8B",
            "key": 486
        },
        "InternVL3-9B": {
            "Method": [
                "InternVL3-9B",
                "https://huggingface.co/OpenGVLab/InternVL3-9B"
            ],
            "Parameters": "9.14B",
            "Language Model": "InternLM3-8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-9B",
            "key": 487
        },
        "InternVL3-14B": {
            "Method": [
                "InternVL3-14B",
                "https://huggingface.co/OpenGVLab/InternVL3-14B"
            ],
            "Parameters": "15.1B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-14B",
            "key": 488
        },
        "InternVL3-38B": {
            "Method": [
                "InternVL3-38B",
                "https://huggingface.co/OpenGVLab/InternVL3-38B"
            ],
            "Parameters": "38.4B",
            "Language Model": "Qwen2.5-32B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-38B",
            "key": 489
        },
        "InternVL3-78B": {
            "Method": [
                "InternVL3-78B",
                "https://huggingface.co/OpenGVLab/InternVL3-78B"
            ],
            "Parameters": "78.4B",
            "Language Model": "Qwen2.5-72B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-78B",
            "key": 490
        },
        "GPT-4.1-20250414": {
            "Method": [
                "GPT-4.1-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-2025-04-14",
            "key": 491
        },
        "GPT-4.1-mini-20250414": {
            "Method": [
                "GPT-4.1-mini-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-mini-2025-04-14",
            "key": 492
        },
        "GPT-4.1-nano-20250414": {
            "Method": [
                "GPT-4.1-nano-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-nano-2025-04-14",
            "key": 493
        },
        "Kimi-VL-A3B-Thinking": {
            "Method": [
                "Kimi-VL-A3B-Thinking",
                "https://huggingface.co/moonshotai/Kimi-VL-A3B-Thinking"
            ],
            "Parameters": "16.4B",
            "Language Model": "Moonlight-16B-A3B",
            "Vision Model": "MoonViT",
            "Org": "moonshot.ai",
            "Time": "2025/04/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kimi-VL-A3B-Thinking",
            "key": 494
        },
        "SAIL-VL-1.5-2B": {
            "Method": [
                "SAIL-VL-1.5-2B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL-1d5-2B"
            ],
            "Parameters": "2.47B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "AIMv2 Huge",
            "Org": "ByteDance",
            "Time": "2025/04/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL-1.5-2B",
            "key": 495
        },
        "SAIL-VL-1.5-8B": {
            "Method": [
                "SAIL-VL-1.5-8B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL-1d5-8B"
            ],
            "Parameters": "7.95B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "InternViT-300B",
            "Org": "ByteDance",
            "Time": "2025/04/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL-1.5-8B",
            "key": 496
        },
        "SAIL-VL-1.6-8B": {
            "Method": [
                "SAIL-VL-1.6-8B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL-1d6-8B"
            ],
            "Parameters": "8.33B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "AIMv2 Huge",
            "Org": "ByteDance",
            "Time": "2025/04/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL-1.6-8B",
            "key": 497
        },
        "SenseNova-V6-Pro": {
            "Method": [
                "SenseNova-V6-Pro",
                "https://platform.sensenova.cn/technology/fusion/Pro/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "SenseTime",
            "Time": "2025/05/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SenseNova-V6-Pro",
            "key": 498
        },
        "QTuneVL1-2B": {
            "Method": [
                "QTuneVL1-2B",
                "https://huggingface.co/hanchaow/QTuneVL1-2B"
            ],
            "Parameters": "2.21B",
            "Language Model": "InternLM2.5-1.8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Reconova AI Lab",
            "Time": "2025/05/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "QTuneVL1-2B",
            "key": 499
        },
        "CongRong-v2.0": {
            "Method": [
                "CongRong-v2.0",
                "http://115.120.28.181:20228/web/#/document-center"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "CloudWalk",
            "Time": "2025/05/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "CongRong-v2.0",
            "key": 500
        },
        "WeThink-Qwen2.5VL-7B": {
            "Method": [
                "WeThink-Qwen2.5VL-7B",
                "https://huggingface.co/yangjie-cv/WeThink-Qwen2.5VL-7B"
            ],
            "Parameters": "8.29B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "QwenViT",
            "Org": "WeChat Vision",
            "Time": "2025/05/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "WeThink-Qwen2.5VL-7B",
            "key": 501
        },
        "valley2": {
            "Method": [
                "valley2",
                "https://huggingface.co/bytedance-research/Valley-Eagle-7B"
            ],
            "Parameters": "8.88B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2025/05/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "valley2",
            "key": 502
        },
        "valley2_dpo": {
            "Method": [
                "valley2_dpo",
                "https://huggingface.co/bytedance-research/Valley2-DPO"
            ],
            "Parameters": "8.88B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2025/05/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "valley2_dpo",
            "key": 503
        },
        "Flash-VL-2B-Dynamic-ISS": {
            "Method": [
                "Flash-VL-2B-Dynamic-ISS",
                "https://huggingface.co/FlashVL/FlashVL-2B-Dynamic-ISS"
            ],
            "Parameters": "2.53B",
            "Language Model": "Qwen-2.5-1.5B-Instruct",
            "Vision Model": "SigLIP2-400M-512",
            "Org": "Meituan",
            "Time": "2025/05/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Flash-VL-2B-Dynamic-ISS",
            "key": 504
        },
        "Seed1.5-VL": {
            "Method": [
                "Seed1.5-VL",
                "https://github.com/ByteDance-Seed/Seed1.5-VL"
            ],
            "Parameters": "",
            "Language Model": "Seed1.5-LLM",
            "Vision Model": "Seed-ViT",
            "Org": "ByteDance",
            "Time": "2025/05/30",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "Seed1.5-VL",
            "key": 505
        },
        "Long-VITA-16K": {
            "Method": [
                "Long-VITA-16K",
                "https://huggingface.co/VITA-MLLM/Long-VITA-16K"
            ],
            "Parameters": "14B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "InternViT-300M",
            "Org": "Tencent Youtu Lab & Nanjing University",
            "Time": "2025/06/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Long-VITA-16K",
            "key": 506
        },
        "HawkVL-2B": {
            "Method": [
                "HawkVL-2B",
                "https://huggingface.co/xjtupanda/HawkVL-2B"
            ],
            "Parameters": "2.44B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "QwenViT",
            "Org": " Reconova AI Lab & USTC",
            "Time": "2025/06/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "HawkVL-2B",
            "key": 507
        },
        "granite-vision-3.1-2b-preview": {
            "Method": [
                "granite-vision-3.1-2b-preview",
                "https://huggingface.co/ibm-granite/granite-vision-3.1-2b-preview"
            ],
            "Parameters": "2.98B",
            "Language Model": "granite-3.1-2b-instruct",
            "Vision Model": "SigLip",
            "Org": "IBM",
            "Time": "2025/06/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "granite_vision_3.1_2b_preview",
            "key": 508
        },
        "granite-vision-3.2-2b": {
            "Method": [
                "granite-vision-3.2-2b",
                "https://huggingface.co/ibm-granite/granite-vision-3.2-2b"
            ],
            "Parameters": "2.98B",
            "Language Model": "granite-3.1-2b-instruct",
            "Vision Model": "SigLip",
            "Org": "IBM",
            "Time": "2025/06/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "granite_vision_3.2_2b",
            "key": 509
        },
        "granite-vision-3.3-2b": {
            "Method": [
                "granite-vision-3.3-2b",
                "https://huggingface.co/ibm-granite/granite-vision-3.3-2b"
            ],
            "Parameters": "2.98B",
            "Language Model": "granite-3.1-2b-instruct",
            "Vision Model": "SigLIP2-400M",
            "Org": "IBM",
            "Time": "2025/06/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "granite_vision_3.3_2b",
            "key": 510
        },
        "MiMo-VL-7B": {
            "Method": [
                "MiMo-VL-7B",
                "https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-RL"
            ],
            "Parameters": "8.31B",
            "Language Model": "Mimo-7B",
            "Vision Model": "Qwen2.5-ViT",
            "Org": "Xiaomi",
            "Time": "2025/07/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MiMo-VL-7B-RL",
            "key": 511
        },
        "Qwen2.5-VL-32B": {
            "Method": [
                "Qwen2.5-VL-32B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct"
            ],
            "Parameters": "33.5B",
            "Language Model": "Qwen2.5-32B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/07/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-32B-Instruct",
            "key": 512
        },
        "Kimi-VL-A3B-Thinking-2506": {
            "Method": [
                "Kimi-VL-A3B-Thinking-2506",
                "https://huggingface.co/moonshotai/Kimi-VL-A3B-Thinking-2506"
            ],
            "Parameters": "16.4B",
            "Language Model": "Moonlight-16B-A3B",
            "Vision Model": "MoonViT",
            "Org": "moonshot.ai",
            "Time": "2025/07/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kimi-VL-A3B-Thinking-2506",
            "key": 513
        },
        "BlueLM-2.5-3B": {
            "Method": [
                "BlueLM-2.5-3B",
                "https://arxiv.org/pdf/2507.05934"
            ],
            "Parameters": "2.9B",
            "Language Model": "BlueLM-base-3B",
            "Vision Model": "Siglip2-So400M",
            "Org": "Vivo",
            "Time": "2025/07/16",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "BlueLM-2.5-3B",
            "key": 514
        },
        "Ovis-U1-3B": {
            "Method": [
                "Ovis-U1-3B",
                "https://huggingface.co/AIDC-AI/Ovis-U1-3B"
            ],
            "Parameters": "3.64B",
            "Language Model": "Qwen3-1.7B",
            "Vision Model": "aimv2-large-path14-448",
            "Org": "Ovis Team, Alibaba Group",
            "Time": "2025/07/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis-U1-3B",
            "key": 515
        },
        "VARCO-VISION-2.0-1.7B": {
            "Method": [
                "VARCO-VISION-2.0-1.7B",
                "https://huggingface.co/NCSOFT/VARCO-VISION-2.0-1.7B"
            ],
            "Parameters": "2.12B",
            "Language Model": "Qwen3-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "NCSOFT",
            "Time": "2025/08/04",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "varco-vision-2-1.7b",
            "key": 516
        },
        "VARCO-VISION-2.0-14B": {
            "Method": [
                "VARCO-VISION-2.0-14B",
                "https://huggingface.co/NCSOFT/VARCO-VISION-2.0-14B"
            ],
            "Parameters": "15.2B",
            "Language Model": "Qwen3-14B",
            "Vision Model": "SigLIP-400M",
            "Org": "NCSOFT",
            "Time": "2025/08/04",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "varco-vision-2-14b",
            "key": 517
        },
        "QTuneVL1.5-2B": {
            "Method": [
                "QTuneVL1.5-2B",
                "https://huggingface.co/hanchaow/QTuneVL1_5-2B"
            ],
            "Parameters": "2.09B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Reconova AI Lab & BDAA-Lab ",
            "Time": "2025/08/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "QTuneVL1_5-2B",
            "key": 518
        },
        "QTuneVL1.5-3B": {
            "Method": [
                "QTuneVL1.5-3B",
                "https://huggingface.co/hanchaow/QTuneVL1_5-3B"
            ],
            "Parameters": "3.75B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "QwenViT",
            "Org": "Reconova AI Lab & BDAA-Lab ",
            "Time": "2025/08/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "QTuneVL1_5-3B",
            "key": 519
        },
        "R-4B": {
            "Method": [
                "R-4B",
                "https://huggingface.co/YannQi/R-4B"
            ],
            "Parameters": "4.82B",
            "Language Model": "Qwen3-4B",
            "Vision Model": "SigLip-400M",
            "Org": "",
            "Time": "2025/08/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "X-VL-4B",
            "key": 520
        },
        "GPT-5-20250807": {
            "Method": [
                "GPT-5-20250807",
                "https://openai.com/index/introducing-gpt-5/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/08/14",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "gpt-5-2025-08-07",
            "key": 521
        },
        "GPT-5-nano-20250807": {
            "Method": [
                "GPT-5-nano-20250807",
                "https://openai.com/index/introducing-gpt-5/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/08/14",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "gpt-5-nano-2025-08-07",
            "key": 522
        },
        "GPT-5-mini-20250807": {
            "Method": [
                "GPT-5-mini-20250807",
                "https://openai.com/index/introducing-gpt-5/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/08/14",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "gpt-5-mini-2025-08-07",
            "key": 523
        },
        "SenseNova-V6-5-Pro": {
            "Method": [
                "SenseNova-V6-5-Pro",
                "https://platform.sensenova.cn/technology/fusion/Pro/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "SenseTime",
            "Time": "2025/09/03",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "SenseNova-V6-5-Pro",
            "key": 524
        },
        "BlueLM-2.5-3B-0909": {
            "Method": [
                "BlueLM-2.5-3B-0909",
                "https://developers.vivo.com/product/ai/bluelm"
            ],
            "Parameters": "3B",
            "Language Model": "BlueLM-base-3B",
            "Vision Model": "Siglip2-So400M",
            "Org": "Vivo",
            "Time": "2025/09/17",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "BlueLM-2.6-3B",
            "key": 525
        },
        "SAIL-VL2-2B": {
            "Method": [
                "SAIL-VL2-2B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL2-2B"
            ],
            "Parameters": "2.73B",
            "Language Model": "Qwen3-1.7B",
            "Vision Model": "SAILViT-Huge",
            "Org": "Douyin",
            "Time": "2025/09/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL2-2B",
            "key": 526
        },
        "SAIL-VL2-8B": {
            "Method": [
                "SAIL-VL2-8B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL2-8B"
            ],
            "Parameters": "8.91B",
            "Language Model": "Qwen3-8B",
            "Vision Model": "SAILViT-Huge",
            "Org": "Douyin",
            "Time": "2025/09/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL2-8B",
            "key": 527
        },
        "JT-VL-Chat-Mini": {
            "Method": [
                "JT-VL-Chat-Mini",
                "https://github.com/jiutiancv/JT-VL-Chat/tree/main"
            ],
            "Parameters": "3.8B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "China Mobile",
            "Time": "2025/10/26",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "JTVL-Mini",
            "key": 528
        },
        "JT-VL-Chat-2B": {
            "Method": [
                "JT-VL-Chat-2B",
                "https://github.com/jiutiancv/JT-VL-Chat/tree/main"
            ],
            "Parameters": "2B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "China Mobile",
            "Time": "2025/11/10",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "JTVL-2B",
            "key": 529
        },
        "RBDashMM3-DPO-38B": {
            "Method": [
                "RBDashMM3-DPO-38B",
                "https://huggingface.co/RBDash-Team/RBDash-v2.0"
            ],
            "Parameters": "38B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "RBDash Team",
            "Time": "2025/11/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "rbdashmm3_DPO_38B_api",
            "key": 530
        },
        "Valley3": {
            "Method": [
                "Valley3",
                "https://huggingface.co/bytedance-research/Valley3"
            ],
            "Parameters": "9B",
            "Language Model": "Qwen3-8B",
            "Vision Model": "Qwen2-VL-ViT",
            "Org": "ByteDance",
            "Time": "2025/11/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "valley3",
            "key": 531
        },
        "MiniCPM-V-4": {
            "Method": [
                "MiniCPM-V-4",
                "https://huggingface.co/openbmb/MiniCPM-V-4"
            ],
            "Parameters": "4.1B",
            "Language Model": "MiniCPM4-3B",
            "Vision Model": "SigLIP2-400M",
            "Org": "OpenBMB",
            "Time": "2025/11/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MiniCPM-V-4",
            "key": 532
        },
        "MiniCPM-V-4_5": {
            "Method": [
                "MiniCPM-V-4_5",
                "https://huggingface.co/openbmb/MiniCPM-V-4_5"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen3-8B",
            "Vision Model": "SigLIP2-400M",
            "Org": "OpenBMB",
            "Time": "2025/11/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MiniCPM-V-4_5",
            "key": 533
        }
    },
    "MMBench_TEST_EN_V11_Data": [
        {
            "Overall": 41.6,
            "AR": 54.3,
            "CP": 44.6,
            "FP-C": 36.3,
            "FP-S": 50.8,
            "LR": 13.6,
            "RR": 33.3,
            "action_recognition": 65.0,
            "attribute_comparison": 21.3,
            "attribute_recognition": 59.6,
            "celebrity_recognition": 72.8,
            "function_reasoning": 67.8,
            "future_prediction": 22.7,
            "identity_reasoning": 76.3,
            "image_emotion": 25.6,
            "image_quality": 0.8,
            "image_scene": 58.3,
            "image_style": 57.6,
            "image_topic": 88.9,
            "nature_relation": 29.3,
            "object_localization": 4.8,
            "ocr": 60.0,
            "physical_property_reasoning": 17.7,
            "physical_relation": 6.7,
            "social_relation": 59.3,
            "spatial_relationship": 6.7,
            "structuralized_imagetext_understanding": 7.3,
            "key": 23,
            "Method": [
                "Qwen-VL",
                "https://github.com/QwenLM/Qwen-VL"
            ],
            "Parameters": "9.6B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-G/16",
            "Org": "Alibaba",
            "Time": "2023/8/24",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 60.8,
            "AR": 78.4,
            "CP": 67.8,
            "FP-C": 49.8,
            "FP-S": 67.7,
            "LR": 37.0,
            "RR": 46.5,
            "action_recognition": 77.8,
            "attribute_comparison": 32.0,
            "attribute_recognition": 77.5,
            "celebrity_recognition": 84.4,
            "function_reasoning": 90.0,
            "future_prediction": 61.3,
            "identity_reasoning": 93.4,
            "image_emotion": 66.7,
            "image_quality": 27.4,
            "image_scene": 81.2,
            "image_style": 72.8,
            "image_topic": 97.8,
            "nature_relation": 53.3,
            "object_localization": 20.0,
            "ocr": 86.7,
            "physical_property_reasoning": 50.6,
            "physical_relation": 20.0,
            "social_relation": 61.5,
            "spatial_relationship": 24.0,
            "structuralized_imagetext_understanding": 20.2,
            "key": 24,
            "Method": [
                "Qwen-VL-Chat",
                "https://github.com/QwenLM/Qwen-VL"
            ],
            "Parameters": "9.6B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-G/16",
            "Org": "Alibaba",
            "Time": "2023/8/24",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 39.7,
            "AR": 62.0,
            "CP": 52.0,
            "FP-C": 27.3,
            "FP-S": 29.0,
            "LR": 19.6,
            "RR": 38.0,
            "action_recognition": 45.3,
            "attribute_comparison": 14.7,
            "attribute_recognition": 52.8,
            "celebrity_recognition": 32.0,
            "function_reasoning": 56.7,
            "future_prediction": 42.7,
            "identity_reasoning": 85.5,
            "image_emotion": 37.8,
            "image_quality": 18.5,
            "image_scene": 66.7,
            "image_style": 62.0,
            "image_topic": 78.9,
            "nature_relation": 37.0,
            "object_localization": 11.4,
            "ocr": 21.1,
            "physical_property_reasoning": 45.6,
            "physical_relation": 13.3,
            "social_relation": 59.3,
            "spatial_relationship": 12.0,
            "structuralized_imagetext_understanding": 3.7,
            "Method": [
                "PandaGPT-13B",
                "https://arxiv.org/abs/2305.16355"
            ],
            "Parameters": "14B",
            "Language Model": "Vicuna 13B",
            "Vision Model": "ImageBind ViT-H/14",
            "Org": "Tencent AI Lab",
            "Time": "2023/5/25",
            "key": 25,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 2.4,
            "AR": 5.3,
            "CP": 1.1,
            "FP-C": 1.5,
            "FP-S": 3.5,
            "LR": 0.0,
            "RR": 3.1,
            "action_recognition": 0.0,
            "attribute_comparison": 4.0,
            "attribute_recognition": 5.6,
            "celebrity_recognition": 4.8,
            "function_reasoning": 0.0,
            "future_prediction": 0.0,
            "identity_reasoning": 7.9,
            "image_emotion": 0.0,
            "image_quality": 3.2,
            "image_scene": 0.7,
            "image_style": 1.1,
            "image_topic": 0.0,
            "nature_relation": 7.6,
            "object_localization": 0.0,
            "ocr": 3.3,
            "physical_property_reasoning": 8.9,
            "physical_relation": 1.3,
            "social_relation": 0.0,
            "spatial_relationship": 1.3,
            "structuralized_imagetext_understanding": 0.0,
            "key": 1,
            "Method": [
                "OpenFlamingo v2",
                "https://github.com/mlfoundations/open_flamingo"
            ],
            "Parameters": "9B",
            "Language Model": "MPT 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "The University of Washington",
            "Time": "2023/6/28",
            "Verified": "No",
            "OpenSource": "Yes"
        },
        {
            "Overall": 64.6,
            "AR": 71.4,
            "CP": 72.0,
            "FP-C": 60.7,
            "FP-S": 68.4,
            "LR": 35.3,
            "RR": 60.9,
            "action_recognition": 79.5,
            "attribute_comparison": 60.0,
            "attribute_recognition": 75.3,
            "celebrity_recognition": 69.4,
            "function_reasoning": 86.7,
            "future_prediction": 64.0,
            "identity_reasoning": 94.7,
            "image_emotion": 77.8,
            "image_quality": 36.3,
            "image_scene": 81.9,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 65.2,
            "object_localization": 48.6,
            "ocr": 83.3,
            "physical_property_reasoning": 31.6,
            "physical_relation": 37.3,
            "social_relation": 75.8,
            "spatial_relationship": 32.0,
            "structuralized_imagetext_understanding": 15.6,
            "Method": [
                "ShareGPT4V-7B",
                "https://sharegpt4v.github.io"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 184
        },
        {
            "Overall": 67.5,
            "AR": 73.5,
            "CP": 75.6,
            "FP-C": 59.2,
            "FP-S": 74.0,
            "LR": 37.5,
            "RR": 64.0,
            "action_recognition": 76.9,
            "attribute_comparison": 60.0,
            "attribute_recognition": 83.1,
            "celebrity_recognition": 76.9,
            "function_reasoning": 86.7,
            "future_prediction": 65.3,
            "identity_reasoning": 96.1,
            "image_emotion": 76.7,
            "image_quality": 43.5,
            "image_scene": 87.5,
            "image_style": 77.2,
            "image_topic": 97.8,
            "nature_relation": 62.0,
            "object_localization": 51.4,
            "ocr": 86.7,
            "physical_property_reasoning": 36.7,
            "physical_relation": 44.0,
            "social_relation": 82.4,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 18.3,
            "Method": [
                "ShareGPT4V-13B",
                "https://sharegpt4v.github.io"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 185
        },
        {
            "Overall": 67.7,
            "AR": 74.7,
            "CP": 74.6,
            "FP-C": 57.3,
            "FP-S": 75.9,
            "LR": 44.6,
            "RR": 60.1,
            "action_recognition": 76.1,
            "attribute_comparison": 52.0,
            "attribute_recognition": 78.7,
            "celebrity_recognition": 74.8,
            "function_reasoning": 90.0,
            "future_prediction": 73.3,
            "identity_reasoning": 92.1,
            "image_emotion": 72.2,
            "image_quality": 46.0,
            "image_scene": 88.9,
            "image_style": 70.7,
            "image_topic": 97.8,
            "nature_relation": 64.1,
            "object_localization": 65.7,
            "ocr": 86.7,
            "physical_property_reasoning": 40.5,
            "physical_relation": 38.7,
            "social_relation": 73.6,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 24.8,
            "Method": [
                "TransCore-M",
                "https://github.com/PCIResearch/TransCore-M"
            ],
            "Parameters": "13.4B",
            "Language Model": "PCITransGPT-13B",
            "Vision Model": "CLIP ViT/L-14",
            "Org": "PCI Research",
            "Time": "2024/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 236
        },
        {
            "Overall": 38.4,
            "AR": 55.5,
            "CP": 46.7,
            "FP-C": 32.2,
            "FP-S": 38.7,
            "LR": 9.2,
            "RR": 31.4,
            "action_recognition": 59.0,
            "attribute_comparison": 4.0,
            "attribute_recognition": 50.6,
            "celebrity_recognition": 51.0,
            "function_reasoning": 65.6,
            "future_prediction": 21.3,
            "identity_reasoning": 81.6,
            "image_emotion": 43.3,
            "image_quality": 5.6,
            "image_scene": 70.1,
            "image_style": 38.0,
            "image_topic": 77.8,
            "nature_relation": 27.2,
            "object_localization": 10.5,
            "ocr": 40.0,
            "physical_property_reasoning": 19.0,
            "physical_relation": 21.3,
            "social_relation": 44.0,
            "spatial_relationship": 18.7,
            "structuralized_imagetext_understanding": 0.9,
            "key": 7,
            "Method": [
                "InstructBLIP-7B",
                "https://arxiv.org/abs/2305.06500"
            ],
            "Parameters": "8B",
            "Language Model": "Vicuna 7B",
            "Vision Model": "EVA-G",
            "Org": "Salesforce Research",
            "Time": "2023/5/11",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 36.7,
            "AR": 47.8,
            "CP": 43.9,
            "FP-C": 26.6,
            "FP-S": 38.5,
            "LR": 21.2,
            "RR": 29.8,
            "action_recognition": 53.8,
            "attribute_comparison": 2.7,
            "attribute_recognition": 46.1,
            "celebrity_recognition": 46.9,
            "function_reasoning": 48.9,
            "future_prediction": 42.7,
            "identity_reasoning": 80.3,
            "image_emotion": 38.9,
            "image_quality": 0.0,
            "image_scene": 65.3,
            "image_style": 38.0,
            "image_topic": 81.1,
            "nature_relation": 21.7,
            "object_localization": 1.0,
            "ocr": 61.1,
            "physical_property_reasoning": 15.2,
            "physical_relation": 16.0,
            "social_relation": 49.5,
            "spatial_relationship": 8.0,
            "structuralized_imagetext_understanding": 6.4,
            "Method": [
                "VisualGLM",
                "https://github.com/THUDM/VisualGLM-6B"
            ],
            "Parameters": "8B",
            "Language Model": "ChatGLM 6B",
            "Vision Model": "EVA-CLIP",
            "Org": "Tsinghua University",
            "Time": "2023/5/17",
            "key": 41,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 63.5,
            "AR": 78.4,
            "CP": 68.1,
            "FP-C": 55.8,
            "FP-S": 69.1,
            "LR": 37.0,
            "RR": 57.0,
            "action_recognition": 78.6,
            "attribute_comparison": 44.0,
            "attribute_recognition": 77.5,
            "celebrity_recognition": 82.3,
            "function_reasoning": 90.0,
            "future_prediction": 61.3,
            "identity_reasoning": 96.1,
            "image_emotion": 72.2,
            "image_quality": 18.5,
            "image_scene": 87.5,
            "image_style": 71.7,
            "image_topic": 97.8,
            "nature_relation": 64.1,
            "object_localization": 29.5,
            "ocr": 85.6,
            "physical_property_reasoning": 48.1,
            "physical_relation": 17.3,
            "social_relation": 82.4,
            "spatial_relationship": 32.0,
            "structuralized_imagetext_understanding": 20.2,
            "Method": [
                "mPLUG-Owl2",
                "https://github.com/X-PLUG/mPLUG-Owl/tree/main/mPLUG-Owl2"
            ],
            "Parameters": "8.2B",
            "Language Model": "LLaMA2 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "DAMO Academy",
            "Time": "2023/11/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 32
        },
        {
            "Overall": 63.6,
            "AR": 71.4,
            "CP": 72.8,
            "FP-C": 55.4,
            "FP-S": 66.6,
            "LR": 33.7,
            "RR": 62.0,
            "action_recognition": 82.9,
            "attribute_comparison": 44.0,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 78.2,
            "function_reasoning": 83.3,
            "future_prediction": 58.7,
            "identity_reasoning": 94.7,
            "image_emotion": 70.0,
            "image_quality": 37.1,
            "image_scene": 86.1,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 79.3,
            "object_localization": 19.0,
            "ocr": 85.6,
            "physical_property_reasoning": 35.4,
            "physical_relation": 20.0,
            "social_relation": 79.1,
            "spatial_relationship": 24.0,
            "structuralized_imagetext_understanding": 16.5,
            "Method": [
                "CogVLM-17B-Chat",
                "https://huggingface.co/THUDM/cogvlm-chat-hf"
            ],
            "Parameters": "17B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "EVA2-CLIP-E",
            "Org": "Zhipu AI",
            "Time": "2024/01/03",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 75
        },
        {
            "Overall": 63.9,
            "AR": 79.6,
            "CP": 59.3,
            "FP-C": 61.8,
            "FP-S": 74.5,
            "LR": 34.2,
            "RR": 64.7,
            "action_recognition": 80.3,
            "attribute_comparison": 64.0,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 72.8,
            "function_reasoning": 84.4,
            "future_prediction": 54.7,
            "identity_reasoning": 98.7,
            "image_emotion": 46.7,
            "image_quality": 45.2,
            "image_scene": 72.9,
            "image_style": 39.1,
            "image_topic": 90.0,
            "nature_relation": 69.6,
            "object_localization": 66.7,
            "ocr": 81.1,
            "physical_property_reasoning": 55.7,
            "physical_relation": 53.3,
            "social_relation": 69.2,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 20.2,
            "Method": [
                "ShareCaptioner",
                "https://huggingface.co/Lin-Chen/ShareCaptioner/"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM-7B",
            "Vision Model": "EVA-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 245
        },
        {
            "Overall": 57.4,
            "AR": 77.6,
            "CP": 64.6,
            "FP-C": 45.3,
            "FP-S": 62.2,
            "LR": 30.4,
            "RR": 46.5,
            "action_recognition": 80.3,
            "attribute_comparison": 26.7,
            "attribute_recognition": 74.2,
            "celebrity_recognition": 81.6,
            "function_reasoning": 83.3,
            "future_prediction": 60.0,
            "identity_reasoning": 94.7,
            "image_emotion": 70.0,
            "image_quality": 12.9,
            "image_scene": 81.2,
            "image_style": 71.7,
            "image_topic": 96.7,
            "nature_relation": 48.9,
            "object_localization": 11.4,
            "ocr": 77.8,
            "physical_property_reasoning": 54.4,
            "physical_relation": 14.7,
            "social_relation": 70.3,
            "spatial_relationship": 9.3,
            "structuralized_imagetext_understanding": 10.1,
            "Method": [
                "Monkey",
                "https://github.com/Yuliang-Liu/Monkey"
            ],
            "Parameters": "9.8B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-BigHuge",
            "Org": "Huazhong University of Science and Technology",
            "Time": "2024/01/11",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 79
        },
        {
            "Overall": 69.6,
            "AR": 82.4,
            "CP": 75.0,
            "FP-C": 63.3,
            "FP-S": 75.4,
            "LR": 47.3,
            "RR": 58.9,
            "action_recognition": 87.2,
            "attribute_comparison": 54.7,
            "attribute_recognition": 82.0,
            "celebrity_recognition": 89.1,
            "function_reasoning": 87.8,
            "future_prediction": 72.0,
            "identity_reasoning": 97.4,
            "image_emotion": 76.7,
            "image_quality": 40.3,
            "image_scene": 86.8,
            "image_style": 79.3,
            "image_topic": 97.8,
            "nature_relation": 62.0,
            "object_localization": 38.1,
            "ocr": 90.0,
            "physical_property_reasoning": 62.0,
            "physical_relation": 34.7,
            "social_relation": 75.8,
            "spatial_relationship": 34.7,
            "structuralized_imagetext_understanding": 30.3,
            "Method": [
                "Monkey-Chat",
                "https://github.com/Yuliang-Liu/Monkey"
            ],
            "Parameters": "9.8B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-BigHuge",
            "Org": "Huazhong University of Science and Technology",
            "Time": "2024/01/16",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 97
        },
        {
            "Overall": 5.0,
            "AR": 14.7,
            "CP": 3.9,
            "FP-C": 1.5,
            "FP-S": 3.5,
            "LR": 3.8,
            "RR": 5.0,
            "action_recognition": 0.0,
            "attribute_comparison": 2.7,
            "attribute_recognition": 5.6,
            "celebrity_recognition": 4.8,
            "function_reasoning": 6.7,
            "future_prediction": 8.0,
            "identity_reasoning": 28.9,
            "image_emotion": 0.0,
            "image_quality": 1.6,
            "image_scene": 10.4,
            "image_style": 1.1,
            "image_topic": 3.3,
            "nature_relation": 7.6,
            "object_localization": 0.0,
            "ocr": 3.3,
            "physical_property_reasoning": 10.1,
            "physical_relation": 5.3,
            "social_relation": 2.2,
            "spatial_relationship": 2.7,
            "structuralized_imagetext_understanding": 0.9,
            "Method": [
                "MiniGPT-4-v2",
                "https://minigpt-v2.github.io"
            ],
            "Parameters": "8B",
            "Language Model": "LLaMA2 13B",
            "Vision Model": "EVA-G",
            "Org": "King Abdullah University of Science and Technology",
            "Time": "2023/10/27",
            "key": 31,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 30.9,
            "AR": 49.8,
            "CP": 37.4,
            "FP-C": 17.6,
            "FP-S": 32.7,
            "LR": 8.7,
            "RR": 26.0,
            "action_recognition": 31.6,
            "attribute_comparison": 5.3,
            "attribute_recognition": 48.3,
            "celebrity_recognition": 32.0,
            "function_reasoning": 47.8,
            "future_prediction": 16.0,
            "identity_reasoning": 77.6,
            "image_emotion": 41.1,
            "image_quality": 2.4,
            "image_scene": 60.4,
            "image_style": 28.3,
            "image_topic": 54.4,
            "nature_relation": 20.7,
            "object_localization": 12.4,
            "ocr": 42.2,
            "physical_property_reasoning": 25.3,
            "physical_relation": 13.3,
            "social_relation": 41.8,
            "spatial_relationship": 8.0,
            "structuralized_imagetext_understanding": 3.7,
            "key": 3,
            "Method": [
                "MiniGPT-4-v1-7B",
                "https://arxiv.org/abs/2304.10592"
            ],
            "Parameters": "8B",
            "Language Model": "Vicuna 7B",
            "Vision Model": "EVA-G",
            "Org": "King Abdullah University of Science and Technology",
            "Time": "2023/4/20",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 61.3,
            "AR": 74.7,
            "CP": 65.9,
            "FP-C": 59.2,
            "FP-S": 65.7,
            "LR": 29.9,
            "RR": 56.2,
            "action_recognition": 88.0,
            "attribute_comparison": 38.7,
            "attribute_recognition": 82.0,
            "celebrity_recognition": 76.9,
            "function_reasoning": 85.6,
            "future_prediction": 64.0,
            "identity_reasoning": 97.4,
            "image_emotion": 67.8,
            "image_quality": 11.3,
            "image_scene": 86.8,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 68.5,
            "object_localization": 28.6,
            "ocr": 74.4,
            "physical_property_reasoning": 40.5,
            "physical_relation": 21.3,
            "social_relation": 72.5,
            "spatial_relationship": 34.7,
            "structuralized_imagetext_understanding": 6.4,
            "Method": [
                "Emu2_chat",
                "https://github.com/baaivision/Emu/tree/main/Emu2"
            ],
            "Parameters": "37B",
            "Language Model": "LLaMA-33B",
            "Vision Model": "EVA-02-CLIP-E-plus",
            "Org": "Beijing Academy of Artificial Intelligence",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 86
        },
        {
            "Overall": 65.2,
            "AR": 76.3,
            "CP": 73.3,
            "FP-C": 55.4,
            "FP-S": 73.1,
            "LR": 38.6,
            "RR": 53.9,
            "action_recognition": 81.2,
            "attribute_comparison": 44.0,
            "attribute_recognition": 75.3,
            "celebrity_recognition": 81.0,
            "function_reasoning": 87.8,
            "future_prediction": 61.3,
            "identity_reasoning": 96.1,
            "image_emotion": 71.1,
            "image_quality": 35.5,
            "image_scene": 90.3,
            "image_style": 75.0,
            "image_topic": 98.9,
            "nature_relation": 48.9,
            "object_localization": 45.7,
            "ocr": 90.0,
            "physical_property_reasoning": 44.3,
            "physical_relation": 28.0,
            "social_relation": 80.2,
            "spatial_relationship": 26.7,
            "structuralized_imagetext_understanding": 22.9,
            "Method": [
                "Yi-VL-6B",
                "https://huggingface.co/01-ai/Yi-VL-6B"
            ],
            "Parameters": "6.6B",
            "Language Model": "Yi-6B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "01-AI",
            "Time": "2024/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 189
        },
        {
            "Overall": 68.7,
            "AR": 80.8,
            "CP": 72.4,
            "FP-C": 55.1,
            "FP-S": 78.0,
            "LR": 40.2,
            "RR": 68.2,
            "action_recognition": 76.9,
            "attribute_comparison": 41.3,
            "attribute_recognition": 82.0,
            "celebrity_recognition": 81.6,
            "function_reasoning": 92.2,
            "future_prediction": 64.0,
            "identity_reasoning": 96.1,
            "image_emotion": 72.2,
            "image_quality": 39.5,
            "image_scene": 84.0,
            "image_style": 72.8,
            "image_topic": 98.9,
            "nature_relation": 72.8,
            "object_localization": 58.1,
            "ocr": 91.1,
            "physical_property_reasoning": 53.2,
            "physical_relation": 41.3,
            "social_relation": 85.7,
            "spatial_relationship": 34.7,
            "structuralized_imagetext_understanding": 23.9,
            "Method": [
                "Yi-VL-34B",
                "https://huggingface.co/01-ai/Yi-VL-34B"
            ],
            "Parameters": "34.6B",
            "Language Model": "Yi-34B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "01-AI",
            "Time": "2024/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 190
        },
        {
            "Overall": 55.7,
            "AR": 72.7,
            "CP": 63.0,
            "FP-C": 52.8,
            "FP-S": 52.9,
            "LR": 28.8,
            "RR": 51.2,
            "action_recognition": 77.8,
            "attribute_comparison": 38.7,
            "attribute_recognition": 69.7,
            "celebrity_recognition": 63.3,
            "function_reasoning": 75.6,
            "future_prediction": 57.3,
            "identity_reasoning": 94.7,
            "image_emotion": 68.9,
            "image_quality": 11.3,
            "image_scene": 85.4,
            "image_style": 59.8,
            "image_topic": 95.6,
            "nature_relation": 58.7,
            "object_localization": 21.9,
            "ocr": 55.6,
            "physical_property_reasoning": 48.1,
            "physical_relation": 18.7,
            "social_relation": 70.3,
            "spatial_relationship": 28.0,
            "structuralized_imagetext_understanding": 9.2,
            "Method": [
                "MMAlaya",
                "https://huggingface.co/DataCanvas/MMAlaya"
            ],
            "Parameters": "7.8B",
            "Language Model": "Alaya-7B-Chat",
            "Vision Model": "EVA-G",
            "Org": "DataCanvas",
            "Time": "2024/01/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 134
        },
        {
            "Overall": 69.2,
            "AR": 77.6,
            "CP": 71.3,
            "FP-C": 61.4,
            "FP-S": 80.7,
            "LR": 39.1,
            "RR": 67.1,
            "action_recognition": 84.6,
            "attribute_comparison": 56.0,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 84.4,
            "function_reasoning": 90.0,
            "future_prediction": 60.0,
            "identity_reasoning": 97.4,
            "image_emotion": 73.3,
            "image_quality": 32.3,
            "image_scene": 84.0,
            "image_style": 77.2,
            "image_topic": 96.7,
            "nature_relation": 66.3,
            "object_localization": 60.0,
            "ocr": 91.1,
            "physical_property_reasoning": 44.3,
            "physical_relation": 48.0,
            "social_relation": 83.5,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 24.8,
            "Method": [
                "OmniLMM-12B",
                "https://huggingface.co/openbmb/OmniLMM-12B"
            ],
            "Parameters": "12B",
            "Language Model": "Zephyr-7B-β",
            "Vision Model": "EVA-02-5B",
            "Org": "OpenBMB",
            "Time": "2024/02/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 145
        },
        {
            "Overall": 61.4,
            "AR": 70.6,
            "CP": 65.6,
            "FP-C": 50.9,
            "FP-S": 69.4,
            "LR": 35.3,
            "RR": 59.7,
            "action_recognition": 83.8,
            "attribute_comparison": 32.0,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 77.6,
            "function_reasoning": 88.9,
            "future_prediction": 62.7,
            "identity_reasoning": 94.7,
            "image_emotion": 68.9,
            "image_quality": 14.5,
            "image_scene": 85.4,
            "image_style": 68.5,
            "image_topic": 97.8,
            "nature_relation": 68.5,
            "object_localization": 31.4,
            "ocr": 85.6,
            "physical_property_reasoning": 26.6,
            "physical_relation": 25.3,
            "social_relation": 79.1,
            "spatial_relationship": 18.7,
            "structuralized_imagetext_understanding": 16.5,
            "Method": [
                "MiniCPM-V",
                "https://huggingface.co/openbmb/MiniCPM-V"
            ],
            "Parameters": "3B",
            "Language Model": "MiniCPM-2.4B",
            "Vision Model": "SigLip-400M",
            "Org": "OpenBMB",
            "Time": "2024/02/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 146
        },
        {
            "Overall": 67.0,
            "AR": 79.6,
            "CP": 70.2,
            "FP-C": 55.8,
            "FP-S": 72.2,
            "LR": 44.6,
            "RR": 67.4,
            "action_recognition": 86.3,
            "attribute_comparison": 42.7,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 82.3,
            "function_reasoning": 92.2,
            "future_prediction": 66.7,
            "identity_reasoning": 96.1,
            "image_emotion": 74.4,
            "image_quality": 25.8,
            "image_scene": 86.8,
            "image_style": 72.8,
            "image_topic": 97.8,
            "nature_relation": 71.7,
            "object_localization": 32.4,
            "ocr": 90.0,
            "physical_property_reasoning": 49.4,
            "physical_relation": 42.7,
            "social_relation": 83.5,
            "spatial_relationship": 21.3,
            "structuralized_imagetext_understanding": 29.4,
            "Method": [
                "MiniCPM-V-2",
                "https://huggingface.co/openbmb/MiniCPM-V-2"
            ],
            "Parameters": "2.8B",
            "Vision Model": "SigLip-400M",
            "Language Model": "MiniCPM-2.4B",
            "Org": "OpenBMB",
            "Time": "2024/04/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 231
        },
        {
            "Overall": 65.6,
            "AR": 80.4,
            "CP": 72.8,
            "FP-C": 57.7,
            "FP-S": 69.6,
            "LR": 33.7,
            "RR": 60.5,
            "action_recognition": 84.6,
            "attribute_comparison": 49.3,
            "attribute_recognition": 82.0,
            "celebrity_recognition": 67.3,
            "function_reasoning": 90.0,
            "future_prediction": 58.7,
            "identity_reasoning": 92.1,
            "image_emotion": 74.4,
            "image_quality": 41.9,
            "image_scene": 86.1,
            "image_style": 67.4,
            "image_topic": 97.8,
            "nature_relation": 58.7,
            "object_localization": 49.5,
            "ocr": 84.4,
            "physical_property_reasoning": 58.2,
            "physical_relation": 40.0,
            "social_relation": 79.1,
            "spatial_relationship": 24.0,
            "structuralized_imagetext_understanding": 16.5,
            "Method": [
                "DeepSeek-VL-1.3B",
                "https://github.com/deepseek-ai/DeepSeek-VL"
            ],
            "Parameters": "2.0B",
            "Language Model": "DeekSeek-1B",
            "Vision Model": "SAM-B\nSigLIP-L",
            "Org": "DeepSeek",
            "Time": "2024/03/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 201
        },
        {
            "Overall": 71.7,
            "AR": 81.2,
            "CP": 76.5,
            "FP-C": 66.7,
            "FP-S": 75.9,
            "LR": 47.8,
            "RR": 67.8,
            "action_recognition": 87.2,
            "attribute_comparison": 64.0,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 77.6,
            "function_reasoning": 91.1,
            "future_prediction": 64.0,
            "identity_reasoning": 97.4,
            "image_emotion": 75.6,
            "image_quality": 46.0,
            "image_scene": 88.2,
            "image_style": 80.4,
            "image_topic": 96.7,
            "nature_relation": 72.8,
            "object_localization": 51.4,
            "ocr": 90.0,
            "physical_property_reasoning": 54.4,
            "physical_relation": 38.7,
            "social_relation": 86.8,
            "spatial_relationship": 37.3,
            "structuralized_imagetext_understanding": 36.7,
            "Method": [
                "DeepSeek-VL-7B",
                "https://github.com/deepseek-ai/DeepSeek-VL"
            ],
            "Parameters": "7.3B",
            "Language Model": "DeekSeek-7B",
            "Vision Model": "SAM-B\nSigLIP-L",
            "Org": "DeepSeek",
            "Time": "2024/03/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 202
        },
        {
            "Overall": 72.1,
            "AR": 73.1,
            "CP": 78.3,
            "FP-C": 67.4,
            "FP-S": 79.4,
            "LR": 42.4,
            "RR": 72.1,
            "action_recognition": 81.2,
            "attribute_comparison": 74.7,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 78.9,
            "function_reasoning": 86.7,
            "future_prediction": 69.3,
            "identity_reasoning": 96.1,
            "image_emotion": 80.0,
            "image_quality": 53.2,
            "image_scene": 88.2,
            "image_style": 76.1,
            "image_topic": 97.8,
            "nature_relation": 75.0,
            "object_localization": 68.6,
            "ocr": 83.3,
            "physical_property_reasoning": 35.4,
            "physical_relation": 60.0,
            "social_relation": 79.1,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 23.9,
            "Method": [
                "XVERSE-V-13B",
                "https://github.com/xverse-ai/XVERSE-V-13B"
            ],
            "Parameters": "13B",
            "Language Model": "XVERSE-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "XVERSE",
            "Time": "2024/05/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 256
        },
        {
            "Overall": 76.0,
            "AR": 87.8,
            "CP": 75.7,
            "FP-C": 72.7,
            "FP-S": 84.7,
            "LR": 50.5,
            "RR": 72.5,
            "action_recognition": 81.2,
            "attribute_comparison": 61.3,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 81.0,
            "function_reasoning": 95.6,
            "future_prediction": 76.0,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 41.9,
            "image_scene": 86.8,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 79.3,
            "object_localization": 80.0,
            "ocr": 90.0,
            "physical_property_reasoning": 69.6,
            "physical_relation": 58.7,
            "social_relation": 76.9,
            "spatial_relationship": 70.7,
            "structuralized_imagetext_understanding": 33.0,
            "Method": [
                "360VL-70B",
                "https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5"
            ],
            "Parameters": "70B",
            "Language Model": "Llama-3-70B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "QiHoo360",
            "Time": "2024/05/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 264
        },
        {
            "Overall": 74.0,
            "AR": 78.8,
            "CP": 76.3,
            "FP-C": 62.2,
            "FP-S": 83.5,
            "LR": 58.2,
            "RR": 72.1,
            "action_recognition": 82.1,
            "attribute_comparison": 53.3,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 84.4,
            "function_reasoning": 91.1,
            "future_prediction": 70.7,
            "identity_reasoning": 96.1,
            "image_emotion": 73.3,
            "image_quality": 43.5,
            "image_scene": 88.2,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 69.6,
            "object_localization": 69.5,
            "ocr": 90.0,
            "physical_property_reasoning": 48.1,
            "physical_relation": 61.3,
            "social_relation": 83.5,
            "spatial_relationship": 40.0,
            "structuralized_imagetext_understanding": 49.5,
            "Method": [
                "MiniCPM-Llama3-V2.5",
                "https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLip-400M",
            "Org": "OpenBMB",
            "Time": "2024/05/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 265
        },
        {
            "Overall": 70.5,
            "AR": 73.5,
            "CP": 74.8,
            "FP-C": 59.6,
            "FP-S": 76.6,
            "LR": 60.3,
            "RR": 67.4,
            "action_recognition": 72.6,
            "attribute_comparison": 60.0,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 73.5,
            "function_reasoning": 82.2,
            "future_prediction": 70.7,
            "identity_reasoning": 96.1,
            "image_emotion": 71.1,
            "image_quality": 47.6,
            "image_scene": 88.9,
            "image_style": 70.7,
            "image_topic": 97.8,
            "nature_relation": 66.3,
            "object_localization": 63.8,
            "ocr": 86.7,
            "physical_property_reasoning": 41.8,
            "physical_relation": 53.3,
            "social_relation": 80.2,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 53.2,
            "Method": [
                "Phi-3-Vision",
                "https://huggingface.co/microsoft/Phi-3-vision-128k-instruct"
            ],
            "Parameters": "4.2B",
            "Language Model": "Phi-3",
            "Vision Model": "CLIP ViT/L-14",
            "Org": "Microsoft",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 268
        },
        {
            "Overall": 72.7,
            "AR": 80.8,
            "CP": 75.0,
            "FP-C": 63.3,
            "FP-S": 76.6,
            "LR": 53.3,
            "RR": 77.1,
            "action_recognition": 84.6,
            "attribute_comparison": 57.3,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 85.7,
            "function_reasoning": 88.9,
            "future_prediction": 70.7,
            "identity_reasoning": 97.4,
            "image_emotion": 76.7,
            "image_quality": 42.7,
            "image_scene": 88.2,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 88.0,
            "object_localization": 41.9,
            "ocr": 92.2,
            "physical_property_reasoning": 55.7,
            "physical_relation": 56.0,
            "social_relation": 83.5,
            "spatial_relationship": 36.0,
            "structuralized_imagetext_understanding": 41.3,
            "Method": [
                "CogVLM2-19B-Chat",
                "https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B"
            ],
            "Parameters": "19B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "EVA2-CLIP-E",
            "Org": "Zhipu AI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 269
        },
        {
            "Overall": 77.8,
            "AR": 83.3,
            "CP": 80.2,
            "FP-C": 72.7,
            "FP-S": 83.5,
            "LR": 63.6,
            "RR": 73.6,
            "action_recognition": 83.8,
            "attribute_comparison": 77.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 83.7,
            "function_reasoning": 93.3,
            "future_prediction": 76.0,
            "identity_reasoning": 96.1,
            "image_emotion": 75.6,
            "image_quality": 56.5,
            "image_scene": 91.0,
            "image_style": 81.5,
            "image_topic": 98.9,
            "nature_relation": 78.3,
            "object_localization": 73.3,
            "ocr": 90.0,
            "physical_property_reasoning": 59.5,
            "physical_relation": 57.3,
            "social_relation": 82.4,
            "spatial_relationship": 50.7,
            "structuralized_imagetext_understanding": 55.0,
            "Method": [
                "WeMM",
                "https://github.com/scenarios/WeMM/tree/main"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "SigLip-400M",
            "Org": "WechatCV",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 273
        },
        {
            "Overall": 35.2,
            "AR": 47.8,
            "CP": 48.1,
            "FP-C": 29.6,
            "FP-S": 31.3,
            "LR": 10.9,
            "RR": 25.6,
            "action_recognition": 53.8,
            "attribute_comparison": 18.7,
            "attribute_recognition": 31.5,
            "celebrity_recognition": 42.9,
            "function_reasoning": 46.7,
            "future_prediction": 26.7,
            "identity_reasoning": 76.3,
            "image_emotion": 51.1,
            "image_quality": 5.6,
            "image_scene": 58.3,
            "image_style": 48.9,
            "image_topic": 86.7,
            "nature_relation": 23.9,
            "object_localization": 7.6,
            "ocr": 40.0,
            "physical_property_reasoning": 21.5,
            "physical_relation": 9.3,
            "social_relation": 40.7,
            "spatial_relationship": 2.7,
            "structuralized_imagetext_understanding": 0.0,
            "key": 18,
            "Method": [
                "IDEFICS-9B-Instruct",
                "https://huggingface.co/HuggingFaceM4/idefics-9b-instruct"
            ],
            "Language Model": "LLaMA 7B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "Hugging Face",
            "Time": "2023/7/25",
            "Parameters": "9B",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 11.3,
            "AR": 12.7,
            "CP": 13.1,
            "FP-C": 7.1,
            "FP-S": 9.0,
            "LR": 8.2,
            "RR": 16.7,
            "action_recognition": 6.8,
            "attribute_comparison": 9.3,
            "attribute_recognition": 6.7,
            "celebrity_recognition": 7.5,
            "function_reasoning": 12.2,
            "future_prediction": 14.7,
            "identity_reasoning": 15.8,
            "image_emotion": 23.3,
            "image_quality": 6.5,
            "image_scene": 15.3,
            "image_style": 13.0,
            "image_topic": 8.9,
            "nature_relation": 14.1,
            "object_localization": 4.8,
            "ocr": 18.9,
            "physical_property_reasoning": 10.1,
            "physical_relation": 10.7,
            "social_relation": 24.2,
            "spatial_relationship": 5.3,
            "structuralized_imagetext_understanding": 3.7,
            "key": 19,
            "Method": [
                "IDEFICS-80B-Instruct",
                "https://huggingface.co/HuggingFaceM4/idefics-80b-instruct"
            ],
            "Language Model": "LLaMA65B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "Hugging Face",
            "Time": "2023/7/25",
            "Parameters": "80B",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 72.7,
            "AR": 84.9,
            "CP": 74.4,
            "FP-C": 67.0,
            "FP-S": 78.9,
            "LR": 50.5,
            "RR": 68.6,
            "action_recognition": 88.0,
            "attribute_comparison": 65.3,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 89.1,
            "function_reasoning": 91.1,
            "future_prediction": 69.3,
            "identity_reasoning": 97.4,
            "image_emotion": 76.7,
            "image_quality": 40.3,
            "image_scene": 84.0,
            "image_style": 79.3,
            "image_topic": 98.9,
            "nature_relation": 76.1,
            "object_localization": 49.5,
            "ocr": 88.9,
            "physical_property_reasoning": 65.8,
            "physical_relation": 42.7,
            "social_relation": 82.4,
            "spatial_relationship": 36.0,
            "structuralized_imagetext_understanding": 37.6,
            "Method": [
                "IDEFICS2-8B",
                "https://huggingface.co/HuggingFaceM4/idefics2-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Mistral-7B",
            "Vision Model": "SigLip-400M",
            "Org": "Hugging Face",
            "Time": "2024/04/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 248
        },
        {
            "Overall": 6.4,
            "AR": 7.8,
            "CP": 5.7,
            "FP-C": 4.9,
            "FP-S": 7.7,
            "LR": 3.3,
            "RR": 8.1,
            "action_recognition": 8.5,
            "attribute_comparison": 1.3,
            "attribute_recognition": 5.6,
            "celebrity_recognition": 10.2,
            "function_reasoning": 7.8,
            "future_prediction": 1.3,
            "identity_reasoning": 6.6,
            "image_emotion": 0.0,
            "image_quality": 6.5,
            "image_scene": 9.7,
            "image_style": 1.1,
            "image_topic": 8.9,
            "nature_relation": 15.2,
            "object_localization": 9.5,
            "ocr": 3.3,
            "physical_property_reasoning": 8.9,
            "physical_relation": 5.3,
            "social_relation": 3.3,
            "spatial_relationship": 2.7,
            "structuralized_imagetext_understanding": 4.6,
            "key": 22,
            "Method": [
                "InternLM-XComposer",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM-7B",
            "Vision Model": "EVA-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/9/26",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 78.1,
            "AR": 83.7,
            "CP": 80.4,
            "FP-C": 73.0,
            "FP-S": 83.5,
            "LR": 63.6,
            "RR": 74.4,
            "action_recognition": 83.8,
            "attribute_comparison": 77.3,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 78.9,
            "function_reasoning": 84.4,
            "future_prediction": 74.7,
            "identity_reasoning": 94.7,
            "image_emotion": 80.0,
            "image_quality": 61.3,
            "image_scene": 89.6,
            "image_style": 75.0,
            "image_topic": 97.8,
            "nature_relation": 79.3,
            "object_localization": 77.1,
            "ocr": 90.0,
            "physical_property_reasoning": 72.2,
            "physical_relation": 64.0,
            "social_relation": 78.0,
            "spatial_relationship": 52.0,
            "structuralized_imagetext_understanding": 56.0,
            "Method": [
                "InternLM-XComposer2",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 132
        },
        {
            "Overall": 70.4,
            "AR": 80.0,
            "CP": 74.4,
            "FP-C": 63.3,
            "FP-S": 74.9,
            "LR": 50.5,
            "RR": 66.7,
            "action_recognition": 81.2,
            "attribute_comparison": 58.7,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 65.3,
            "function_reasoning": 78.9,
            "future_prediction": 62.7,
            "identity_reasoning": 97.4,
            "image_emotion": 74.4,
            "image_quality": 50.8,
            "image_scene": 86.1,
            "image_style": 66.3,
            "image_topic": 96.7,
            "nature_relation": 65.2,
            "object_localization": 69.5,
            "ocr": 86.7,
            "physical_property_reasoning": 64.6,
            "physical_relation": 57.3,
            "social_relation": 75.8,
            "spatial_relationship": 40.0,
            "structuralized_imagetext_understanding": 42.2,
            "Method": [
                "InternLM-XComposer2-1.8B",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 275
        },
        {
            "Overall": 77.0,
            "AR": 84.5,
            "CP": 78.0,
            "FP-C": 68.9,
            "FP-S": 82.8,
            "LR": 66.3,
            "RR": 74.0,
            "action_recognition": 81.2,
            "attribute_comparison": 66.7,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 78.2,
            "function_reasoning": 84.4,
            "future_prediction": 73.3,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 57.3,
            "image_scene": 84.0,
            "image_style": 76.1,
            "image_topic": 97.8,
            "nature_relation": 75.0,
            "object_localization": 78.1,
            "ocr": 90.0,
            "physical_property_reasoning": 72.2,
            "physical_relation": 65.3,
            "social_relation": 80.2,
            "spatial_relationship": 52.0,
            "structuralized_imagetext_understanding": 61.5,
            "Method": [
                "InternLM-XComposer2-4KHD",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 276
        },
        {
            "Overall": 80.3,
            "AR": 86.5,
            "CP": 80.4,
            "FP-C": 77.2,
            "FP-S": 86.1,
            "LR": 65.2,
            "RR": 78.7,
            "action_recognition": 93.2,
            "attribute_comparison": 81.3,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 83.7,
            "function_reasoning": 96.7,
            "future_prediction": 78.7,
            "identity_reasoning": 98.7,
            "image_emotion": 78.9,
            "image_quality": 59.7,
            "image_scene": 88.9,
            "image_style": 80.4,
            "image_topic": 96.7,
            "nature_relation": 83.7,
            "object_localization": 76.2,
            "ocr": 92.2,
            "physical_property_reasoning": 63.3,
            "physical_relation": 68.0,
            "social_relation": 82.4,
            "spatial_relationship": 48.0,
            "structuralized_imagetext_understanding": 56.0,
            "Method": [
                "InternVL-Chat-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/04/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 241
        },
        {
            "Overall": 41.6,
            "AR": 57.1,
            "CP": 56.9,
            "FP-C": 26.6,
            "FP-S": 39.0,
            "LR": 18.5,
            "RR": 31.0,
            "action_recognition": 42.7,
            "attribute_comparison": 21.3,
            "attribute_recognition": 52.8,
            "celebrity_recognition": 39.5,
            "function_reasoning": 48.9,
            "future_prediction": 38.7,
            "identity_reasoning": 89.5,
            "image_emotion": 61.1,
            "image_quality": 16.9,
            "image_scene": 72.2,
            "image_style": 55.4,
            "image_topic": 84.4,
            "nature_relation": 32.6,
            "object_localization": 9.5,
            "ocr": 58.9,
            "physical_property_reasoning": 35.4,
            "physical_relation": 14.7,
            "social_relation": 42.9,
            "spatial_relationship": 6.7,
            "structuralized_imagetext_understanding": 4.6,
            "Method": [
                "LLaVA-v1-7B",
                "https://arxiv.org/abs/2304.08485"
            ],
            "Parameters": "7.2B",
            "Language Model": "LLaMA 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin-Madison",
            "Time": "2023/4/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 187
        },
        {
            "Overall": 66.0,
            "AR": 80.0,
            "CP": 72.6,
            "FP-C": 57.3,
            "FP-S": 68.7,
            "LR": 38.0,
            "RR": 63.2,
            "action_recognition": 78.6,
            "attribute_comparison": 56.0,
            "attribute_recognition": 80.9,
            "celebrity_recognition": 71.4,
            "function_reasoning": 85.6,
            "future_prediction": 68.0,
            "identity_reasoning": 96.1,
            "image_emotion": 77.8,
            "image_quality": 41.9,
            "image_scene": 83.3,
            "image_style": 67.4,
            "image_topic": 97.8,
            "nature_relation": 71.7,
            "object_localization": 39.0,
            "ocr": 86.7,
            "physical_property_reasoning": 58.2,
            "physical_relation": 37.3,
            "social_relation": 75.8,
            "spatial_relationship": 25.3,
            "structuralized_imagetext_understanding": 17.4,
            "Method": [
                "LLaVA-InternLM-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "7.6B",
            "Language Model": "InternLM-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 70
        },
        {
            "Overall": 64.7,
            "AR": 77.1,
            "CP": 71.3,
            "FP-C": 57.3,
            "FP-S": 70.1,
            "LR": 34.8,
            "RR": 58.9,
            "action_recognition": 75.2,
            "attribute_comparison": 56.0,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 73.5,
            "function_reasoning": 84.4,
            "future_prediction": 68.0,
            "identity_reasoning": 96.1,
            "image_emotion": 73.3,
            "image_quality": 35.5,
            "image_scene": 86.1,
            "image_style": 69.6,
            "image_topic": 96.7,
            "nature_relation": 60.9,
            "object_localization": 44.8,
            "ocr": 84.4,
            "physical_property_reasoning": 50.6,
            "physical_relation": 29.3,
            "social_relation": 81.3,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 11.9,
            "Method": [
                "LLaVA-v1.5-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 71
        },
        {
            "Overall": 67.0,
            "AR": 78.4,
            "CP": 74.6,
            "FP-C": 60.3,
            "FP-S": 70.1,
            "LR": 42.4,
            "RR": 59.3,
            "action_recognition": 81.2,
            "attribute_comparison": 50.7,
            "attribute_recognition": 77.5,
            "celebrity_recognition": 71.4,
            "function_reasoning": 85.6,
            "future_prediction": 70.7,
            "identity_reasoning": 98.7,
            "image_emotion": 76.7,
            "image_quality": 46.8,
            "image_scene": 86.1,
            "image_style": 70.7,
            "image_topic": 96.7,
            "nature_relation": 65.2,
            "object_localization": 50.5,
            "ocr": 83.3,
            "physical_property_reasoning": 50.6,
            "physical_relation": 32.0,
            "social_relation": 75.8,
            "spatial_relationship": 37.3,
            "structuralized_imagetext_understanding": 22.9,
            "Method": [
                "LLaVA-v1.5-13B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 72
        },
        {
            "Overall": 68.5,
            "AR": 79.6,
            "CP": 72.6,
            "FP-C": 65.2,
            "FP-S": 72.4,
            "LR": 42.4,
            "RR": 64.7,
            "action_recognition": 78.6,
            "attribute_comparison": 72.0,
            "attribute_recognition": 80.9,
            "celebrity_recognition": 71.4,
            "function_reasoning": 85.6,
            "future_prediction": 65.3,
            "identity_reasoning": 96.1,
            "image_emotion": 74.4,
            "image_quality": 41.9,
            "image_scene": 82.6,
            "image_style": 71.7,
            "image_topic": 97.8,
            "nature_relation": 63.0,
            "object_localization": 58.1,
            "ocr": 82.2,
            "physical_property_reasoning": 57.0,
            "physical_relation": 42.7,
            "social_relation": 84.6,
            "spatial_relationship": 37.3,
            "structuralized_imagetext_understanding": 26.6,
            "Method": [
                "LLaVA-LLaMA-3-8B",
                "https://huggingface.co/xtuner/llava-llama-3-8b-v1_1"
            ],
            "Parameters": "8B",
            "Language Model": "LLaMA-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/05/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 254
        },
        {
            "Overall": 71.9,
            "AR": 80.8,
            "CP": 76.7,
            "FP-C": 67.0,
            "FP-S": 77.3,
            "LR": 46.2,
            "RR": 68.2,
            "action_recognition": 81.2,
            "attribute_comparison": 66.7,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 74.8,
            "function_reasoning": 84.4,
            "future_prediction": 72.0,
            "identity_reasoning": 98.7,
            "image_emotion": 73.3,
            "image_quality": 48.4,
            "image_scene": 88.9,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 73.9,
            "object_localization": 66.7,
            "ocr": 86.7,
            "physical_property_reasoning": 59.5,
            "physical_relation": 45.3,
            "social_relation": 81.3,
            "spatial_relationship": 45.3,
            "structuralized_imagetext_understanding": 28.4,
            "Method": [
                "LLaVA-InternLM2-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "8.1B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 91
        },
        {
            "Overall": 72.3,
            "AR": 78.4,
            "CP": 78.3,
            "FP-C": 68.2,
            "FP-S": 76.6,
            "LR": 46.2,
            "RR": 69.4,
            "action_recognition": 80.3,
            "attribute_comparison": 68.0,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 74.1,
            "function_reasoning": 91.1,
            "future_prediction": 76.0,
            "identity_reasoning": 96.1,
            "image_emotion": 80.0,
            "image_quality": 48.4,
            "image_scene": 91.0,
            "image_style": 77.2,
            "image_topic": 98.9,
            "nature_relation": 71.7,
            "object_localization": 64.8,
            "ocr": 85.6,
            "physical_property_reasoning": 46.8,
            "physical_relation": 50.7,
            "social_relation": 82.4,
            "spatial_relationship": 49.3,
            "structuralized_imagetext_understanding": 25.7,
            "Method": [
                "LLaVA-InternLM2-20B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "20.2B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 92
        },
        {
            "Overall": 66.5,
            "AR": 77.1,
            "CP": 72.4,
            "FP-C": 59.9,
            "FP-S": 73.5,
            "LR": 39.1,
            "RR": 58.9,
            "action_recognition": 82.9,
            "attribute_comparison": 57.3,
            "attribute_recognition": 82.0,
            "celebrity_recognition": 72.1,
            "function_reasoning": 84.4,
            "future_prediction": 65.3,
            "identity_reasoning": 97.4,
            "image_emotion": 75.6,
            "image_quality": 38.7,
            "image_scene": 81.2,
            "image_style": 76.1,
            "image_topic": 97.8,
            "nature_relation": 63.0,
            "object_localization": 58.1,
            "ocr": 85.6,
            "physical_property_reasoning": 49.4,
            "physical_relation": 34.7,
            "social_relation": 74.7,
            "spatial_relationship": 26.7,
            "structuralized_imagetext_understanding": 21.1,
            "Method": [
                "LLaVA-Next-Vicuna-7B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "7.1B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 210
        },
        {
            "Overall": 66.5,
            "AR": 78.4,
            "CP": 70.9,
            "FP-C": 60.3,
            "FP-S": 69.8,
            "LR": 45.7,
            "RR": 61.6,
            "action_recognition": 76.9,
            "attribute_comparison": 62.7,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 64.6,
            "function_reasoning": 84.4,
            "future_prediction": 72.0,
            "identity_reasoning": 93.4,
            "image_emotion": 75.6,
            "image_quality": 39.5,
            "image_scene": 80.6,
            "image_style": 67.4,
            "image_topic": 97.8,
            "nature_relation": 60.9,
            "object_localization": 53.3,
            "ocr": 83.3,
            "physical_property_reasoning": 57.0,
            "physical_relation": 45.3,
            "social_relation": 75.8,
            "spatial_relationship": 32.0,
            "structuralized_imagetext_understanding": 27.5,
            "Method": [
                "LLaVA-Next-Mistral-7B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "7.6B",
            "Language Model": "Mistral-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 211
        },
        {
            "Overall": 67.3,
            "AR": 76.3,
            "CP": 72.6,
            "FP-C": 60.7,
            "FP-S": 72.2,
            "LR": 42.4,
            "RR": 64.3,
            "action_recognition": 78.6,
            "attribute_comparison": 62.7,
            "attribute_recognition": 78.7,
            "celebrity_recognition": 74.1,
            "function_reasoning": 83.3,
            "future_prediction": 65.3,
            "identity_reasoning": 97.4,
            "image_emotion": 73.3,
            "image_quality": 37.9,
            "image_scene": 86.1,
            "image_style": 72.8,
            "image_topic": 97.8,
            "nature_relation": 67.4,
            "object_localization": 52.4,
            "ocr": 85.6,
            "physical_property_reasoning": 48.1,
            "physical_relation": 40.0,
            "social_relation": 81.3,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 26.6,
            "Method": [
                "LLaVA-Next-Vicuna-13B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 212
        },
        {
            "Overall": 78.5,
            "AR": 85.7,
            "CP": 78.0,
            "FP-C": 77.9,
            "FP-S": 83.3,
            "LR": 64.7,
            "RR": 75.6,
            "action_recognition": 85.5,
            "attribute_comparison": 78.7,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 83.0,
            "function_reasoning": 92.2,
            "future_prediction": 77.3,
            "identity_reasoning": 96.1,
            "image_emotion": 81.1,
            "image_quality": 48.4,
            "image_scene": 86.1,
            "image_style": 82.6,
            "image_topic": 97.8,
            "nature_relation": 83.7,
            "object_localization": 74.3,
            "ocr": 92.2,
            "physical_property_reasoning": 68.4,
            "physical_relation": 53.3,
            "social_relation": 85.7,
            "spatial_relationship": 65.3,
            "structuralized_imagetext_understanding": 56.0,
            "Method": [
                "LLaVA-Next-Yi-34B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "34.8B",
            "Language Model": "Yi-34B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 213
        },
        {
            "Overall": 68.4,
            "AR": 83.7,
            "CP": 73.7,
            "FP-C": 58.8,
            "FP-S": 69.1,
            "LR": 41.8,
            "RR": 70.5,
            "action_recognition": 82.9,
            "attribute_comparison": 48.0,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 72.8,
            "function_reasoning": 88.9,
            "future_prediction": 70.7,
            "identity_reasoning": 96.1,
            "image_emotion": 74.4,
            "image_quality": 40.3,
            "image_scene": 88.2,
            "image_style": 73.9,
            "image_topic": 95.6,
            "nature_relation": 70.7,
            "object_localization": 41.0,
            "ocr": 74.4,
            "physical_property_reasoning": 65.8,
            "physical_relation": 54.7,
            "social_relation": 83.5,
            "spatial_relationship": 32.0,
            "structuralized_imagetext_understanding": 22.0,
            "Method": [
                "PaliGemma-3B-mix-448",
                "https://github.com/google-research/big_vision/blob/main/big_vision/configs/proj/paligemma/README.md"
            ],
            "Parameters": "3B",
            "Language Model": "Gemma-2B",
            "Vision Model": "SigLip-400M",
            "Org": "Google",
            "Time": "2024/05/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 261
        },
        {
            "Overall": 75.3,
            "AR": 86.1,
            "CP": 78.3,
            "FP-C": 71.9,
            "FP-S": 74.5,
            "LR": 64.1,
            "RR": 71.3,
            "action_recognition": 86.3,
            "attribute_comparison": 53.3,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 66.7,
            "function_reasoning": 93.3,
            "future_prediction": 68.0,
            "identity_reasoning": 94.7,
            "image_emotion": 81.1,
            "image_quality": 50.8,
            "image_scene": 87.5,
            "image_style": 80.4,
            "image_topic": 96.7,
            "nature_relation": 89.1,
            "object_localization": 57.1,
            "ocr": 95.6,
            "physical_property_reasoning": 69.6,
            "physical_relation": 48.0,
            "social_relation": 72.5,
            "spatial_relationship": 68.0,
            "structuralized_imagetext_understanding": 61.5,
            "Method": [
                "GPT-4v (1106, detail-low)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2023/12/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 242
        },
        {
            "Overall": 65.4,
            "AR": 79.6,
            "CP": 68.7,
            "FP-C": 57.7,
            "FP-S": 65.4,
            "LR": 59.8,
            "RR": 57.0,
            "action_recognition": 73.5,
            "attribute_comparison": 46.7,
            "attribute_recognition": 78.7,
            "celebrity_recognition": 61.2,
            "function_reasoning": 88.9,
            "future_prediction": 65.3,
            "identity_reasoning": 96.1,
            "image_emotion": 56.7,
            "image_quality": 37.9,
            "image_scene": 81.9,
            "image_style": 76.1,
            "image_topic": 94.4,
            "nature_relation": 68.5,
            "object_localization": 36.2,
            "ocr": 93.3,
            "physical_property_reasoning": 53.2,
            "physical_relation": 33.3,
            "social_relation": 64.8,
            "spatial_relationship": 44.0,
            "structuralized_imagetext_understanding": 56.0,
            "Method": [
                "GPT-4v (1106, detail-high)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/04/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 243
        },
        {
            "Overall": 79.3,
            "AR": 87.3,
            "CP": 78.7,
            "FP-C": 73.4,
            "FP-S": 84.9,
            "LR": 72.3,
            "RR": 74.4,
            "action_recognition": 85.5,
            "attribute_comparison": 60.0,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 93.9,
            "function_reasoning": 94.4,
            "future_prediction": 78.7,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 52.4,
            "image_scene": 86.8,
            "image_style": 83.7,
            "image_topic": 96.7,
            "nature_relation": 90.2,
            "object_localization": 57.1,
            "ocr": 98.9,
            "physical_property_reasoning": 69.6,
            "physical_relation": 46.7,
            "social_relation": 81.3,
            "spatial_relationship": 68.0,
            "structuralized_imagetext_understanding": 67.9,
            "Method": [
                "GPT-4v (0409, detail-low)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 244
        },
        {
            "Overall": 80.0,
            "AR": 86.1,
            "CP": 79.4,
            "FP-C": 74.2,
            "FP-S": 86.5,
            "LR": 74.5,
            "RR": 74.4,
            "action_recognition": 88.0,
            "attribute_comparison": 58.7,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 95.2,
            "function_reasoning": 93.3,
            "future_prediction": 80.0,
            "identity_reasoning": 96.1,
            "image_emotion": 81.1,
            "image_quality": 52.4,
            "image_scene": 88.2,
            "image_style": 83.7,
            "image_topic": 96.7,
            "nature_relation": 89.1,
            "object_localization": 61.9,
            "ocr": 98.9,
            "physical_property_reasoning": 68.4,
            "physical_relation": 45.3,
            "social_relation": 83.5,
            "spatial_relationship": 68.0,
            "structuralized_imagetext_understanding": 70.6,
            "Method": [
                "GPT-4v (0409, detail-high)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 246
        },
        {
            "Overall": 83.1,
            "AR": 89.8,
            "CP": 81.7,
            "FP-C": 87.3,
            "FP-S": 82.4,
            "LR": 77.2,
            "RR": 80.6,
            "action_recognition": 94.9,
            "attribute_comparison": 84.0,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 65.3,
            "function_reasoning": 93.3,
            "future_prediction": 81.3,
            "identity_reasoning": 98.7,
            "image_emotion": 82.2,
            "image_quality": 60.5,
            "image_scene": 88.2,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 82.9,
            "ocr": 100.0,
            "physical_property_reasoning": 77.2,
            "physical_relation": 57.3,
            "social_relation": 86.8,
            "spatial_relationship": 78.7,
            "structuralized_imagetext_understanding": 74.3,
            "Method": [
                "GPT-4o (0513, detail-low)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 260
        },
        {
            "Overall": 83.0,
            "AR": 90.2,
            "CP": 81.3,
            "FP-C": 86.1,
            "FP-S": 81.4,
            "LR": 78.8,
            "RR": 82.2,
            "action_recognition": 93.2,
            "attribute_comparison": 82.7,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 62.6,
            "function_reasoning": 93.3,
            "future_prediction": 82.7,
            "identity_reasoning": 98.7,
            "image_emotion": 81.1,
            "image_quality": 59.7,
            "image_scene": 88.2,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 92.4,
            "object_localization": 84.8,
            "ocr": 98.9,
            "physical_property_reasoning": 78.5,
            "physical_relation": 61.3,
            "social_relation": 89.0,
            "spatial_relationship": 78.7,
            "structuralized_imagetext_understanding": 76.1,
            "Method": [
                "GPT-4o (0513, detail-high)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 270
        },
        {
            "Overall": 70.2,
            "AR": 82.9,
            "CP": 70.0,
            "FP-C": 65.9,
            "FP-S": 78.9,
            "LR": 46.2,
            "RR": 65.9,
            "action_recognition": 86.3,
            "attribute_comparison": 50.7,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 89.8,
            "function_reasoning": 92.2,
            "future_prediction": 56.0,
            "identity_reasoning": 96.1,
            "image_emotion": 77.8,
            "image_quality": 30.6,
            "image_scene": 79.9,
            "image_style": 77.2,
            "image_topic": 93.3,
            "nature_relation": 85.9,
            "object_localization": 50.5,
            "ocr": 88.9,
            "physical_property_reasoning": 59.5,
            "physical_relation": 30.7,
            "social_relation": 74.7,
            "spatial_relationship": 49.3,
            "structuralized_imagetext_understanding": 39.4,
            "Method": [
                "Gemini-1.0-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2023/12/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 101
        },
        {
            "Overall": 64.3,
            "AR": 73.5,
            "CP": 65.4,
            "FP-C": 50.2,
            "FP-S": 79.1,
            "LR": 41.3,
            "RR": 59.7,
            "action_recognition": 76.1,
            "attribute_comparison": 33.3,
            "attribute_recognition": 82.0,
            "celebrity_recognition": 88.4,
            "function_reasoning": 90.0,
            "future_prediction": 37.3,
            "identity_reasoning": 94.7,
            "image_emotion": 73.3,
            "image_quality": 25.0,
            "image_scene": 75.7,
            "image_style": 72.8,
            "image_topic": 88.9,
            "nature_relation": 71.7,
            "object_localization": 53.3,
            "ocr": 91.1,
            "physical_property_reasoning": 34.2,
            "physical_relation": 24.0,
            "social_relation": 76.9,
            "spatial_relationship": 26.7,
            "structuralized_imagetext_understanding": 44.0,
            "Method": [
                "Qwen-VL-Plus",
                "https://github.com/QwenLM/Qwen-VL?tab=readme-ov-file#qwen-vl-plus"
            ],
            "Parameters": "",
            "Language Model": "QwenLM",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/01/10",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 77
        },
        {
            "Overall": 75.4,
            "AR": 86.1,
            "CP": 74.8,
            "FP-C": 67.0,
            "FP-S": 87.0,
            "LR": 54.3,
            "RR": 70.5,
            "action_recognition": 91.5,
            "attribute_comparison": 53.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 94.6,
            "function_reasoning": 94.4,
            "future_prediction": 58.7,
            "identity_reasoning": 96.1,
            "image_emotion": 81.1,
            "image_quality": 41.1,
            "image_scene": 84.0,
            "image_style": 78.3,
            "image_topic": 96.7,
            "nature_relation": 81.5,
            "object_localization": 68.6,
            "ocr": 94.4,
            "physical_property_reasoning": 67.1,
            "physical_relation": 44.0,
            "social_relation": 81.3,
            "spatial_relationship": 42.7,
            "structuralized_imagetext_understanding": 51.4,
            "Method": [
                "Qwen-VL-Max",
                "https://huggingface.co/spaces/Qwen/Qwen-VL-Max"
            ],
            "Parameters": "",
            "Language Model": "QwenLM",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 136
        },
        {
            "Overall": 58.0,
            "AR": 75.9,
            "CP": 66.7,
            "FP-C": 41.2,
            "FP-S": 56.8,
            "LR": 48.4,
            "RR": 49.2,
            "action_recognition": 59.8,
            "attribute_comparison": 29.3,
            "attribute_recognition": 76.4,
            "celebrity_recognition": 44.9,
            "function_reasoning": 91.1,
            "future_prediction": 61.3,
            "identity_reasoning": 89.5,
            "image_emotion": 62.2,
            "image_quality": 27.4,
            "image_scene": 85.4,
            "image_style": 70.7,
            "image_topic": 91.1,
            "nature_relation": 52.2,
            "object_localization": 27.6,
            "ocr": 91.1,
            "physical_property_reasoning": 45.6,
            "physical_relation": 21.3,
            "social_relation": 69.2,
            "spatial_relationship": 24.0,
            "structuralized_imagetext_understanding": 39.4,
            "Method": [
                "Claude3-Haiku",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 217
        },
        {
            "Overall": 64.2,
            "AR": 76.3,
            "CP": 68.3,
            "FP-C": 55.8,
            "FP-S": 65.4,
            "LR": 57.6,
            "RR": 55.0,
            "action_recognition": 62.4,
            "attribute_comparison": 56.0,
            "attribute_recognition": 78.7,
            "celebrity_recognition": 61.9,
            "function_reasoning": 92.2,
            "future_prediction": 66.7,
            "identity_reasoning": 92.1,
            "image_emotion": 64.4,
            "image_quality": 33.9,
            "image_scene": 79.9,
            "image_style": 76.1,
            "image_topic": 93.3,
            "nature_relation": 63.0,
            "object_localization": 39.0,
            "ocr": 88.9,
            "physical_property_reasoning": 43.0,
            "physical_relation": 26.7,
            "social_relation": 70.3,
            "spatial_relationship": 45.3,
            "structuralized_imagetext_understanding": 51.4,
            "Method": [
                "Claude3-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 218
        },
        {
            "Overall": 60.1,
            "AR": 75.9,
            "CP": 68.0,
            "FP-C": 46.8,
            "FP-S": 59.2,
            "LR": 52.2,
            "RR": 49.2,
            "action_recognition": 59.0,
            "attribute_comparison": 36.0,
            "attribute_recognition": 80.9,
            "celebrity_recognition": 46.9,
            "function_reasoning": 82.2,
            "future_prediction": 61.3,
            "identity_reasoning": 92.1,
            "image_emotion": 58.9,
            "image_quality": 31.5,
            "image_scene": 83.3,
            "image_style": 78.3,
            "image_topic": 92.2,
            "nature_relation": 46.7,
            "object_localization": 31.4,
            "ocr": 90.0,
            "physical_property_reasoning": 53.2,
            "physical_relation": 24.0,
            "social_relation": 72.5,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 45.9,
            "Method": [
                "Claude3-Opus",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 219
        },
        {
            "Overall": 74.5,
            "AR": 80.8,
            "CP": 76.5,
            "FP-C": 69.3,
            "FP-S": 78.0,
            "LR": 62.5,
            "RR": 72.9,
            "action_recognition": 83.8,
            "attribute_comparison": 61.3,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 74.1,
            "function_reasoning": 93.3,
            "future_prediction": 69.3,
            "identity_reasoning": 97.4,
            "image_emotion": 77.8,
            "image_quality": 47.6,
            "image_scene": 83.3,
            "image_style": 82.6,
            "image_topic": 97.8,
            "nature_relation": 81.5,
            "object_localization": 61.0,
            "ocr": 92.2,
            "physical_property_reasoning": 50.6,
            "physical_relation": 57.3,
            "social_relation": 76.9,
            "spatial_relationship": 54.7,
            "structuralized_imagetext_understanding": 57.8,
            "Method": [
                "RekaFlash",
                "https://www.reka.ai"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Reka AI",
            "Time": "2024/05/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 262
        },
        {
            "Overall": 63.6,
            "AR": 78.8,
            "CP": 71.1,
            "FP-C": 50.6,
            "FP-S": 68.9,
            "LR": 30.4,
            "RR": 62.0,
            "action_recognition": 82.9,
            "attribute_comparison": 26.7,
            "attribute_recognition": 83.1,
            "celebrity_recognition": 75.5,
            "function_reasoning": 91.1,
            "future_prediction": 58.7,
            "identity_reasoning": 96.1,
            "image_emotion": 73.3,
            "image_quality": 32.3,
            "image_scene": 84.7,
            "image_style": 75.0,
            "image_topic": 96.7,
            "nature_relation": 70.7,
            "object_localization": 32.4,
            "ocr": 86.7,
            "physical_property_reasoning": 48.1,
            "physical_relation": 28.0,
            "social_relation": 81.3,
            "spatial_relationship": 24.0,
            "structuralized_imagetext_understanding": 11.0,
            "Method": [
                "RekaEdge",
                "https://www.reka.ai"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Reka AI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 271
        },
        {
            "Overall": 79.2,
            "AR": 89.0,
            "CP": 78.7,
            "FP-C": 74.9,
            "FP-S": 83.1,
            "LR": 66.3,
            "RR": 78.3,
            "action_recognition": 92.3,
            "attribute_comparison": 72.0,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 91.8,
            "function_reasoning": 94.4,
            "future_prediction": 73.3,
            "identity_reasoning": 98.7,
            "image_emotion": 82.2,
            "image_quality": 50.8,
            "image_scene": 88.2,
            "image_style": 80.4,
            "image_topic": 96.7,
            "nature_relation": 80.4,
            "object_localization": 54.3,
            "ocr": 91.1,
            "physical_property_reasoning": 73.4,
            "physical_relation": 62.7,
            "social_relation": 89.0,
            "spatial_relationship": 50.7,
            "structuralized_imagetext_understanding": 61.5,
            "Method": [
                "GLM-4v",
                "https://open.bigmodel.cn/dev/api#glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2024/05/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 263
        },
        {
            "Overall": 67.5,
            "AR": 74.7,
            "CP": 74.3,
            "FP-C": 59.6,
            "FP-S": 71.2,
            "LR": 48.4,
            "RR": 62.0,
            "action_recognition": 84.6,
            "attribute_comparison": 49.3,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 68.7,
            "function_reasoning": 84.4,
            "future_prediction": 65.3,
            "identity_reasoning": 94.7,
            "image_emotion": 74.4,
            "image_quality": 43.5,
            "image_scene": 88.2,
            "image_style": 70.7,
            "image_topic": 97.8,
            "nature_relation": 57.6,
            "object_localization": 48.6,
            "ocr": 85.6,
            "physical_property_reasoning": 44.3,
            "physical_relation": 49.3,
            "social_relation": 76.9,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 36.7,
            "Method": [
                "Mini-InternVL-Chat-2B-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 277
        },
        {
            "Overall": 72.6,
            "AR": 79.6,
            "CP": 73.3,
            "FP-C": 67.4,
            "FP-S": 77.7,
            "LR": 59.2,
            "RR": 70.9,
            "action_recognition": 79.5,
            "attribute_comparison": 72.0,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 67.3,
            "function_reasoning": 88.9,
            "future_prediction": 69.3,
            "identity_reasoning": 96.1,
            "image_emotion": 66.7,
            "image_quality": 46.8,
            "image_scene": 86.1,
            "image_style": 72.8,
            "image_topic": 96.7,
            "nature_relation": 70.7,
            "object_localization": 69.5,
            "ocr": 90.0,
            "physical_property_reasoning": 53.2,
            "physical_relation": 56.0,
            "social_relation": 83.5,
            "spatial_relationship": 44.0,
            "structuralized_imagetext_understanding": 52.3,
            "Method": [
                "Mini-InternVL-Chat-4B-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 278
        },
        {
            "Overall": 74.6,
            "AR": 81.6,
            "CP": 72.4,
            "FP-C": 74.5,
            "FP-S": 81.2,
            "LR": 63.6,
            "RR": 69.4,
            "action_recognition": 85.5,
            "attribute_comparison": 65.3,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 84.4,
            "function_reasoning": 85.6,
            "future_prediction": 61.3,
            "identity_reasoning": 94.7,
            "image_emotion": 74.4,
            "image_quality": 49.2,
            "image_scene": 84.7,
            "image_style": 79.3,
            "image_topic": 75.6,
            "nature_relation": 83.7,
            "object_localization": 69.5,
            "ocr": 77.8,
            "physical_property_reasoning": 64.6,
            "physical_relation": 52.0,
            "social_relation": 69.2,
            "spatial_relationship": 66.7,
            "structuralized_imagetext_understanding": 65.1,
            "Method": [
                "Gemini-1.5-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 279
        },
        {
            "Overall": 68.7,
            "AR": 76.3,
            "CP": 65.2,
            "FP-C": 64.0,
            "FP-S": 79.6,
            "LR": 58.2,
            "RR": 63.2,
            "action_recognition": 81.2,
            "attribute_comparison": 64.0,
            "attribute_recognition": 83.1,
            "celebrity_recognition": 87.1,
            "function_reasoning": 85.6,
            "future_prediction": 58.7,
            "identity_reasoning": 88.2,
            "image_emotion": 63.3,
            "image_quality": 44.4,
            "image_scene": 69.4,
            "image_style": 65.2,
            "image_topic": 88.9,
            "nature_relation": 70.7,
            "object_localization": 62.9,
            "ocr": 83.3,
            "physical_property_reasoning": 54.4,
            "physical_relation": 57.3,
            "social_relation": 60.4,
            "spatial_relationship": 37.3,
            "structuralized_imagetext_understanding": 57.8,
            "Method": [
                "GLM-4v-9B",
                "https://huggingface.co/THUDM/glm-4v-9b"
            ],
            "Parameters": "9B",
            "Language Model": "GLM-4-9B",
            "Vision Model": "EVA-02-5B",
            "Org": "Zhipu AI",
            "Time": "2024/06/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 281
        },
        {
            "Overall": 77.7,
            "AR": 81.6,
            "CP": 78.1,
            "FP-C": 76.0,
            "FP-S": 81.9,
            "LR": 74.5,
            "RR": 70.2,
            "action_recognition": 79.5,
            "attribute_comparison": 77.3,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 75.5,
            "function_reasoning": 91.1,
            "future_prediction": 68.0,
            "identity_reasoning": 96.1,
            "image_emotion": 66.7,
            "image_quality": 61.3,
            "image_scene": 86.8,
            "image_style": 79.3,
            "image_topic": 97.8,
            "nature_relation": 82.6,
            "object_localization": 73.3,
            "ocr": 96.7,
            "physical_property_reasoning": 57.0,
            "physical_relation": 42.7,
            "social_relation": 80.2,
            "spatial_relationship": 69.3,
            "structuralized_imagetext_understanding": 78.9,
            "Method": [
                "Claude3.5-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/06/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 284
        },
        {
            "Overall": 80.9,
            "AR": 87.8,
            "CP": 80.9,
            "FP-C": 77.9,
            "FP-S": 87.2,
            "LR": 64.1,
            "RR": 78.7,
            "action_recognition": 91.5,
            "attribute_comparison": 81.3,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 83.0,
            "function_reasoning": 96.7,
            "future_prediction": 77.3,
            "identity_reasoning": 97.4,
            "image_emotion": 77.8,
            "image_quality": 61.3,
            "image_scene": 88.9,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 84.8,
            "object_localization": 79.0,
            "ocr": 95.6,
            "physical_property_reasoning": 68.4,
            "physical_relation": 68.0,
            "social_relation": 81.3,
            "spatial_relationship": 53.3,
            "structuralized_imagetext_understanding": 55.0,
            "Method": [
                "CongRong",
                "https://mllm.cloudwalk.com/web/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "CloudWalk",
            "Time": "2024/06/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 285
        },
        {
            "Overall": 73.6,
            "AR": 81.2,
            "CP": 78.1,
            "FP-C": 65.2,
            "FP-S": 80.7,
            "LR": 53.3,
            "RR": 68.2,
            "action_recognition": 87.2,
            "attribute_comparison": 64.0,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 79.6,
            "function_reasoning": 92.2,
            "future_prediction": 80.0,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 52.4,
            "image_scene": 87.5,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 79.3,
            "object_localization": 63.8,
            "ocr": 94.4,
            "physical_property_reasoning": 53.2,
            "physical_relation": 41.3,
            "social_relation": 79.1,
            "spatial_relationship": 32.0,
            "structuralized_imagetext_understanding": 34.9,
            "Method": [
                "Bumblebee-7B-v1.6",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Monolith Foundation",
            "Time": "2024/06/27",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 286
        },
        {
            "Overall": 73.5,
            "AR": 82.9,
            "CP": 79.1,
            "FP-C": 66.7,
            "FP-S": 78.7,
            "LR": 46.7,
            "RR": 70.2,
            "action_recognition": 86.3,
            "attribute_comparison": 64.0,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 80.3,
            "function_reasoning": 93.3,
            "future_prediction": 74.7,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 58.9,
            "image_scene": 88.9,
            "image_style": 75.0,
            "image_topic": 95.6,
            "nature_relation": 70.7,
            "object_localization": 65.7,
            "ocr": 82.2,
            "physical_property_reasoning": 57.0,
            "physical_relation": 46.7,
            "social_relation": 89.0,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 27.5,
            "Method": [
                "Llama-3-MixSense",
                "https://huggingface.co/Zero-Vision/Llama-3-MixSense"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "ZeroVision",
            "Time": "2024/07/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 288
        },
        {
            "Overall": 86.6,
            "AR": 91.8,
            "CP": 83.7,
            "FP-C": 86.1,
            "FP-S": 91.2,
            "LR": 78.8,
            "RR": 86.0,
            "action_recognition": 93.2,
            "attribute_comparison": 81.3,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 90.5,
            "function_reasoning": 95.6,
            "future_prediction": 81.3,
            "identity_reasoning": 98.7,
            "image_emotion": 81.1,
            "image_quality": 60.5,
            "image_scene": 91.7,
            "image_style": 91.3,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 81.9,
            "ocr": 97.8,
            "physical_property_reasoning": 81.0,
            "physical_relation": 76.0,
            "social_relation": 86.8,
            "spatial_relationship": 80.0,
            "structuralized_imagetext_understanding": 77.1,
            "Method": [
                "InternVL-2.0-Pro",
                "https://huggingface.co/spaces/OpenGVLab/InternVL/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/08",
            "Verified": "Yes",
            "OpenSource": "No",
            "key": 290
        },
        {
            "Overall": 61.6,
            "AR": 75.1,
            "CP": 69.1,
            "FP-C": 50.2,
            "FP-S": 66.1,
            "LR": 37.0,
            "RR": 55.0,
            "action_recognition": 84.6,
            "attribute_comparison": 24.0,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 63.3,
            "function_reasoning": 75.6,
            "future_prediction": 56.0,
            "identity_reasoning": 93.4,
            "image_emotion": 60.0,
            "image_quality": 37.9,
            "image_scene": 84.7,
            "image_style": 69.6,
            "image_topic": 95.6,
            "nature_relation": 52.2,
            "object_localization": 45.7,
            "ocr": 81.1,
            "physical_property_reasoning": 57.0,
            "physical_relation": 42.7,
            "social_relation": 68.1,
            "spatial_relationship": 22.7,
            "structuralized_imagetext_understanding": 23.9,
            "Method": [
                "InternVL2-1B",
                "https://huggingface.co/OpenGVLab/InternVL2-1B"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 292
        },
        {
            "Overall": 70.2,
            "AR": 79.6,
            "CP": 74.6,
            "FP-C": 61.4,
            "FP-S": 74.7,
            "LR": 48.9,
            "RR": 69.0,
            "action_recognition": 87.2,
            "attribute_comparison": 49.3,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 67.3,
            "function_reasoning": 85.6,
            "future_prediction": 56.0,
            "identity_reasoning": 96.1,
            "image_emotion": 71.1,
            "image_quality": 43.5,
            "image_scene": 90.3,
            "image_style": 72.8,
            "image_topic": 97.8,
            "nature_relation": 70.7,
            "object_localization": 57.1,
            "ocr": 90.0,
            "physical_property_reasoning": 57.0,
            "physical_relation": 52.0,
            "social_relation": 81.3,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 44.0,
            "Method": [
                "InternVL2-2B",
                "https://huggingface.co/OpenGVLab/InternVL2-2B"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 293
        },
        {
            "Overall": 75.8,
            "AR": 84.1,
            "CP": 78.5,
            "FP-C": 70.0,
            "FP-S": 80.0,
            "LR": 60.9,
            "RR": 71.7,
            "action_recognition": 86.3,
            "attribute_comparison": 70.7,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 76.9,
            "function_reasoning": 90.0,
            "future_prediction": 66.7,
            "identity_reasoning": 96.1,
            "image_emotion": 75.6,
            "image_quality": 49.2,
            "image_scene": 90.3,
            "image_style": 82.6,
            "image_topic": 98.9,
            "nature_relation": 78.3,
            "object_localization": 66.7,
            "ocr": 90.0,
            "physical_property_reasoning": 65.8,
            "physical_relation": 48.0,
            "social_relation": 84.6,
            "spatial_relationship": 44.0,
            "structuralized_imagetext_understanding": 56.9,
            "Method": [
                "InternVL2-4B",
                "https://huggingface.co/OpenGVLab/InternVL2-4B"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 294
        },
        {
            "Overall": 79.5,
            "AR": 82.9,
            "CP": 79.6,
            "FP-C": 73.4,
            "FP-S": 85.2,
            "LR": 69.0,
            "RR": 80.2,
            "action_recognition": 87.2,
            "attribute_comparison": 77.3,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 81.6,
            "function_reasoning": 90.0,
            "future_prediction": 69.3,
            "identity_reasoning": 96.1,
            "image_emotion": 78.9,
            "image_quality": 54.0,
            "image_scene": 91.7,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 82.6,
            "object_localization": 76.2,
            "ocr": 94.4,
            "physical_property_reasoning": 62.0,
            "physical_relation": 65.3,
            "social_relation": 90.1,
            "spatial_relationship": 48.0,
            "structuralized_imagetext_understanding": 68.8,
            "Method": [
                "InternVL2-8B",
                "https://huggingface.co/OpenGVLab/InternVL2-8B"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 295
        },
        {
            "Overall": 81.5,
            "AR": 88.6,
            "CP": 80.9,
            "FP-C": 76.8,
            "FP-S": 86.5,
            "LR": 70.1,
            "RR": 80.2,
            "action_recognition": 91.5,
            "attribute_comparison": 81.3,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 83.0,
            "function_reasoning": 95.6,
            "future_prediction": 80.0,
            "identity_reasoning": 98.7,
            "image_emotion": 76.7,
            "image_quality": 60.5,
            "image_scene": 88.9,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 85.9,
            "object_localization": 77.1,
            "ocr": 94.4,
            "physical_property_reasoning": 70.9,
            "physical_relation": 69.3,
            "social_relation": 83.5,
            "spatial_relationship": 49.3,
            "structuralized_imagetext_understanding": 63.3,
            "Method": [
                "InternVL2-26B",
                "https://huggingface.co/OpenGVLab/InternVL2-26B"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 296
        },
        {
            "Overall": 85.1,
            "AR": 87.3,
            "CP": 82.2,
            "FP-C": 81.3,
            "FP-S": 93.3,
            "LR": 76.1,
            "RR": 85.7,
            "action_recognition": 92.3,
            "attribute_comparison": 78.7,
            "attribute_recognition": 97.8,
            "celebrity_recognition": 91.8,
            "function_reasoning": 96.7,
            "future_prediction": 82.7,
            "identity_reasoning": 96.1,
            "image_emotion": 84.4,
            "image_quality": 61.3,
            "image_scene": 88.2,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 88.6,
            "ocr": 96.7,
            "physical_property_reasoning": 68.4,
            "physical_relation": 72.0,
            "social_relation": 89.0,
            "spatial_relationship": 66.7,
            "structuralized_imagetext_understanding": 71.6,
            "Method": [
                "InternVL2-40B",
                "https://huggingface.co/OpenGVLab/InternVL2-40B"
            ],
            "Parameters": "40B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 297
        },
        {
            "Overall": 71.6,
            "AR": 77.6,
            "CP": 75.9,
            "FP-C": 68.2,
            "FP-S": 75.6,
            "LR": 48.4,
            "RR": 70.5,
            "action_recognition": 86.3,
            "attribute_comparison": 69.3,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 61.9,
            "function_reasoning": 87.8,
            "future_prediction": 66.7,
            "identity_reasoning": 94.7,
            "image_emotion": 76.7,
            "image_quality": 47.6,
            "image_scene": 86.8,
            "image_style": 75.0,
            "image_topic": 97.8,
            "nature_relation": 76.1,
            "object_localization": 73.3,
            "ocr": 90.0,
            "physical_property_reasoning": 49.4,
            "physical_relation": 52.0,
            "social_relation": 80.2,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 35.8,
            "Method": [
                "Cambrian-8B",
                "https://huggingface.co/nyu-visionx/cambrian-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "NYU",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 298
        },
        {
            "Overall": 80.1,
            "AR": 84.9,
            "CP": 79.4,
            "FP-C": 76.8,
            "FP-S": 86.5,
            "LR": 69.6,
            "RR": 77.1,
            "action_recognition": 88.0,
            "attribute_comparison": 82.7,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 83.7,
            "function_reasoning": 87.8,
            "future_prediction": 74.7,
            "identity_reasoning": 97.4,
            "image_emotion": 76.7,
            "image_quality": 59.7,
            "image_scene": 89.6,
            "image_style": 75.0,
            "image_topic": 97.8,
            "nature_relation": 80.4,
            "object_localization": 77.1,
            "ocr": 94.4,
            "physical_property_reasoning": 69.6,
            "physical_relation": 65.3,
            "social_relation": 83.5,
            "spatial_relationship": 53.3,
            "structuralized_imagetext_understanding": 66.1,
            "Method": [
                "InternLM-XComposer2.5",
                "https://huggingface.co/internlm/internlm-xcomposer2d5-7b"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 299
        },
        {
            "Overall": 75.7,
            "AR": 78.8,
            "CP": 79.8,
            "FP-C": 65.9,
            "FP-S": 79.4,
            "LR": 61.4,
            "RR": 78.7,
            "action_recognition": 83.8,
            "attribute_comparison": 70.7,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 74.1,
            "function_reasoning": 94.4,
            "future_prediction": 76.0,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 54.0,
            "image_scene": 88.9,
            "image_style": 82.6,
            "image_topic": 97.8,
            "nature_relation": 83.7,
            "object_localization": 66.7,
            "ocr": 93.3,
            "physical_property_reasoning": 43.0,
            "physical_relation": 61.3,
            "social_relation": 87.9,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 51.4,
            "Method": [
                "Bumblebee-7B-v2.0",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Monolith Foundation",
            "Time": "2024/07/11",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 300
        },
        {
            "Overall": 76.9,
            "AR": 87.3,
            "CP": 78.9,
            "FP-C": 70.8,
            "FP-S": 78.9,
            "LR": 54.9,
            "RR": 81.4,
            "action_recognition": 87.2,
            "attribute_comparison": 76.0,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 71.4,
            "function_reasoning": 93.3,
            "future_prediction": 77.3,
            "identity_reasoning": 98.7,
            "image_emotion": 80.0,
            "image_quality": 58.9,
            "image_scene": 85.4,
            "image_style": 75.0,
            "image_topic": 98.9,
            "nature_relation": 85.9,
            "object_localization": 72.4,
            "ocr": 88.9,
            "physical_property_reasoning": 69.6,
            "physical_relation": 66.7,
            "social_relation": 89.0,
            "spatial_relationship": 40.0,
            "structuralized_imagetext_understanding": 39.4,
            "Method": [
                "XinYuan-VL",
                "https://cece.com"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Cylingo Group",
            "Time": "2024/07/18",
            "Verified": "No",
            "OpenSource": "No",
            "key": 301
        },
        {
            "Overall": 78.3,
            "AR": 81.2,
            "CP": 78.1,
            "FP-C": 77.2,
            "FP-S": 84.9,
            "LR": 64.7,
            "RR": 76.0,
            "action_recognition": 83.8,
            "attribute_comparison": 82.7,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 82.3,
            "function_reasoning": 91.1,
            "future_prediction": 78.7,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 53.2,
            "image_scene": 86.8,
            "image_style": 75.0,
            "image_topic": 97.8,
            "nature_relation": 85.9,
            "object_localization": 77.1,
            "ocr": 94.4,
            "physical_property_reasoning": 54.4,
            "physical_relation": 54.7,
            "social_relation": 83.5,
            "spatial_relationship": 61.3,
            "structuralized_imagetext_understanding": 55.0,
            "Method": [
                "Cambrian-34B",
                "https://huggingface.co/nyu-visionx/cambrian-34b"
            ],
            "Parameters": "34B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "NYU",
            "Time": "2024/07/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 302
        },
        {
            "Overall": 74.1,
            "AR": 83.7,
            "CP": 77.2,
            "FP-C": 64.8,
            "FP-S": 81.4,
            "LR": 48.4,
            "RR": 74.4,
            "action_recognition": 82.9,
            "attribute_comparison": 61.3,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 82.3,
            "function_reasoning": 92.2,
            "future_prediction": 74.7,
            "identity_reasoning": 98.7,
            "image_emotion": 74.4,
            "image_quality": 50.8,
            "image_scene": 88.9,
            "image_style": 77.2,
            "image_topic": 97.8,
            "nature_relation": 79.3,
            "object_localization": 68.6,
            "ocr": 86.7,
            "physical_property_reasoning": 59.5,
            "physical_relation": 50.7,
            "social_relation": 89.0,
            "spatial_relationship": 40.0,
            "structuralized_imagetext_understanding": 30.3,
            "Method": [
                "Bunny-Llama3-8B",
                "https://huggingface.co/BAAI/Bunny-v1_1-Llama-3-8B-V"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "BAAI",
            "Time": "2024/07/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 303
        },
        {
            "Overall": 85.5,
            "AR": 91.0,
            "CP": 82.2,
            "FP-C": 83.9,
            "FP-S": 91.4,
            "LR": 78.8,
            "RR": 83.3,
            "action_recognition": 94.0,
            "attribute_comparison": 82.7,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 91.2,
            "function_reasoning": 96.7,
            "future_prediction": 81.3,
            "identity_reasoning": 100.0,
            "image_emotion": 78.9,
            "image_quality": 58.1,
            "image_scene": 91.0,
            "image_style": 88.0,
            "image_topic": 98.9,
            "nature_relation": 89.1,
            "object_localization": 84.8,
            "ocr": 94.4,
            "physical_property_reasoning": 75.9,
            "physical_relation": 70.7,
            "social_relation": 87.9,
            "spatial_relationship": 69.3,
            "structuralized_imagetext_understanding": 77.1,
            "Method": [
                "InternVL2-Llama3-76B",
                "https://huggingface.co/OpenGVLab/InternVL2-Llama3-76B"
            ],
            "Parameters": "76B",
            "Language Model": "Llama-3-70B-Instruct",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 304
        },
        {
            "Overall": 77.1,
            "AR": 85.7,
            "CP": 76.3,
            "FP-C": 71.9,
            "FP-S": 80.7,
            "LR": 70.7,
            "RR": 74.4,
            "action_recognition": 92.3,
            "attribute_comparison": 56.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 68.0,
            "function_reasoning": 92.2,
            "future_prediction": 82.7,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 43.5,
            "image_scene": 86.1,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 84.8,
            "object_localization": 72.4,
            "ocr": 98.9,
            "physical_property_reasoning": 67.1,
            "physical_relation": 45.3,
            "social_relation": 87.9,
            "spatial_relationship": 56.0,
            "structuralized_imagetext_understanding": 62.4,
            "Method": [
                "GPT-4o-mini (0718, detail-high)",
                "https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/07/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 305
        },
        {
            "Overall": 78.1,
            "AR": 79.2,
            "CP": 79.4,
            "FP-C": 76.4,
            "FP-S": 84.9,
            "LR": 62.0,
            "RR": 76.0,
            "action_recognition": 85.5,
            "attribute_comparison": 84.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 82.3,
            "function_reasoning": 91.1,
            "future_prediction": 73.3,
            "identity_reasoning": 97.4,
            "image_emotion": 75.6,
            "image_quality": 58.9,
            "image_scene": 88.2,
            "image_style": 81.5,
            "image_topic": 95.6,
            "nature_relation": 76.1,
            "object_localization": 74.3,
            "ocr": 93.3,
            "physical_property_reasoning": 48.1,
            "physical_relation": 65.3,
            "social_relation": 84.6,
            "spatial_relationship": 54.7,
            "structuralized_imagetext_understanding": 54.1,
            "Method": [
                "Ovis1.5-Llama3-8B",
                "https://huggingface.co/AIDC-AI/Ovis1.5-Llama3-8B"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 306
        },
        {
            "Overall": 19.9,
            "AR": 33.9,
            "CP": 25.9,
            "FP-C": 15.0,
            "FP-S": 12.5,
            "LR": 8.7,
            "RR": 19.4,
            "action_recognition": 22.2,
            "attribute_comparison": 14.7,
            "attribute_recognition": 21.3,
            "celebrity_recognition": 19.7,
            "function_reasoning": 37.8,
            "future_prediction": 18.7,
            "identity_reasoning": 46.1,
            "image_emotion": 13.3,
            "image_quality": 4.8,
            "image_scene": 38.2,
            "image_style": 30.4,
            "image_topic": 43.3,
            "nature_relation": 23.9,
            "object_localization": 1.0,
            "ocr": 5.6,
            "physical_property_reasoning": 17.7,
            "physical_relation": 1.3,
            "social_relation": 29.7,
            "spatial_relationship": 4.0,
            "structuralized_imagetext_understanding": 1.8,
            "Method": [
                "Chameleon-7B",
                "https://huggingface.co/facebook/chameleon-7b"
            ],
            "Parameters": "7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 309
        },
        {
            "Overall": 37.6,
            "AR": 58.4,
            "CP": 52.0,
            "FP-C": 23.2,
            "FP-S": 31.8,
            "LR": 9.8,
            "RR": 31.8,
            "action_recognition": 40.2,
            "attribute_comparison": 9.3,
            "attribute_recognition": 61.8,
            "celebrity_recognition": 36.1,
            "function_reasoning": 63.3,
            "future_prediction": 16.0,
            "identity_reasoning": 71.1,
            "image_emotion": 44.4,
            "image_quality": 1.6,
            "image_scene": 72.9,
            "image_style": 59.8,
            "image_topic": 87.8,
            "nature_relation": 30.4,
            "object_localization": 8.6,
            "ocr": 22.2,
            "physical_property_reasoning": 40.5,
            "physical_relation": 9.3,
            "social_relation": 51.6,
            "spatial_relationship": 10.7,
            "structuralized_imagetext_understanding": 5.5,
            "Method": [
                "Chameleon-30B",
                "https://huggingface.co/facebook/chameleon-30b"
            ],
            "Parameters": "30B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 310
        },
        {
            "Overall": 71.4,
            "AR": 80.4,
            "CP": 74.1,
            "FP-C": 65.5,
            "FP-S": 76.1,
            "LR": 50.0,
            "RR": 70.9,
            "action_recognition": 82.1,
            "attribute_comparison": 69.3,
            "attribute_recognition": 82.0,
            "celebrity_recognition": 70.1,
            "function_reasoning": 90.0,
            "future_prediction": 61.3,
            "identity_reasoning": 97.4,
            "image_emotion": 76.7,
            "image_quality": 47.6,
            "image_scene": 85.4,
            "image_style": 66.3,
            "image_topic": 97.8,
            "nature_relation": 84.8,
            "object_localization": 65.7,
            "ocr": 92.2,
            "physical_property_reasoning": 53.2,
            "physical_relation": 48.0,
            "social_relation": 75.8,
            "spatial_relationship": 36.0,
            "structuralized_imagetext_understanding": 42.2,
            "Method": [
                "Cambrian-13B",
                "https://huggingface.co/nyu-visionx/cambrian-13b"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "NYU",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 311
        },
        {
            "Overall": 76.6,
            "AR": 84.9,
            "CP": 76.3,
            "FP-C": 72.7,
            "FP-S": 82.6,
            "LR": 64.1,
            "RR": 72.1,
            "action_recognition": 88.9,
            "attribute_comparison": 72.0,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 77.6,
            "function_reasoning": 92.2,
            "future_prediction": 76.0,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 47.6,
            "image_scene": 85.4,
            "image_style": 75.0,
            "image_topic": 96.7,
            "nature_relation": 88.0,
            "object_localization": 72.4,
            "ocr": 94.4,
            "physical_property_reasoning": 64.6,
            "physical_relation": 48.0,
            "social_relation": 75.8,
            "spatial_relationship": 48.0,
            "structuralized_imagetext_understanding": 56.0,
            "Method": [
                "Yi-Vision",
                "https://platform.lingyiwanwu.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "01-AI",
            "Time": "2024/08/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 312
        },
        {
            "Overall": 78.4,
            "AR": 83.7,
            "CP": 79.4,
            "FP-C": 70.0,
            "FP-S": 84.0,
            "LR": 65.8,
            "RR": 79.5,
            "action_recognition": 80.3,
            "attribute_comparison": 76.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 79.6,
            "function_reasoning": 92.2,
            "future_prediction": 78.7,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 60.5,
            "image_scene": 85.4,
            "image_style": 76.1,
            "image_topic": 96.7,
            "nature_relation": 84.8,
            "object_localization": 75.2,
            "ocr": 92.2,
            "physical_property_reasoning": 60.8,
            "physical_relation": 66.7,
            "social_relation": 84.6,
            "spatial_relationship": 48.0,
            "structuralized_imagetext_understanding": 56.9,
            "Method": [
                "Ovis1.5-Gemma2-9B",
                "https://huggingface.co/AIDC-AI/Ovis1.5-Gemma2-9B"
            ],
            "Parameters": "11.4B",
            "Language Model": "Gemma2-9B-It",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/08/04",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 313
        },
        {
            "Overall": 72.1,
            "AR": 83.7,
            "CP": 76.9,
            "FP-C": 66.3,
            "FP-S": 75.2,
            "LR": 49.5,
            "RR": 68.2,
            "action_recognition": 80.3,
            "attribute_comparison": 66.7,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 74.8,
            "function_reasoning": 88.9,
            "future_prediction": 66.7,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 48.4,
            "image_scene": 85.4,
            "image_style": 79.3,
            "image_topic": 97.8,
            "nature_relation": 66.3,
            "object_localization": 64.8,
            "ocr": 83.3,
            "physical_property_reasoning": 64.6,
            "physical_relation": 50.7,
            "social_relation": 84.6,
            "spatial_relationship": 44.0,
            "structuralized_imagetext_understanding": 37.6,
            "Method": [
                "LLaVA-Next-Llama3",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "ByteDance",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 307
        },
        {
            "Overall": 71.7,
            "AR": 86.5,
            "CP": 78.1,
            "FP-C": 65.9,
            "FP-S": 72.4,
            "LR": 48.9,
            "RR": 65.5,
            "action_recognition": 88.9,
            "attribute_comparison": 62.7,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 71.4,
            "function_reasoning": 91.1,
            "future_prediction": 74.7,
            "identity_reasoning": 97.4,
            "image_emotion": 76.7,
            "image_quality": 52.4,
            "image_scene": 89.6,
            "image_style": 77.2,
            "image_topic": 97.8,
            "nature_relation": 75.0,
            "object_localization": 50.5,
            "ocr": 87.8,
            "physical_property_reasoning": 70.9,
            "physical_relation": 33.3,
            "social_relation": 82.4,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 31.2,
            "Method": [
                "LLaVA-Next-Interleave-7B-DPO",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen1.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 308
        },
        {
            "Overall": 72.8,
            "AR": 86.9,
            "CP": 77.8,
            "FP-C": 66.7,
            "FP-S": 74.2,
            "LR": 52.7,
            "RR": 67.1,
            "action_recognition": 88.9,
            "attribute_comparison": 58.7,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 76.2,
            "function_reasoning": 90.0,
            "future_prediction": 74.7,
            "identity_reasoning": 98.7,
            "image_emotion": 73.3,
            "image_quality": 51.6,
            "image_scene": 88.2,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 68.5,
            "object_localization": 45.7,
            "ocr": 91.1,
            "physical_property_reasoning": 72.2,
            "physical_relation": 40.0,
            "social_relation": 87.9,
            "spatial_relationship": 40.0,
            "structuralized_imagetext_understanding": 37.6,
            "Method": [
                "LLaVA-Next-Interleave-7B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen1.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 314
        },
        {
            "Overall": 76.5,
            "AR": 81.6,
            "CP": 77.2,
            "FP-C": 71.2,
            "FP-S": 85.2,
            "LR": 56.0,
            "RR": 76.0,
            "action_recognition": 85.5,
            "attribute_comparison": 68.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 85.0,
            "function_reasoning": 94.4,
            "future_prediction": 74.7,
            "identity_reasoning": 98.7,
            "image_emotion": 82.2,
            "image_quality": 47.6,
            "image_scene": 88.9,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 89.1,
            "object_localization": 69.5,
            "ocr": 95.6,
            "physical_property_reasoning": 50.6,
            "physical_relation": 49.3,
            "social_relation": 84.6,
            "spatial_relationship": 52.0,
            "structuralized_imagetext_understanding": 43.1,
            "Method": [
                "LLaVA-Next-Qwen-32B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "33B",
            "Language Model": "Qwen1.5-32B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 315
        },
        {
            "Overall": 63.8,
            "AR": 75.9,
            "CP": 72.4,
            "FP-C": 56.6,
            "FP-S": 64.0,
            "LR": 37.5,
            "RR": 60.5,
            "action_recognition": 84.6,
            "attribute_comparison": 36.0,
            "attribute_recognition": 75.3,
            "celebrity_recognition": 76.2,
            "function_reasoning": 83.3,
            "future_prediction": 66.7,
            "identity_reasoning": 96.1,
            "image_emotion": 71.1,
            "image_quality": 36.3,
            "image_scene": 85.4,
            "image_style": 76.1,
            "image_topic": 98.9,
            "nature_relation": 63.0,
            "object_localization": 30.5,
            "ocr": 72.2,
            "physical_property_reasoning": 48.1,
            "physical_relation": 25.3,
            "social_relation": 86.8,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 17.4,
            "Method": [
                "Mantis-8B-clip-llama3",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-clip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 316
        },
        {
            "Overall": 66.1,
            "AR": 79.6,
            "CP": 71.5,
            "FP-C": 59.2,
            "FP-S": 71.7,
            "LR": 39.7,
            "RR": 58.5,
            "action_recognition": 89.7,
            "attribute_comparison": 42.7,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 75.5,
            "function_reasoning": 92.2,
            "future_prediction": 70.7,
            "identity_reasoning": 97.4,
            "image_emotion": 75.6,
            "image_quality": 25.0,
            "image_scene": 85.4,
            "image_style": 82.6,
            "image_topic": 97.8,
            "nature_relation": 54.3,
            "object_localization": 40.0,
            "ocr": 88.9,
            "physical_property_reasoning": 48.1,
            "physical_relation": 29.3,
            "social_relation": 86.8,
            "spatial_relationship": 28.0,
            "structuralized_imagetext_understanding": 18.3,
            "Method": [
                "Mantis-8B-siglip-llama3",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-siglip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 317
        },
        {
            "Overall": 73.6,
            "AR": 78.4,
            "CP": 76.5,
            "FP-C": 67.8,
            "FP-S": 83.1,
            "LR": 53.8,
            "RR": 67.1,
            "action_recognition": 85.5,
            "attribute_comparison": 68.0,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 87.8,
            "function_reasoning": 90.0,
            "future_prediction": 72.0,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 41.9,
            "image_scene": 88.2,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 73.9,
            "object_localization": 62.9,
            "ocr": 92.2,
            "physical_property_reasoning": 46.8,
            "physical_relation": 40.0,
            "social_relation": 82.4,
            "spatial_relationship": 40.0,
            "structuralized_imagetext_understanding": 41.3,
            "Method": [
                "Mantis-8B-Idefics2",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-Idefics2"
            ],
            "Parameters": "8B",
            "Language Model": "Mistral-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 318
        },
        {
            "Overall": 79.0,
            "AR": 83.7,
            "CP": 79.6,
            "FP-C": 71.2,
            "FP-S": 87.0,
            "LR": 65.8,
            "RR": 77.5,
            "action_recognition": 82.9,
            "attribute_comparison": 76.0,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 84.4,
            "function_reasoning": 94.4,
            "future_prediction": 76.0,
            "identity_reasoning": 97.4,
            "image_emotion": 74.4,
            "image_quality": 57.3,
            "image_scene": 89.6,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 85.9,
            "object_localization": 76.2,
            "ocr": 95.6,
            "physical_property_reasoning": 58.2,
            "physical_relation": 64.0,
            "social_relation": 80.2,
            "spatial_relationship": 48.0,
            "structuralized_imagetext_understanding": 58.7,
            "Method": [
                "MiniCPM-V-2.6",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-siglip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "OpenBMB",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 319
        },
        {
            "Overall": 81.8,
            "AR": 89.4,
            "CP": 81.1,
            "FP-C": 85.4,
            "FP-S": 78.7,
            "LR": 77.2,
            "RR": 80.6,
            "action_recognition": 95.7,
            "attribute_comparison": 78.7,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 59.2,
            "function_reasoning": 94.4,
            "future_prediction": 80.0,
            "identity_reasoning": 96.1,
            "image_emotion": 80.0,
            "image_quality": 58.9,
            "image_scene": 88.2,
            "image_style": 84.8,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 78.1,
            "ocr": 98.9,
            "physical_property_reasoning": 77.2,
            "physical_relation": 57.3,
            "social_relation": 86.8,
            "spatial_relationship": 76.0,
            "structuralized_imagetext_understanding": 75.2,
            "Method": [
                "GPT-4o (0806, detail-high)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 320
        },
        {
            "Overall": 73.7,
            "AR": 83.7,
            "CP": 76.5,
            "FP-C": 71.2,
            "FP-S": 77.5,
            "LR": 47.8,
            "RR": 72.9,
            "action_recognition": 84.6,
            "attribute_comparison": 76.0,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 70.1,
            "function_reasoning": 92.2,
            "future_prediction": 65.3,
            "identity_reasoning": 96.1,
            "image_emotion": 74.4,
            "image_quality": 52.4,
            "image_scene": 87.5,
            "image_style": 72.8,
            "image_topic": 97.8,
            "nature_relation": 69.6,
            "object_localization": 73.3,
            "ocr": 81.1,
            "physical_property_reasoning": 62.0,
            "physical_relation": 66.7,
            "social_relation": 81.3,
            "spatial_relationship": 45.3,
            "structuralized_imagetext_understanding": 35.8,
            "Method": [
                "Llama-3-MixSense-v1.1",
                "https://huggingface.co/Zero-Vision/Llama-3-MixSenseV1_1"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "Florence-2-Large-FT",
            "Org": "ZeroVision",
            "Time": "2024/08/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 321
        },
        {
            "Overall": 79.6,
            "AR": 87.3,
            "CP": 76.7,
            "FP-C": 77.9,
            "FP-S": 87.7,
            "LR": 65.2,
            "RR": 76.7,
            "action_recognition": 90.6,
            "attribute_comparison": 80.0,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 87.8,
            "function_reasoning": 95.6,
            "future_prediction": 80.0,
            "identity_reasoning": 97.4,
            "image_emotion": 76.7,
            "image_quality": 52.4,
            "image_scene": 83.3,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 80.4,
            "object_localization": 74.3,
            "ocr": 96.7,
            "physical_property_reasoning": 68.4,
            "physical_relation": 58.7,
            "social_relation": 87.9,
            "spatial_relationship": 56.0,
            "structuralized_imagetext_understanding": 55.0,
            "Method": [
                "OmChat-v2.0-13B",
                "https://huggingface.co/omlab/omchat-v2.0-13B-single-beta_hf"
            ],
            "Parameters": "13B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "InternViT-6B",
            "Org": "Om AI",
            "Time": "2024/08/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 323
        },
        {
            "Overall": 68.8,
            "AR": 77.1,
            "CP": 73.1,
            "FP-C": 62.2,
            "FP-S": 76.3,
            "LR": 47.3,
            "RR": 61.6,
            "action_recognition": 80.3,
            "attribute_comparison": 64.0,
            "attribute_recognition": 76.4,
            "celebrity_recognition": 75.5,
            "function_reasoning": 85.6,
            "future_prediction": 74.7,
            "identity_reasoning": 94.7,
            "image_emotion": 71.1,
            "image_quality": 37.1,
            "image_scene": 85.4,
            "image_style": 80.4,
            "image_topic": 97.8,
            "nature_relation": 67.4,
            "object_localization": 62.9,
            "ocr": 93.3,
            "physical_property_reasoning": 50.6,
            "physical_relation": 34.7,
            "social_relation": 78.0,
            "spatial_relationship": 32.0,
            "structuralized_imagetext_understanding": 28.4,
            "Method": [
                "Parrot-7B",
                "https://huggingface.co/AIDC-AI/Parrot-7B"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Alibaba",
            "Time": "2024/08/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 324
        },
        {
            "Overall": 63.1,
            "AR": 79.2,
            "CP": 67.8,
            "FP-C": 56.2,
            "FP-S": 66.8,
            "LR": 33.7,
            "RR": 59.7,
            "action_recognition": 83.8,
            "attribute_comparison": 42.7,
            "attribute_recognition": 82.0,
            "celebrity_recognition": 72.8,
            "function_reasoning": 90.0,
            "future_prediction": 65.3,
            "identity_reasoning": 97.4,
            "image_emotion": 72.2,
            "image_quality": 21.8,
            "image_scene": 84.0,
            "image_style": 71.7,
            "image_topic": 96.7,
            "nature_relation": 68.5,
            "object_localization": 34.3,
            "ocr": 80.0,
            "physical_property_reasoning": 49.4,
            "physical_relation": 25.3,
            "social_relation": 79.1,
            "spatial_relationship": 26.7,
            "structuralized_imagetext_understanding": 11.9,
            "Method": [
                "VILA1.5-3B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-3b"
            ],
            "Parameters": "3B",
            "Language Model": "Sheared-LLaMA-2.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 325
        },
        {
            "Overall": 57.9,
            "AR": 73.9,
            "CP": 65.0,
            "FP-C": 53.2,
            "FP-S": 61.7,
            "LR": 33.2,
            "RR": 44.2,
            "action_recognition": 76.9,
            "attribute_comparison": 50.7,
            "attribute_recognition": 71.9,
            "celebrity_recognition": 64.6,
            "function_reasoning": 87.8,
            "future_prediction": 58.7,
            "identity_reasoning": 90.8,
            "image_emotion": 68.9,
            "image_quality": 30.6,
            "image_scene": 75.7,
            "image_style": 59.8,
            "image_topic": 96.7,
            "nature_relation": 41.3,
            "object_localization": 30.5,
            "ocr": 83.3,
            "physical_property_reasoning": 41.8,
            "physical_relation": 14.7,
            "social_relation": 71.4,
            "spatial_relationship": 18.7,
            "structuralized_imagetext_understanding": 15.6,
            "Method": [
                "Llama-3-VILA1.5-8B",
                "https://huggingface.co/Efficient-Large-Model/Llama-3-VILA1.5-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 326
        },
        {
            "Overall": 71.8,
            "AR": 79.2,
            "CP": 76.7,
            "FP-C": 65.2,
            "FP-S": 77.0,
            "LR": 47.8,
            "RR": 69.8,
            "action_recognition": 82.1,
            "attribute_comparison": 69.3,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 79.6,
            "function_reasoning": 92.2,
            "future_prediction": 68.0,
            "identity_reasoning": 96.1,
            "image_emotion": 76.7,
            "image_quality": 45.2,
            "image_scene": 87.5,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 80.4,
            "object_localization": 58.1,
            "ocr": 87.8,
            "physical_property_reasoning": 48.1,
            "physical_relation": 45.3,
            "social_relation": 79.1,
            "spatial_relationship": 34.7,
            "structuralized_imagetext_understanding": 33.9,
            "Method": [
                "VILA1.5-13B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-13b"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 327
        },
        {
            "Overall": 79.9,
            "AR": 84.5,
            "CP": 78.7,
            "FP-C": 76.8,
            "FP-S": 88.6,
            "LR": 62.0,
            "RR": 79.5,
            "action_recognition": 91.5,
            "attribute_comparison": 68.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 89.1,
            "function_reasoning": 94.4,
            "future_prediction": 80.0,
            "identity_reasoning": 97.4,
            "image_emotion": 81.1,
            "image_quality": 51.6,
            "image_scene": 86.8,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 90.2,
            "object_localization": 79.0,
            "ocr": 94.4,
            "physical_property_reasoning": 60.8,
            "physical_relation": 56.0,
            "social_relation": 87.9,
            "spatial_relationship": 62.7,
            "structuralized_imagetext_understanding": 49.5,
            "Method": [
                "VILA1.5-40B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-40b"
            ],
            "Parameters": "40B",
            "Language Model": "Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 328
        },
        {
            "Overall": 80.6,
            "AR": 86.9,
            "CP": 80.6,
            "FP-C": 77.5,
            "FP-S": 86.3,
            "LR": 65.8,
            "RR": 78.7,
            "action_recognition": 93.2,
            "attribute_comparison": 81.3,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 83.0,
            "function_reasoning": 95.6,
            "future_prediction": 80.0,
            "identity_reasoning": 98.7,
            "image_emotion": 80.0,
            "image_quality": 58.1,
            "image_scene": 88.9,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 82.6,
            "object_localization": 78.1,
            "ocr": 93.3,
            "physical_property_reasoning": 65.8,
            "physical_relation": 69.3,
            "social_relation": 82.4,
            "spatial_relationship": 49.3,
            "structuralized_imagetext_understanding": 56.0,
            "Org": "DataCanvas",
            "Time": "2024/08/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "MMAlaya2",
                "https://huggingface.co/DataCanvas/MMAlaya2"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "key": 329
        },
        {
            "Overall": 75.0,
            "AR": 84.9,
            "CP": 76.3,
            "FP-C": 66.7,
            "FP-S": 79.6,
            "LR": 61.4,
            "RR": 73.3,
            "action_recognition": 82.9,
            "attribute_comparison": 65.3,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 76.9,
            "function_reasoning": 91.1,
            "future_prediction": 77.3,
            "identity_reasoning": 96.1,
            "image_emotion": 80.0,
            "image_quality": 45.2,
            "image_scene": 87.5,
            "image_style": 76.1,
            "image_topic": 97.8,
            "nature_relation": 76.1,
            "object_localization": 62.9,
            "ocr": 90.0,
            "physical_property_reasoning": 67.1,
            "physical_relation": 56.0,
            "social_relation": 84.6,
            "spatial_relationship": 42.7,
            "structuralized_imagetext_understanding": 50.5,
            "Org": "HuggingFace",
            "Time": "2024/08/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "Idefics3-8B-Llama3",
                "https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "key": 330
        },
        {
            "Overall": 72.1,
            "AR": 77.6,
            "CP": 76.3,
            "FP-C": 62.5,
            "FP-S": 75.2,
            "LR": 58.2,
            "RR": 72.9,
            "action_recognition": 76.9,
            "attribute_comparison": 62.7,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 74.8,
            "function_reasoning": 85.6,
            "future_prediction": 65.3,
            "identity_reasoning": 97.4,
            "image_emotion": 76.7,
            "image_quality": 47.6,
            "image_scene": 88.9,
            "image_style": 75.0,
            "image_topic": 96.7,
            "nature_relation": 78.3,
            "object_localization": 53.3,
            "ocr": 87.8,
            "physical_property_reasoning": 49.4,
            "physical_relation": 52.0,
            "social_relation": 84.6,
            "spatial_relationship": 40.0,
            "structuralized_imagetext_understanding": 53.2,
            "Org": "Microsoft",
            "Time": "2024/08/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "Phi-3.5-Vision",
                "https://huggingface.co/microsoft/Phi-3.5-vision-instruct"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3.5",
            "Vision Model": "CLIP ViT-L/14",
            "key": 331
        },
        {
            "Overall": 78.5,
            "AR": 82.4,
            "CP": 78.1,
            "FP-C": 73.4,
            "FP-S": 81.2,
            "LR": 68.5,
            "RR": 83.3,
            "action_recognition": 83.8,
            "attribute_comparison": 76.0,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 76.9,
            "function_reasoning": 91.1,
            "future_prediction": 78.7,
            "identity_reasoning": 96.1,
            "image_emotion": 74.4,
            "image_quality": 57.3,
            "image_scene": 84.7,
            "image_style": 80.4,
            "image_topic": 97.8,
            "nature_relation": 94.6,
            "object_localization": 75.2,
            "ocr": 91.1,
            "physical_property_reasoning": 59.5,
            "physical_relation": 68.0,
            "social_relation": 84.6,
            "spatial_relationship": 54.7,
            "structuralized_imagetext_understanding": 61.5,
            "Org": "Monolith Foundation",
            "Time": "2024/08/30",
            "Verified": "No",
            "OpenSource": "Yes",
            "Method": [
                "Mirage-12B-v2.0",
                "https://huggingface.co/MonolithFoundation/Mirage-12B"
            ],
            "Parameters": "12B",
            "Language Model": "Mistral-12B",
            "Vision Model": "SigLIP-400M",
            "key": 332
        },
        {
            "Overall": 62.3,
            "AR": 73.1,
            "CP": 68.5,
            "FP-C": 57.7,
            "FP-S": 69.6,
            "LR": 29.9,
            "RR": 54.7,
            "action_recognition": 80.3,
            "attribute_comparison": 53.3,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 70.1,
            "function_reasoning": 83.3,
            "future_prediction": 54.7,
            "identity_reasoning": 94.7,
            "image_emotion": 72.2,
            "image_quality": 29.8,
            "image_scene": 81.9,
            "image_style": 68.5,
            "image_topic": 96.7,
            "nature_relation": 55.4,
            "object_localization": 44.8,
            "ocr": 83.3,
            "physical_property_reasoning": 40.5,
            "physical_relation": 24.0,
            "social_relation": 79.1,
            "spatial_relationship": 26.7,
            "structuralized_imagetext_understanding": 12.8,
            "Method": [
                "LLaVA-v1.5-7B",
                "https://arxiv.org/abs/2310.03744"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2023/10/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 186
        },
        {
            "Overall": 65.8,
            "AR": 72.2,
            "CP": 72.2,
            "FP-C": 60.3,
            "FP-S": 72.6,
            "LR": 34.2,
            "RR": 63.2,
            "action_recognition": 79.5,
            "attribute_comparison": 60.0,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 76.2,
            "function_reasoning": 83.3,
            "future_prediction": 68.0,
            "identity_reasoning": 92.1,
            "image_emotion": 76.7,
            "image_quality": 33.9,
            "image_scene": 88.9,
            "image_style": 68.5,
            "image_topic": 97.8,
            "nature_relation": 62.0,
            "object_localization": 49.5,
            "ocr": 86.7,
            "physical_property_reasoning": 40.5,
            "physical_relation": 42.7,
            "social_relation": 81.3,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 11.0,
            "Method": [
                "LLaVA-v1.5-13B",
                "https://arxiv.org/abs/2310.03744"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2023/10/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 188
        },
        {
            "Overall": 75.3,
            "AR": 81.2,
            "CP": 76.7,
            "FP-C": 71.5,
            "FP-S": 84.0,
            "LR": 46.2,
            "RR": 76.7,
            "action_recognition": 86.3,
            "attribute_comparison": 80.0,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 83.0,
            "function_reasoning": 93.3,
            "future_prediction": 69.3,
            "identity_reasoning": 98.7,
            "image_emotion": 78.9,
            "image_quality": 46.0,
            "image_scene": 84.0,
            "image_style": 82.6,
            "image_topic": 98.9,
            "nature_relation": 82.6,
            "object_localization": 74.3,
            "ocr": 90.0,
            "physical_property_reasoning": 50.6,
            "physical_relation": 56.0,
            "social_relation": 87.9,
            "spatial_relationship": 40.0,
            "structuralized_imagetext_understanding": 30.3,
            "Method": [
                "XGen-MM-Instruct-Interleave-v1.5",
                "https://huggingface.co/Salesforce/xgen-mm-phi3-mini-instruct-interleave-r-v1.5"
            ],
            "Parameters": "4.4B",
            "Language Model": "Phi-3",
            "Vision Model": "SigLIP-400M",
            "Org": "Salesforce",
            "Time": "2024/09/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 333
        },
        {
            "Overall": 75.2,
            "AR": 83.7,
            "CP": 75.9,
            "FP-C": 73.0,
            "FP-S": 81.0,
            "LR": 46.7,
            "RR": 78.7,
            "action_recognition": 87.2,
            "attribute_comparison": 81.3,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 83.7,
            "function_reasoning": 92.2,
            "future_prediction": 72.0,
            "identity_reasoning": 97.4,
            "image_emotion": 77.8,
            "image_quality": 43.5,
            "image_scene": 87.5,
            "image_style": 77.2,
            "image_topic": 98.9,
            "nature_relation": 85.9,
            "object_localization": 65.7,
            "ocr": 85.6,
            "physical_property_reasoning": 60.8,
            "physical_relation": 58.7,
            "social_relation": 87.9,
            "spatial_relationship": 42.7,
            "structuralized_imagetext_understanding": 29.4,
            "Method": [
                "XGen-MM-Instruct-DPO-v1.5",
                "https://huggingface.co/Salesforce/xgen-mm-phi3-mini-instruct-dpo-r-v1.5"
            ],
            "Parameters": "4.4B",
            "Language Model": "Phi-3",
            "Vision Model": "SigLIP-400M",
            "Org": "Salesforce",
            "Time": "2024/09/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 334
        },
        {
            "Overall": 81.8,
            "AR": 85.3,
            "CP": 81.3,
            "FP-C": 79.4,
            "FP-S": 89.3,
            "LR": 70.1,
            "RR": 77.5,
            "action_recognition": 89.7,
            "attribute_comparison": 82.7,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 93.2,
            "function_reasoning": 91.1,
            "future_prediction": 77.3,
            "identity_reasoning": 97.4,
            "image_emotion": 83.3,
            "image_quality": 59.7,
            "image_scene": 88.2,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 84.8,
            "object_localization": 76.2,
            "ocr": 97.8,
            "physical_property_reasoning": 67.1,
            "physical_relation": 56.0,
            "social_relation": 87.9,
            "spatial_relationship": 60.0,
            "structuralized_imagetext_understanding": 65.1,
            "Method": [
                "Qwen2-VL-7B",
                "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/09/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 336
        },
        {
            "Overall": 73.2,
            "AR": 79.2,
            "CP": 76.3,
            "FP-C": 64.8,
            "FP-S": 81.2,
            "LR": 50.5,
            "RR": 72.9,
            "action_recognition": 88.0,
            "attribute_comparison": 64.0,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 89.1,
            "function_reasoning": 92.2,
            "future_prediction": 69.3,
            "identity_reasoning": 97.4,
            "image_emotion": 75.6,
            "image_quality": 47.6,
            "image_scene": 87.5,
            "image_style": 76.1,
            "image_topic": 98.9,
            "nature_relation": 76.1,
            "object_localization": 55.2,
            "ocr": 92.2,
            "physical_property_reasoning": 46.8,
            "physical_relation": 44.0,
            "social_relation": 93.4,
            "spatial_relationship": 29.3,
            "structuralized_imagetext_understanding": 37.6,
            "Method": [
                "Qwen2-VL-2B",
                "https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct"
            ],
            "Parameters": "2B",
            "Language Model": "Qwen2-1.5B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/09/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 337
        },
        {
            "Overall": 44.1,
            "AR": 53.1,
            "CP": 58.9,
            "FP-C": 38.6,
            "FP-S": 38.7,
            "LR": 22.3,
            "RR": 34.5,
            "action_recognition": 60.7,
            "attribute_comparison": 25.3,
            "attribute_recognition": 65.2,
            "celebrity_recognition": 31.3,
            "function_reasoning": 51.1,
            "future_prediction": 42.7,
            "identity_reasoning": 72.4,
            "image_emotion": 40.0,
            "image_quality": 21.0,
            "image_scene": 78.5,
            "image_style": 63.0,
            "image_topic": 94.4,
            "nature_relation": 28.3,
            "object_localization": 25.7,
            "ocr": 40.0,
            "physical_property_reasoning": 36.7,
            "physical_relation": 24.0,
            "social_relation": 49.5,
            "spatial_relationship": 17.3,
            "structuralized_imagetext_understanding": 8.3,
            "Method": [
                "Mantis-8B-Fuyu",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-Fuyu"
            ],
            "Parameters": "8B",
            "Language Model": "Fuyu-8B",
            "Vision Model": "",
            "Org": "TIGER Lab",
            "Time": "2024/09/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 339
        },
        {
            "Overall": 63.1,
            "AR": 76.7,
            "CP": 70.2,
            "FP-C": 55.4,
            "FP-S": 65.9,
            "LR": 31.5,
            "RR": 60.9,
            "action_recognition": 82.9,
            "attribute_comparison": 45.3,
            "attribute_recognition": 82.0,
            "celebrity_recognition": 70.7,
            "function_reasoning": 86.7,
            "future_prediction": 60.0,
            "identity_reasoning": 97.4,
            "image_emotion": 73.3,
            "image_quality": 31.5,
            "image_scene": 84.7,
            "image_style": 70.7,
            "image_topic": 96.7,
            "nature_relation": 64.1,
            "object_localization": 42.9,
            "ocr": 68.9,
            "physical_property_reasoning": 45.6,
            "physical_relation": 38.7,
            "social_relation": 75.8,
            "spatial_relationship": 22.7,
            "structuralized_imagetext_understanding": 11.9,
            "Method": [
                "Slime-7B",
                "https://huggingface.co/yifanzhang114/SliME-vicuna-7B"
            ],
            "Parameters": "7B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 340
        },
        {
            "Overall": 69.0,
            "AR": 79.2,
            "CP": 74.4,
            "FP-C": 61.8,
            "FP-S": 70.1,
            "LR": 39.7,
            "RR": 74.8,
            "action_recognition": 81.2,
            "attribute_comparison": 54.7,
            "attribute_recognition": 77.5,
            "celebrity_recognition": 74.8,
            "function_reasoning": 92.2,
            "future_prediction": 68.0,
            "identity_reasoning": 97.4,
            "image_emotion": 75.6,
            "image_quality": 42.7,
            "image_scene": 85.4,
            "image_style": 76.1,
            "image_topic": 97.8,
            "nature_relation": 78.3,
            "object_localization": 57.1,
            "ocr": 70.0,
            "physical_property_reasoning": 46.8,
            "physical_relation": 54.7,
            "social_relation": 87.9,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 20.2,
            "Method": [
                "Slime-8B",
                "https://huggingface.co/yifanzhang114/SliME-Llama3-8B"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 341
        },
        {
            "Overall": 62.9,
            "AR": 75.9,
            "CP": 71.9,
            "FP-C": 56.9,
            "FP-S": 64.3,
            "LR": 28.3,
            "RR": 60.1,
            "action_recognition": 82.1,
            "attribute_comparison": 44.0,
            "attribute_recognition": 76.4,
            "celebrity_recognition": 69.4,
            "function_reasoning": 84.4,
            "future_prediction": 53.3,
            "identity_reasoning": 96.1,
            "image_emotion": 76.7,
            "image_quality": 38.7,
            "image_scene": 84.7,
            "image_style": 68.5,
            "image_topic": 95.6,
            "nature_relation": 59.8,
            "object_localization": 45.7,
            "ocr": 65.6,
            "physical_property_reasoning": 46.8,
            "physical_relation": 44.0,
            "social_relation": 73.6,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 11.0,
            "Method": [
                "Slime-13B",
                "https://huggingface.co/yifanzhang114/SliME-vicuna-13B"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 342
        },
        {
            "Overall": 75.3,
            "AR": 82.4,
            "CP": 76.3,
            "FP-C": 67.0,
            "FP-S": 81.0,
            "LR": 68.5,
            "RR": 70.2,
            "action_recognition": 75.2,
            "attribute_comparison": 74.7,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 78.9,
            "function_reasoning": 94.4,
            "future_prediction": 73.3,
            "identity_reasoning": 93.4,
            "image_emotion": 70.0,
            "image_quality": 50.0,
            "image_scene": 85.4,
            "image_style": 81.5,
            "image_topic": 98.9,
            "nature_relation": 75.0,
            "object_localization": 70.5,
            "ocr": 91.1,
            "physical_property_reasoning": 58.2,
            "physical_relation": 58.7,
            "social_relation": 74.7,
            "spatial_relationship": 46.7,
            "structuralized_imagetext_understanding": 65.1,
            "Method": [
                "Pixtral-12B",
                "https://huggingface.co/mistralai/Pixtral-12B-2409"
            ],
            "Parameters": "13B",
            "Language Model": "Nemo-12B",
            "Vision Model": "ViT-400M",
            "Org": "Mistral AI",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 343
        },
        {
            "Overall": 77.1,
            "AR": 84.1,
            "CP": 78.9,
            "FP-C": 73.8,
            "FP-S": 86.5,
            "LR": 59.2,
            "RR": 67.4,
            "action_recognition": 82.1,
            "attribute_comparison": 72.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 89.1,
            "function_reasoning": 96.7,
            "future_prediction": 61.3,
            "identity_reasoning": 96.1,
            "image_emotion": 78.9,
            "image_quality": 54.8,
            "image_scene": 87.5,
            "image_style": 82.6,
            "image_topic": 94.4,
            "nature_relation": 85.9,
            "object_localization": 76.2,
            "ocr": 87.8,
            "physical_property_reasoning": 58.2,
            "physical_relation": 45.3,
            "social_relation": 67.0,
            "spatial_relationship": 62.7,
            "structuralized_imagetext_understanding": 57.8,
            "Method": [
                "Gemini-1.5-Flash",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 344
        },
        {
            "Overall": 59.6,
            "AR": 74.7,
            "CP": 68.3,
            "FP-C": 48.3,
            "FP-S": 61.3,
            "LR": 31.5,
            "RR": 55.8,
            "action_recognition": 85.5,
            "attribute_comparison": 17.3,
            "attribute_recognition": 77.5,
            "celebrity_recognition": 65.3,
            "function_reasoning": 81.1,
            "future_prediction": 57.3,
            "identity_reasoning": 92.1,
            "image_emotion": 72.2,
            "image_quality": 17.7,
            "image_scene": 84.0,
            "image_style": 78.3,
            "image_topic": 98.9,
            "nature_relation": 57.6,
            "object_localization": 22.9,
            "ocr": 83.3,
            "physical_property_reasoning": 50.6,
            "physical_relation": 37.3,
            "social_relation": 69.2,
            "spatial_relationship": 21.3,
            "structuralized_imagetext_understanding": 13.8,
            "Method": [
                "LLaVA-OneVision-0.5B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-0.5b-ov"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 345
        },
        {
            "Overall": 80.9,
            "AR": 88.2,
            "CP": 81.9,
            "FP-C": 73.8,
            "FP-S": 84.9,
            "LR": 67.9,
            "RR": 82.2,
            "action_recognition": 90.6,
            "attribute_comparison": 70.7,
            "attribute_recognition": 97.8,
            "celebrity_recognition": 82.3,
            "function_reasoning": 95.6,
            "future_prediction": 81.3,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 62.9,
            "image_scene": 89.6,
            "image_style": 79.3,
            "image_topic": 97.8,
            "nature_relation": 90.2,
            "object_localization": 71.4,
            "ocr": 92.2,
            "physical_property_reasoning": 70.9,
            "physical_relation": 69.3,
            "social_relation": 84.6,
            "spatial_relationship": 50.7,
            "structuralized_imagetext_understanding": 58.7,
            "Method": [
                "LLaVA-OneVision-7B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-7b-ov"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 346
        },
        {
            "Overall": 53.0,
            "AR": 73.5,
            "CP": 63.0,
            "FP-C": 39.0,
            "FP-S": 55.0,
            "LR": 20.1,
            "RR": 47.3,
            "action_recognition": 80.3,
            "attribute_comparison": 0.0,
            "attribute_recognition": 78.7,
            "celebrity_recognition": 61.9,
            "function_reasoning": 75.6,
            "future_prediction": 45.3,
            "identity_reasoning": 94.7,
            "image_emotion": 73.3,
            "image_quality": 0.8,
            "image_scene": 81.2,
            "image_style": 75.0,
            "image_topic": 96.7,
            "nature_relation": 53.3,
            "object_localization": 9.5,
            "ocr": 73.3,
            "physical_property_reasoning": 50.6,
            "physical_relation": 17.3,
            "social_relation": 65.9,
            "spatial_relationship": 13.3,
            "structuralized_imagetext_understanding": 2.8,
            "Method": [
                "LLaVA-OneVision-0.5B (SI)",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-0.5b-si"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 347
        },
        {
            "Overall": 77.7,
            "AR": 86.1,
            "CP": 78.7,
            "FP-C": 71.9,
            "FP-S": 82.4,
            "LR": 61.4,
            "RR": 77.5,
            "action_recognition": 89.7,
            "attribute_comparison": 74.7,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 80.3,
            "function_reasoning": 95.6,
            "future_prediction": 82.7,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 55.6,
            "image_scene": 88.9,
            "image_style": 75.0,
            "image_topic": 97.8,
            "nature_relation": 80.4,
            "object_localization": 69.5,
            "ocr": 95.6,
            "physical_property_reasoning": 64.6,
            "physical_relation": 61.3,
            "social_relation": 87.9,
            "spatial_relationship": 41.3,
            "structuralized_imagetext_understanding": 46.8,
            "Method": [
                "LLaVA-OneVision-7B (SI)",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-7b-si"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 348
        },
        {
            "Overall": 81.1,
            "AR": 85.3,
            "CP": 80.2,
            "FP-C": 78.3,
            "FP-S": 89.3,
            "LR": 67.9,
            "RR": 77.9,
            "action_recognition": 90.6,
            "attribute_comparison": 81.3,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 93.2,
            "function_reasoning": 92.2,
            "future_prediction": 76.0,
            "identity_reasoning": 97.4,
            "image_emotion": 83.3,
            "image_quality": 58.9,
            "image_scene": 86.1,
            "image_style": 80.4,
            "image_topic": 96.7,
            "nature_relation": 85.9,
            "object_localization": 75.2,
            "ocr": 97.8,
            "physical_property_reasoning": 65.8,
            "physical_relation": 56.0,
            "social_relation": 87.9,
            "spatial_relationship": 56.0,
            "structuralized_imagetext_understanding": 62.4,
            "Method": [
                "Qwen-VL-Plus-0809",
                "https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-qianwen-vl-plus-api"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 349
        },
        {
            "Overall": 83.3,
            "AR": 90.2,
            "CP": 80.0,
            "FP-C": 83.9,
            "FP-S": 87.9,
            "LR": 71.7,
            "RR": 83.3,
            "action_recognition": 90.6,
            "attribute_comparison": 81.3,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 83.7,
            "function_reasoning": 95.6,
            "future_prediction": 85.3,
            "identity_reasoning": 100.0,
            "image_emotion": 82.2,
            "image_quality": 57.3,
            "image_scene": 84.7,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 95.7,
            "object_localization": 79.0,
            "ocr": 96.7,
            "physical_property_reasoning": 74.7,
            "physical_relation": 64.0,
            "social_relation": 86.8,
            "spatial_relationship": 76.0,
            "structuralized_imagetext_understanding": 62.4,
            "Method": [
                "LLaVA-OneVision-72B (SI)",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-72b-si"
            ],
            "Parameters": "73B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 350
        },
        {
            "Overall": 85.0,
            "AR": 89.8,
            "CP": 83.5,
            "FP-C": 85.0,
            "FP-S": 89.8,
            "LR": 71.7,
            "RR": 84.9,
            "action_recognition": 89.7,
            "attribute_comparison": 89.3,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 87.1,
            "function_reasoning": 95.6,
            "future_prediction": 84.0,
            "identity_reasoning": 100.0,
            "image_emotion": 83.3,
            "image_quality": 66.9,
            "image_scene": 88.9,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 89.1,
            "object_localization": 82.9,
            "ocr": 95.6,
            "physical_property_reasoning": 73.4,
            "physical_relation": 72.0,
            "social_relation": 91.2,
            "spatial_relationship": 73.3,
            "structuralized_imagetext_understanding": 63.3,
            "Method": [
                "LLaVA-OneVision-72B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-72b-ov"
            ],
            "Parameters": "73B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 351
        },
        {
            "Overall": 81.5,
            "AR": 85.7,
            "CP": 79.8,
            "FP-C": 79.4,
            "FP-S": 85.6,
            "LR": 72.8,
            "RR": 82.6,
            "action_recognition": 87.2,
            "attribute_comparison": 81.3,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 79.6,
            "function_reasoning": 93.3,
            "future_prediction": 82.7,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 60.5,
            "image_scene": 86.1,
            "image_style": 79.3,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 81.9,
            "ocr": 94.4,
            "physical_property_reasoning": 65.8,
            "physical_relation": 66.7,
            "social_relation": 84.6,
            "spatial_relationship": 65.3,
            "structuralized_imagetext_understanding": 66.1,
            "Method": [
                "Ovis1.6-Gemma2-9B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B"
            ],
            "Parameters": "10.2B",
            "Language Model": "Gemma2-9B-It",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/09/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 352
        },
        {
            "Overall": 67.4,
            "AR": 76.3,
            "CP": 72.4,
            "FP-C": 62.5,
            "FP-S": 71.5,
            "LR": 41.8,
            "RR": 64.7,
            "action_recognition": 83.8,
            "attribute_comparison": 61.3,
            "attribute_recognition": 80.9,
            "celebrity_recognition": 70.1,
            "function_reasoning": 84.4,
            "future_prediction": 65.3,
            "identity_reasoning": 96.1,
            "image_emotion": 73.3,
            "image_quality": 37.1,
            "image_scene": 85.4,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 66.3,
            "object_localization": 53.3,
            "ocr": 85.6,
            "physical_property_reasoning": 48.1,
            "physical_relation": 44.0,
            "social_relation": 80.2,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 25.7,
            "Method": [
                "Eagle-X5-7B",
                "https://huggingface.co/NVEagle/Eagle-X5-7B"
            ],
            "Parameters": "9B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 353
        },
        {
            "Overall": 70.0,
            "AR": 81.6,
            "CP": 74.4,
            "FP-C": 62.2,
            "FP-S": 74.0,
            "LR": 47.8,
            "RR": 67.1,
            "action_recognition": 82.1,
            "attribute_comparison": 65.3,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 68.0,
            "function_reasoning": 87.8,
            "future_prediction": 68.0,
            "identity_reasoning": 96.1,
            "image_emotion": 71.1,
            "image_quality": 46.8,
            "image_scene": 87.5,
            "image_style": 71.7,
            "image_topic": 97.8,
            "nature_relation": 69.6,
            "object_localization": 60.0,
            "ocr": 88.9,
            "physical_property_reasoning": 60.8,
            "physical_relation": 52.0,
            "social_relation": 76.9,
            "spatial_relationship": 28.0,
            "structuralized_imagetext_understanding": 33.9,
            "Method": [
                "Eagle-X5-13B",
                "https://huggingface.co/NVEagle/Eagle-X5-13B"
            ],
            "Parameters": "15B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 354
        },
        {
            "Overall": 59.6,
            "AR": 75.9,
            "CP": 64.8,
            "FP-C": 50.6,
            "FP-S": 57.8,
            "LR": 30.4,
            "RR": 66.3,
            "action_recognition": 74.4,
            "attribute_comparison": 40.0,
            "attribute_recognition": 75.3,
            "celebrity_recognition": 54.4,
            "function_reasoning": 85.6,
            "future_prediction": 60.0,
            "identity_reasoning": 94.7,
            "image_emotion": 61.1,
            "image_quality": 21.0,
            "image_scene": 83.3,
            "image_style": 68.5,
            "image_topic": 95.6,
            "nature_relation": 77.2,
            "object_localization": 36.2,
            "ocr": 71.1,
            "physical_property_reasoning": 46.8,
            "physical_relation": 29.3,
            "social_relation": 85.7,
            "spatial_relationship": 24.0,
            "structuralized_imagetext_understanding": 10.1,
            "Method": [
                "Moondream1",
                "https://huggingface.co/vikhyatk/moondream1"
            ],
            "Parameters": "1.9B",
            "Language Model": "SigLIP-400M",
            "Vision Model": "Phi-1.5",
            "Org": "Moondream",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 355
        },
        {
            "Overall": 69.6,
            "AR": 80.0,
            "CP": 74.1,
            "FP-C": 59.2,
            "FP-S": 74.2,
            "LR": 50.5,
            "RR": 66.7,
            "action_recognition": 88.0,
            "attribute_comparison": 40.0,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 66.7,
            "function_reasoning": 86.7,
            "future_prediction": 60.0,
            "identity_reasoning": 96.1,
            "image_emotion": 70.0,
            "image_quality": 41.1,
            "image_scene": 90.3,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 66.3,
            "object_localization": 57.1,
            "ocr": 91.1,
            "physical_property_reasoning": 57.0,
            "physical_relation": 57.3,
            "social_relation": 74.7,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 44.0,
            "Method": [
                "MiniMonkey",
                "https://huggingface.co/mx262/MiniMonkey"
            ],
            "Parameters": "2.2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "HUST",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 357
        },
        {
            "Overall": 76.2,
            "AR": 79.2,
            "CP": 76.5,
            "FP-C": 70.4,
            "FP-S": 86.1,
            "LR": 56.5,
            "RR": 76.0,
            "action_recognition": 89.7,
            "attribute_comparison": 69.3,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 91.2,
            "function_reasoning": 92.2,
            "future_prediction": 73.3,
            "identity_reasoning": 97.4,
            "image_emotion": 74.4,
            "image_quality": 50.0,
            "image_scene": 86.8,
            "image_style": 76.1,
            "image_topic": 98.9,
            "nature_relation": 73.9,
            "object_localization": 68.6,
            "ocr": 92.2,
            "physical_property_reasoning": 46.8,
            "physical_relation": 60.0,
            "social_relation": 91.2,
            "spatial_relationship": 41.3,
            "structuralized_imagetext_understanding": 45.0,
            "Method": [
                "XinYuan-VL-2B-Instruct",
                "https://huggingface.co/Cylingo/Xinyuan-VL-2B"
            ],
            "Parameters": "2B",
            "Language Model": "Qwen2-1.5B",
            "Vision Model": "QwenViT",
            "Org": "Cylingo",
            "Time": "2024/09/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 359
        },
        {
            "Overall": 67.5,
            "AR": 79.6,
            "CP": 67.6,
            "FP-C": 62.2,
            "FP-S": 72.4,
            "LR": 48.9,
            "RR": 66.3,
            "action_recognition": 77.8,
            "attribute_comparison": 52.0,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 61.9,
            "function_reasoning": 90.0,
            "future_prediction": 62.7,
            "identity_reasoning": 96.1,
            "image_emotion": 73.3,
            "image_quality": 28.2,
            "image_scene": 84.0,
            "image_style": 60.9,
            "image_topic": 96.7,
            "nature_relation": 66.3,
            "object_localization": 60.0,
            "ocr": 90.0,
            "physical_property_reasoning": 51.9,
            "physical_relation": 50.7,
            "social_relation": 79.1,
            "spatial_relationship": 48.0,
            "structuralized_imagetext_understanding": 39.4,
            "Method": [
                "Llama-3.2-11B-Vision-Instruct",
                "https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct"
            ],
            "Parameters": "11B",
            "Language Model": "Llama-3.1-8B",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/10/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 360
        },
        {
            "Overall": 80.4,
            "AR": 86.9,
            "CP": 76.7,
            "FP-C": 76.8,
            "FP-S": 88.2,
            "LR": 69.6,
            "RR": 80.6,
            "action_recognition": 78.6,
            "attribute_comparison": 82.7,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 95.9,
            "function_reasoning": 94.4,
            "future_prediction": 82.7,
            "identity_reasoning": 96.1,
            "image_emotion": 74.4,
            "image_quality": 65.3,
            "image_scene": 76.4,
            "image_style": 84.8,
            "image_topic": 86.7,
            "nature_relation": 92.4,
            "object_localization": 71.4,
            "ocr": 95.6,
            "physical_property_reasoning": 69.6,
            "physical_relation": 58.7,
            "social_relation": 86.8,
            "spatial_relationship": 68.0,
            "structuralized_imagetext_understanding": 60.6,
            "Method": [
                "Step-1.5V",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "Step-1.5",
            "Vision Model": "stepencoder",
            "Org": "StepFun",
            "Time": "2024/10/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 322
        },
        {
            "Overall": 79.0,
            "AR": 82.0,
            "CP": 79.4,
            "FP-C": 72.7,
            "FP-S": 87.7,
            "LR": 65.8,
            "RR": 76.7,
            "action_recognition": 79.5,
            "attribute_comparison": 76.0,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 84.4,
            "function_reasoning": 90.0,
            "future_prediction": 76.0,
            "identity_reasoning": 96.1,
            "image_emotion": 78.9,
            "image_quality": 59.7,
            "image_scene": 88.9,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 79.3,
            "object_localization": 80.0,
            "ocr": 95.6,
            "physical_property_reasoning": 59.5,
            "physical_relation": 62.7,
            "social_relation": 85.7,
            "spatial_relationship": 58.7,
            "structuralized_imagetext_understanding": 58.7,
            "Method": [
                "POINTS-Yi-1.5-9B",
                "https://huggingface.co/WePOINTS/POINTS-Yi-1-5-9B-Chat"
            ],
            "Parameters": "9.5B",
            "Language Model": "Yi-1.5-9B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "WeChat",
            "Time": "2024/10/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTS-Yi-1.5-9B-Chat",
            "key": 362
        },
        {
            "Overall": 79.0,
            "AR": 85.7,
            "CP": 79.8,
            "FP-C": 71.9,
            "FP-S": 85.6,
            "LR": 66.3,
            "RR": 76.0,
            "action_recognition": 80.3,
            "attribute_comparison": 76.0,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 82.3,
            "function_reasoning": 91.1,
            "future_prediction": 77.3,
            "identity_reasoning": 98.7,
            "image_emotion": 75.6,
            "image_quality": 58.9,
            "image_scene": 90.3,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 77.2,
            "object_localization": 76.2,
            "ocr": 95.6,
            "physical_property_reasoning": 67.1,
            "physical_relation": 61.3,
            "social_relation": 86.8,
            "spatial_relationship": 54.7,
            "structuralized_imagetext_understanding": 58.7,
            "Method": [
                "POINTS-Qwen2.5-7B",
                "https://huggingface.co/WePOINTS/POINTS-Qwen-2-5-7B-Chat"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen-2.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "WeChat",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTS-Qwen-2.5-7B-Chat",
            "key": 363
        },
        {
            "Overall": 1.2,
            "AR": 1.2,
            "CP": 1.3,
            "FP-C": 0.0,
            "FP-S": 0.5,
            "LR": 0.5,
            "RR": 4.3,
            "action_recognition": 0.0,
            "attribute_comparison": 0.0,
            "attribute_recognition": 0.0,
            "celebrity_recognition": 0.0,
            "function_reasoning": 1.1,
            "future_prediction": 0.0,
            "identity_reasoning": 1.3,
            "image_emotion": 0.0,
            "image_quality": 4.8,
            "image_scene": 0.0,
            "image_style": 1.1,
            "image_topic": 0.0,
            "nature_relation": 8.7,
            "object_localization": 1.0,
            "ocr": 1.1,
            "physical_property_reasoning": 1.3,
            "physical_relation": 4.0,
            "social_relation": 0.0,
            "spatial_relationship": 0.0,
            "structuralized_imagetext_understanding": 0.9,
            "Method": [
                "Kosmos2",
                "https://huggingface.co/microsoft/kosmos-2-patch14-224"
            ],
            "Parameters": "1.7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Microsoft",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kosmos2",
            "key": 364
        },
        {
            "Overall": 79.5,
            "AR": 86.5,
            "CP": 76.5,
            "FP-C": 76.4,
            "FP-S": 88.2,
            "LR": 66.3,
            "RR": 77.5,
            "action_recognition": 88.9,
            "attribute_comparison": 65.3,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 89.8,
            "function_reasoning": 97.8,
            "future_prediction": 78.7,
            "identity_reasoning": 96.1,
            "image_emotion": 74.4,
            "image_quality": 53.2,
            "image_scene": 85.4,
            "image_style": 75.0,
            "image_topic": 97.8,
            "nature_relation": 83.7,
            "object_localization": 80.0,
            "ocr": 93.3,
            "physical_property_reasoning": 64.6,
            "physical_relation": 62.7,
            "social_relation": 83.5,
            "spatial_relationship": 68.0,
            "structuralized_imagetext_understanding": 57.8,
            "Method": [
                "Llama-3.2-90B-Vision-Instruct",
                "https://huggingface.co/meta-llama/Llama-3.2-90B-Vision-Instruct"
            ],
            "Parameters": "88.6B",
            "Language Model": "Llama-3.1-70B",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Llama-3.2-90B-Vision-Instruct",
            "key": 365
        },
        {
            "Overall": 79.0,
            "AR": 80.4,
            "CP": 76.9,
            "FP-C": 78.7,
            "FP-S": 86.8,
            "LR": 69.0,
            "RR": 76.4,
            "action_recognition": 90.6,
            "attribute_comparison": 69.3,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 82.3,
            "function_reasoning": 88.9,
            "future_prediction": 76.0,
            "identity_reasoning": 94.7,
            "image_emotion": 75.6,
            "image_quality": 54.0,
            "image_scene": 83.3,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 82.6,
            "object_localization": 80.0,
            "ocr": 96.7,
            "physical_property_reasoning": 57.0,
            "physical_relation": 62.7,
            "social_relation": 81.3,
            "spatial_relationship": 69.3,
            "structuralized_imagetext_understanding": 64.2,
            "Method": [
                "NVLM-D-72B",
                "https://huggingface.co/nvidia/NVLM-D-72B"
            ],
            "Parameters": "79.4B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "InternViT-6B",
            "Org": "Nvidia",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "NVLM",
            "key": 366
        },
        {
            "Overall": 67.7,
            "AR": 79.6,
            "CP": 74.8,
            "FP-C": 64.0,
            "FP-S": 65.7,
            "LR": 38.0,
            "RR": 69.8,
            "action_recognition": 85.5,
            "attribute_comparison": 60.0,
            "attribute_recognition": 80.9,
            "celebrity_recognition": 63.9,
            "function_reasoning": 88.9,
            "future_prediction": 68.0,
            "identity_reasoning": 97.4,
            "image_emotion": 75.6,
            "image_quality": 43.5,
            "image_scene": 89.6,
            "image_style": 70.7,
            "image_topic": 97.8,
            "nature_relation": 76.1,
            "object_localization": 49.5,
            "ocr": 72.2,
            "physical_property_reasoning": 51.9,
            "physical_relation": 41.3,
            "social_relation": 86.8,
            "spatial_relationship": 34.7,
            "structuralized_imagetext_understanding": 17.4,
            "Method": [
                "Moondream2",
                "https://huggingface.co/vikhyatk/moondream2"
            ],
            "Parameters": "1.9B",
            "Language Model": "SigLIP-400M",
            "Vision Model": "Phi-1.5",
            "Org": "Moondream",
            "Time": "2024/10/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Moondream2",
            "key": 356
        },
        {
            "Overall": 70.3,
            "AR": 72.7,
            "CP": 72.2,
            "FP-C": 62.9,
            "FP-S": 78.7,
            "LR": 56.5,
            "RR": 67.8,
            "action_recognition": 76.1,
            "attribute_comparison": 60.0,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 70.7,
            "function_reasoning": 74.4,
            "future_prediction": 65.3,
            "identity_reasoning": 92.1,
            "image_emotion": 62.2,
            "image_quality": 51.6,
            "image_scene": 84.0,
            "image_style": 66.3,
            "image_topic": 97.8,
            "nature_relation": 73.9,
            "object_localization": 69.5,
            "ocr": 90.0,
            "physical_property_reasoning": 51.9,
            "physical_relation": 54.7,
            "social_relation": 72.5,
            "spatial_relationship": 45.3,
            "structuralized_imagetext_understanding": 50.5,
            "Method": [
                "Molmo-7B-D",
                "https://huggingface.co/allenai/Molmo-7B-D-0924"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 361,
            "dir_name": "molmo-7B-D-0924"
        },
        {
            "Overall": 69.1,
            "AR": 72.2,
            "CP": 72.6,
            "FP-C": 63.3,
            "FP-S": 73.8,
            "LR": 50.5,
            "RR": 70.2,
            "action_recognition": 76.9,
            "attribute_comparison": 66.7,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 68.7,
            "function_reasoning": 80.0,
            "future_prediction": 69.3,
            "identity_reasoning": 93.4,
            "image_emotion": 71.1,
            "image_quality": 54.0,
            "image_scene": 81.9,
            "image_style": 65.2,
            "image_topic": 92.2,
            "nature_relation": 69.6,
            "object_localization": 62.9,
            "ocr": 82.2,
            "physical_property_reasoning": 43.0,
            "physical_relation": 57.3,
            "social_relation": 81.3,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 37.6,
            "Method": [
                "Molmo-7B-O",
                "https://huggingface.co/allenai/Molmo-7B-O-0924"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 367,
            "dir_name": "molmo-7B-O-0924"
        },
        {
            "Overall": 60.5,
            "AR": 68.2,
            "CP": 67.6,
            "FP-C": 52.1,
            "FP-S": 64.0,
            "LR": 37.5,
            "RR": 57.8,
            "action_recognition": 76.1,
            "attribute_comparison": 45.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 58.5,
            "function_reasoning": 68.9,
            "future_prediction": 57.3,
            "identity_reasoning": 92.1,
            "image_emotion": 70.0,
            "image_quality": 29.8,
            "image_scene": 79.9,
            "image_style": 69.6,
            "image_topic": 95.6,
            "nature_relation": 57.6,
            "object_localization": 39.0,
            "ocr": 77.8,
            "physical_property_reasoning": 44.3,
            "physical_relation": 36.0,
            "social_relation": 75.8,
            "spatial_relationship": 21.3,
            "structuralized_imagetext_understanding": 23.9,
            "Method": [
                "MolmoE-1B",
                "https://huggingface.co/allenai/MolmoE-1B-0924"
            ],
            "Parameters": "7.2B",
            "Language Model": "OLMoE-1B-7B-0924",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "molmoE-1B-0924",
            "key": 368
        },
        {
            "Overall": 50.2,
            "AR": 63.3,
            "CP": 61.7,
            "FP-C": 42.7,
            "FP-S": 49.4,
            "LR": 22.3,
            "RR": 42.6,
            "action_recognition": 78.6,
            "attribute_comparison": 13.3,
            "attribute_recognition": 74.2,
            "celebrity_recognition": 41.5,
            "function_reasoning": 68.9,
            "future_prediction": 45.3,
            "identity_reasoning": 92.1,
            "image_emotion": 60.0,
            "image_quality": 21.8,
            "image_scene": 76.4,
            "image_style": 59.8,
            "image_topic": 96.7,
            "nature_relation": 34.8,
            "object_localization": 26.7,
            "ocr": 64.4,
            "physical_property_reasoning": 29.1,
            "physical_relation": 24.0,
            "social_relation": 65.9,
            "spatial_relationship": 16.0,
            "structuralized_imagetext_understanding": 6.4,
            "Method": [
                "Janus-1.3B",
                "https://huggingface.co/deepseek-ai/Janus-1.3B"
            ],
            "Parameters": "2.1B",
            "Language Model": "DeepSeek-1B",
            "Vision Model": "SigLIP-400M",
            "Org": "deepseek",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Janus-1.3B",
            "key": 370
        },
        {
            "Overall": 67.0,
            "AR": 78.4,
            "CP": 73.3,
            "FP-C": 60.7,
            "FP-S": 66.1,
            "LR": 54.3,
            "RR": 60.1,
            "action_recognition": 80.3,
            "attribute_comparison": 58.7,
            "attribute_recognition": 80.9,
            "celebrity_recognition": 61.2,
            "function_reasoning": 83.3,
            "future_prediction": 62.7,
            "identity_reasoning": 94.7,
            "image_emotion": 75.6,
            "image_quality": 36.3,
            "image_scene": 86.8,
            "image_style": 76.1,
            "image_topic": 97.8,
            "nature_relation": 54.3,
            "object_localization": 41.9,
            "ocr": 87.8,
            "physical_property_reasoning": 57.0,
            "physical_relation": 36.0,
            "social_relation": 85.7,
            "spatial_relationship": 32.0,
            "structuralized_imagetext_understanding": 48.6,
            "Method": [
                "Vintern-3B-beta",
                "https://huggingface.co/5CD-AI/Vintern-3B-beta"
            ],
            "Parameters": "3.7B",
            "Language Model": "Qwen-2.5-3B",
            "Vision Model": "InternViT-300M",
            "Org": "Fifth Civil Defender",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Vintern-3B-beta",
            "key": 371
        },
        {
            "Overall": 76.2,
            "AR": 82.9,
            "CP": 75.6,
            "FP-C": 68.9,
            "FP-S": 84.7,
            "LR": 60.9,
            "RR": 75.2,
            "action_recognition": 83.8,
            "attribute_comparison": 72.0,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 83.7,
            "function_reasoning": 90.0,
            "future_prediction": 77.3,
            "identity_reasoning": 97.4,
            "image_emotion": 77.8,
            "image_quality": 53.2,
            "image_scene": 83.3,
            "image_style": 70.7,
            "image_topic": 96.7,
            "nature_relation": 78.3,
            "object_localization": 72.4,
            "ocr": 94.4,
            "physical_property_reasoning": 60.8,
            "physical_relation": 61.3,
            "social_relation": 83.5,
            "spatial_relationship": 42.7,
            "structuralized_imagetext_understanding": 49.5,
            "Method": [
                "Ovis1.6-Llama3.2-3B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Llama3.2-3B"
            ],
            "Parameters": "4.1B",
            "Language Model": "Llama-3.2-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis1.6-Llama3.2-3B",
            "key": 372
        },
        {
            "Overall": 76.3,
            "AR": 85.7,
            "CP": 76.5,
            "FP-C": 73.0,
            "FP-S": 81.7,
            "LR": 59.2,
            "RR": 73.6,
            "action_recognition": 86.3,
            "attribute_comparison": 76.0,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 74.1,
            "function_reasoning": 94.4,
            "future_prediction": 70.7,
            "identity_reasoning": 96.1,
            "image_emotion": 76.7,
            "image_quality": 48.4,
            "image_scene": 86.8,
            "image_style": 76.1,
            "image_topic": 98.9,
            "nature_relation": 78.3,
            "object_localization": 71.4,
            "ocr": 91.1,
            "physical_property_reasoning": 65.8,
            "physical_relation": 54.7,
            "social_relation": 84.6,
            "spatial_relationship": 49.3,
            "structuralized_imagetext_understanding": 51.4,
            "Method": [
                "Aquila-VL-2B",
                "https://huggingface.co/BAAI/Aquila-VL-2B-llava-qwen"
            ],
            "Parameters": "2.2B",
            "Language Model": "Qwen-2.5-1.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "BAAI",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Aquila-VL-2B",
            "key": 373
        },
        {
            "Overall": 79.4,
            "AR": 82.9,
            "CP": 78.5,
            "FP-C": 76.4,
            "FP-S": 84.5,
            "LR": 67.9,
            "RR": 81.0,
            "action_recognition": 83.8,
            "attribute_comparison": 73.3,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 75.5,
            "function_reasoning": 87.8,
            "future_prediction": 76.0,
            "identity_reasoning": 96.1,
            "image_emotion": 77.8,
            "image_quality": 54.8,
            "image_scene": 89.6,
            "image_style": 76.1,
            "image_topic": 96.7,
            "nature_relation": 89.1,
            "object_localization": 80.0,
            "ocr": 95.6,
            "physical_property_reasoning": 64.6,
            "physical_relation": 64.0,
            "social_relation": 86.8,
            "spatial_relationship": 68.0,
            "structuralized_imagetext_understanding": 62.4,
            "Method": [
                "Molmo-72B",
                "https://huggingface.co/allenai/Molmo-72B-0924"
            ],
            "Parameters": "73.3B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "molmo-72B-0924",
            "key": 377
        },
        {
            "Overall": 86.1,
            "AR": 89.4,
            "CP": 82.0,
            "FP-C": 89.1,
            "FP-S": 92.3,
            "LR": 81.0,
            "RR": 81.4,
            "action_recognition": 92.3,
            "attribute_comparison": 89.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 96.6,
            "function_reasoning": 94.4,
            "future_prediction": 86.7,
            "identity_reasoning": 100.0,
            "image_emotion": 83.3,
            "image_quality": 63.7,
            "image_scene": 87.5,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 88.0,
            "object_localization": 85.7,
            "ocr": 96.7,
            "physical_property_reasoning": 73.4,
            "physical_relation": 61.3,
            "social_relation": 91.2,
            "spatial_relationship": 84.0,
            "structuralized_imagetext_understanding": 77.1,
            "Method": [
                "Qwen2-VL-72B",
                "https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct"
            ],
            "Parameters": "73.4B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/10/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2-VL-72B-Instruct",
            "key": 378
        },
        {
            "Overall": 78.7,
            "AR": 84.5,
            "CP": 80.0,
            "FP-C": 74.2,
            "FP-S": 80.7,
            "LR": 67.4,
            "RR": 79.8,
            "action_recognition": 87.2,
            "attribute_comparison": 74.7,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 81.6,
            "function_reasoning": 92.2,
            "future_prediction": 84.0,
            "identity_reasoning": 96.1,
            "image_emotion": 81.1,
            "image_quality": 54.8,
            "image_scene": 88.2,
            "image_style": 81.5,
            "image_topic": 98.9,
            "nature_relation": 87.0,
            "object_localization": 62.9,
            "ocr": 92.2,
            "physical_property_reasoning": 64.6,
            "physical_relation": 62.7,
            "social_relation": 86.8,
            "spatial_relationship": 53.3,
            "structuralized_imagetext_understanding": 56.0,
            "Method": [
                "Bumblebee-7B-v2.2",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "Mono-Encoder",
            "Org": "Monolith Foundation",
            "Time": "2024/10/30",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 379
        },
        {
            "Overall": 83.1,
            "AR": 86.9,
            "CP": 86.5,
            "FP-C": 80.1,
            "FP-S": 86.5,
            "LR": 71.7,
            "RR": 77.9,
            "action_recognition": 85.5,
            "attribute_comparison": 82.7,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 80.3,
            "function_reasoning": 92.2,
            "future_prediction": 76.0,
            "identity_reasoning": 96.1,
            "image_emotion": 73.3,
            "image_quality": 93.5,
            "image_scene": 88.2,
            "image_style": 76.1,
            "image_topic": 97.8,
            "nature_relation": 92.4,
            "object_localization": 80.0,
            "ocr": 95.6,
            "physical_property_reasoning": 72.2,
            "physical_relation": 62.7,
            "social_relation": 75.8,
            "spatial_relationship": 69.3,
            "structuralized_imagetext_understanding": 68.8,
            "Method": [
                "BlueLM-V-3B",
                "https://developers.vivo.com/product/ai/bluelm"
            ],
            "Parameters": "3B",
            "Language Model": "BlueLM-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "vivo",
            "Time": "2024/10/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 358,
            "dir_name": "BlueLM_V"
        },
        {
            "Overall": 68.7,
            "AR": 78.8,
            "CP": 74.3,
            "FP-C": 63.7,
            "FP-S": 70.1,
            "LR": 44.0,
            "RR": 67.8,
            "action_recognition": 82.9,
            "attribute_comparison": 64.0,
            "attribute_recognition": 77.5,
            "celebrity_recognition": 72.8,
            "function_reasoning": 86.7,
            "future_prediction": 65.3,
            "identity_reasoning": 96.1,
            "image_emotion": 77.8,
            "image_quality": 40.3,
            "image_scene": 89.6,
            "image_style": 69.6,
            "image_topic": 97.8,
            "nature_relation": 71.7,
            "object_localization": 49.5,
            "ocr": 82.2,
            "physical_property_reasoning": 53.2,
            "physical_relation": 44.0,
            "social_relation": 83.5,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 29.4,
            "Method": [
                "Falcon2-VLM-11B",
                "https://huggingface.co/tiiuae/falcon-11B-vlm"
            ],
            "Parameters": "11.4B",
            "Language Model": "Falcon2-11B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Technology Innovation Institute",
            "Time": "2024/10/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Falcon2-VLM-11B",
            "key": 380
        },
        {
            "Overall": 53.9,
            "AR": 68.6,
            "CP": 63.7,
            "FP-C": 40.8,
            "FP-S": 53.6,
            "LR": 27.2,
            "RR": 52.3,
            "action_recognition": 75.2,
            "attribute_comparison": 6.7,
            "attribute_recognition": 67.4,
            "celebrity_recognition": 57.1,
            "function_reasoning": 75.6,
            "future_prediction": 56.0,
            "identity_reasoning": 90.8,
            "image_emotion": 68.9,
            "image_quality": 7.3,
            "image_scene": 83.3,
            "image_style": 71.7,
            "image_topic": 96.7,
            "nature_relation": 47.8,
            "object_localization": 16.2,
            "ocr": 77.8,
            "physical_property_reasoning": 39.2,
            "physical_relation": 28.0,
            "social_relation": 76.9,
            "spatial_relationship": 21.3,
            "structuralized_imagetext_understanding": 7.3,
            "Method": [
                "H2OVL-800M",
                "https://huggingface.co/h2oai/h2ovl-mississippi-800m"
            ],
            "Parameters": "0.83B",
            "Language Model": "H2O-DANUBE3-500M",
            "Vision Model": "InternViT-300M",
            "Org": "H2O.ai",
            "Time": "2024/10/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "h2ovl-mississippi-1b",
            "key": 381
        },
        {
            "Overall": 68.7,
            "AR": 72.2,
            "CP": 76.1,
            "FP-C": 62.9,
            "FP-S": 70.5,
            "LR": 51.6,
            "RR": 65.1,
            "action_recognition": 79.5,
            "attribute_comparison": 61.3,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 60.5,
            "function_reasoning": 80.0,
            "future_prediction": 66.7,
            "identity_reasoning": 96.1,
            "image_emotion": 73.3,
            "image_quality": 50.0,
            "image_scene": 88.2,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 60.9,
            "object_localization": 60.0,
            "ocr": 82.2,
            "physical_property_reasoning": 40.5,
            "physical_relation": 53.3,
            "social_relation": 79.1,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 41.3,
            "Method": [
                "H2OVL-2B",
                "https://huggingface.co/h2oai/h2ovl-mississippi-2b"
            ],
            "Parameters": "2.2B",
            "Language Model": "H2O-DANUBE2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "H2O.ai",
            "Time": "2024/10/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "h2ovl-mississippi-2b",
            "key": 382
        },
        {
            "Overall": 86.0,
            "AR": 89.4,
            "CP": 81.5,
            "FP-C": 89.5,
            "FP-S": 92.3,
            "LR": 81.5,
            "RR": 81.0,
            "action_recognition": 91.5,
            "attribute_comparison": 90.7,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 95.9,
            "function_reasoning": 94.4,
            "future_prediction": 86.7,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 64.5,
            "image_scene": 86.8,
            "image_style": 80.4,
            "image_topic": 96.7,
            "nature_relation": 88.0,
            "object_localization": 85.7,
            "ocr": 96.7,
            "physical_property_reasoning": 75.9,
            "physical_relation": 60.0,
            "social_relation": 91.2,
            "spatial_relationship": 85.3,
            "structuralized_imagetext_understanding": 78.0,
            "Method": [
                "Qwen-VL-Max-0809",
                "https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-qianwen-vl-plus-api"
            ],
            "Parameters": "72B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/09/12",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "Qwen-VL-Max-0809",
            "key": 384
        },
        {
            "Overall": 80.9,
            "AR": 83.3,
            "CP": 78.5,
            "FP-C": 80.5,
            "FP-S": 85.2,
            "LR": 82.1,
            "RR": 76.0,
            "action_recognition": 82.9,
            "attribute_comparison": 82.7,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 85.0,
            "function_reasoning": 88.9,
            "future_prediction": 76.0,
            "identity_reasoning": 96.1,
            "image_emotion": 71.1,
            "image_quality": 59.7,
            "image_scene": 86.8,
            "image_style": 80.4,
            "image_topic": 96.7,
            "nature_relation": 87.0,
            "object_localization": 74.3,
            "ocr": 94.4,
            "physical_property_reasoning": 64.6,
            "physical_relation": 57.3,
            "social_relation": 80.2,
            "spatial_relationship": 74.7,
            "structuralized_imagetext_understanding": 86.2,
            "Method": [
                "Claude3.5-Sonnet-20241022",
                "https://docs.anthropic.com/en/docs/build-with-claude/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/11/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Claude3-5V_Sonnet_20241022",
            "key": 376
        },
        {
            "Overall": 82.1,
            "AR": 85.7,
            "CP": 81.3,
            "FP-C": 79.4,
            "FP-S": 87.9,
            "LR": 65.2,
            "RR": 85.3,
            "action_recognition": 86.3,
            "attribute_comparison": 84.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 90.5,
            "function_reasoning": 93.3,
            "future_prediction": 77.3,
            "identity_reasoning": 98.7,
            "image_emotion": 80.0,
            "image_quality": 60.5,
            "image_scene": 89.6,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 88.0,
            "object_localization": 71.4,
            "ocr": 97.8,
            "physical_property_reasoning": 64.6,
            "physical_relation": 72.0,
            "social_relation": 93.4,
            "spatial_relationship": 64.0,
            "structuralized_imagetext_understanding": 56.9,
            "Method": [
                "bailingMM-mini",
                "https://bailingmm.alipay.com/llm/landing"
            ],
            "Parameters": "17B",
            "Language Model": "bailing-mini",
            "Vision Model": "bailingMM-encoder-1B\nInternViT-6B",
            "Org": "Ant Group",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "bailingMM",
            "key": 385
        },
        {
            "Overall": 54.6,
            "AR": 67.8,
            "CP": 65.2,
            "FP-C": 43.4,
            "FP-S": 54.1,
            "LR": 33.7,
            "RR": 47.3,
            "action_recognition": 80.3,
            "attribute_comparison": 12.0,
            "attribute_recognition": 70.8,
            "celebrity_recognition": 53.1,
            "function_reasoning": 68.9,
            "future_prediction": 53.3,
            "identity_reasoning": 94.7,
            "image_emotion": 64.4,
            "image_quality": 25.8,
            "image_scene": 81.9,
            "image_style": 64.1,
            "image_topic": 94.4,
            "nature_relation": 50.0,
            "object_localization": 25.7,
            "ocr": 72.2,
            "physical_property_reasoning": 40.5,
            "physical_relation": 22.7,
            "social_relation": 64.8,
            "spatial_relationship": 17.3,
            "structuralized_imagetext_understanding": 20.2,
            "Method": [
                "Vintern-1B-v2",
                "https://huggingface.co/5CD-AI/Vintern-1B-v2"
            ],
            "Parameters": "3.7B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "InternViT-300M",
            "Org": "Fifth Civil Defender",
            "Time": "2024/11/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Vintern-1B-v2",
            "key": 387
        },
        {
            "Overall": 82.3,
            "AR": 84.5,
            "CP": 80.6,
            "FP-C": 79.4,
            "FP-S": 88.6,
            "LR": 76.6,
            "RR": 80.6,
            "action_recognition": 88.9,
            "attribute_comparison": 80.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 84.4,
            "function_reasoning": 95.6,
            "future_prediction": 81.3,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 59.7,
            "image_scene": 88.2,
            "image_style": 79.3,
            "image_topic": 96.7,
            "nature_relation": 89.1,
            "object_localization": 83.8,
            "ocr": 96.7,
            "physical_property_reasoning": 59.5,
            "physical_relation": 57.3,
            "social_relation": 91.2,
            "spatial_relationship": 64.0,
            "structuralized_imagetext_understanding": 73.4,
            "Method": [
                "RBDash-v1.5",
                "https://huggingface.co/RBDash-Team/RBDash-v1.5"
            ],
            "Parameters": "79B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "CLIP ViT-L/14\nInternViT-6B",
            "Org": "DLUT",
            "Time": "2024/11/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "RBDash_72b",
            "key": 388
        },
        {
            "Overall": 82.6,
            "AR": 87.3,
            "CP": 80.2,
            "FP-C": 80.1,
            "FP-S": 89.3,
            "LR": 71.7,
            "RR": 82.2,
            "action_recognition": 90.6,
            "attribute_comparison": 84.0,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 93.9,
            "function_reasoning": 92.2,
            "future_prediction": 80.0,
            "identity_reasoning": 98.7,
            "image_emotion": 84.4,
            "image_quality": 56.5,
            "image_scene": 84.7,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 92.4,
            "object_localization": 73.3,
            "ocr": 97.8,
            "physical_property_reasoning": 70.9,
            "physical_relation": 65.3,
            "social_relation": 85.7,
            "spatial_relationship": 60.0,
            "structuralized_imagetext_understanding": 66.1,
            "Method": [
                "Awaker2.5-VL",
                "https://github.com/MetabrainAGI/Awaker"
            ],
            "Parameters": "10.8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "QwenViT",
            "Org": "MetabrainAGI",
            "Time": "2024/11/23",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 389
        },
        {
            "Overall": 76.5,
            "AR": 80.8,
            "CP": 75.6,
            "FP-C": 69.3,
            "FP-S": 84.5,
            "LR": 64.1,
            "RR": 77.5,
            "action_recognition": 82.1,
            "attribute_comparison": 69.3,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 76.2,
            "function_reasoning": 90.0,
            "future_prediction": 69.3,
            "identity_reasoning": 96.1,
            "image_emotion": 71.1,
            "image_quality": 48.4,
            "image_scene": 88.2,
            "image_style": 75.0,
            "image_topic": 97.8,
            "nature_relation": 78.3,
            "object_localization": 81.9,
            "ocr": 93.3,
            "physical_property_reasoning": 55.7,
            "physical_relation": 68.0,
            "social_relation": 84.6,
            "spatial_relationship": 49.3,
            "structuralized_imagetext_understanding": 60.6,
            "Method": [
                "InternVL2-8B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/11/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2-8B-MPO",
            "key": 390
        },
        {
            "Overall": 75.6,
            "AR": 75.9,
            "CP": 75.0,
            "FP-C": 68.2,
            "FP-S": 84.2,
            "LR": 66.3,
            "RR": 76.4,
            "action_recognition": 82.1,
            "attribute_comparison": 66.7,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 77.6,
            "function_reasoning": 85.6,
            "future_prediction": 69.3,
            "identity_reasoning": 92.1,
            "image_emotion": 71.1,
            "image_quality": 47.6,
            "image_scene": 88.2,
            "image_style": 72.8,
            "image_topic": 97.8,
            "nature_relation": 79.3,
            "object_localization": 81.9,
            "ocr": 92.2,
            "physical_property_reasoning": 49.4,
            "physical_relation": 65.3,
            "social_relation": 82.4,
            "spatial_relationship": 48.0,
            "structuralized_imagetext_understanding": 64.2,
            "Method": [
                "InternVL2-8B-MPO-CoT",
                "https://huggingface.co/OpenGVLab/InternVL2-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/11/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2-8B-MPO-CoT",
            "key": 391
        },
        {
            "Overall": 77.8,
            "AR": 82.9,
            "CP": 79.1,
            "FP-C": 70.0,
            "FP-S": 83.5,
            "LR": 65.8,
            "RR": 77.5,
            "action_recognition": 84.6,
            "attribute_comparison": 65.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 81.6,
            "function_reasoning": 93.3,
            "future_prediction": 72.0,
            "identity_reasoning": 97.4,
            "image_emotion": 83.3,
            "image_quality": 50.0,
            "image_scene": 89.6,
            "image_style": 79.3,
            "image_topic": 97.8,
            "nature_relation": 81.5,
            "object_localization": 77.1,
            "ocr": 88.9,
            "physical_property_reasoning": 57.0,
            "physical_relation": 64.0,
            "social_relation": 84.6,
            "spatial_relationship": 52.0,
            "structuralized_imagetext_understanding": 61.5,
            "Method": [
                "Eagle-X5-34B-Chat",
                "https://huggingface.co/NVEagle/Eagle-X5-34B-Chat"
            ],
            "Parameters": "36.8B",
            "Language Model": "Yi-34B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/11/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Eagle-X5-34B-Chat",
            "key": 395
        },
        {
            "Overall": 82.8,
            "AR": 89.4,
            "CP": 80.0,
            "FP-C": 80.9,
            "FP-S": 88.6,
            "LR": 72.8,
            "RR": 81.4,
            "action_recognition": 83.8,
            "attribute_comparison": 88.0,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 83.0,
            "function_reasoning": 92.2,
            "future_prediction": 77.3,
            "identity_reasoning": 98.7,
            "image_emotion": 74.4,
            "image_quality": 63.7,
            "image_scene": 86.1,
            "image_style": 80.4,
            "image_topic": 97.8,
            "nature_relation": 90.2,
            "object_localization": 86.7,
            "ocr": 96.7,
            "physical_property_reasoning": 77.2,
            "physical_relation": 66.7,
            "social_relation": 84.6,
            "spatial_relationship": 69.3,
            "structuralized_imagetext_understanding": 69.7,
            "Method": [
                "Ovis1.6-Gemma2-27B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-27B"
            ],
            "Parameters": "28.9B",
            "Language Model": "Gemma2-27B",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/11/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis1.6-Gemma2-27B",
            "key": 396
        },
        {
            "Overall": 84.4,
            "AR": 87.8,
            "CP": 80.4,
            "FP-C": 88.0,
            "FP-S": 91.6,
            "LR": 74.5,
            "RR": 80.6,
            "action_recognition": 93.2,
            "attribute_comparison": 86.7,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 93.2,
            "function_reasoning": 94.4,
            "future_prediction": 70.7,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 59.7,
            "image_scene": 84.7,
            "image_style": 83.7,
            "image_topic": 96.7,
            "nature_relation": 91.3,
            "object_localization": 81.0,
            "ocr": 100.0,
            "physical_property_reasoning": 70.9,
            "physical_relation": 61.3,
            "social_relation": 85.7,
            "spatial_relationship": 81.3,
            "structuralized_imagetext_understanding": 77.1,
            "Method": [
                "Gemini-1.5-Pro-002",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/12/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GeminiPro1-5-002",
            "key": 398
        },
        {
            "Overall": 81.6,
            "AR": 86.5,
            "CP": 79.8,
            "FP-C": 79.8,
            "FP-S": 88.6,
            "LR": 72.8,
            "RR": 77.1,
            "action_recognition": 93.2,
            "attribute_comparison": 77.3,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 91.8,
            "function_reasoning": 96.7,
            "future_prediction": 73.3,
            "identity_reasoning": 98.7,
            "image_emotion": 83.3,
            "image_quality": 55.6,
            "image_scene": 83.3,
            "image_style": 85.9,
            "image_topic": 97.8,
            "nature_relation": 91.3,
            "object_localization": 73.3,
            "ocr": 95.6,
            "physical_property_reasoning": 63.3,
            "physical_relation": 48.0,
            "social_relation": 86.8,
            "spatial_relationship": 61.3,
            "structuralized_imagetext_understanding": 72.5,
            "Method": [
                "Gemini-1.5-Flash-002",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/12/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GeminiFlash1-5-002",
            "key": 399
        },
        {
            "Overall": 84.8,
            "AR": 89.0,
            "CP": 82.6,
            "FP-C": 88.8,
            "FP-S": 86.1,
            "LR": 81.0,
            "RR": 82.2,
            "action_recognition": 95.7,
            "attribute_comparison": 88.0,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 76.9,
            "function_reasoning": 92.2,
            "future_prediction": 85.3,
            "identity_reasoning": 97.4,
            "image_emotion": 81.1,
            "image_quality": 61.3,
            "image_scene": 88.9,
            "image_style": 88.0,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 81.9,
            "ocr": 97.8,
            "physical_property_reasoning": 77.2,
            "physical_relation": 58.7,
            "social_relation": 90.1,
            "spatial_relationship": 78.7,
            "structuralized_imagetext_understanding": 78.0,
            "Method": [
                "GPT-4o (1120, detail-high)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/12/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GPT4o_20241120",
            "key": 400
        },
        {
            "Overall": 78.2,
            "AR": 88.6,
            "CP": 73.7,
            "FP-C": 70.8,
            "FP-S": 86.5,
            "LR": 68.5,
            "RR": 78.3,
            "action_recognition": 82.9,
            "attribute_comparison": 72.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 84.4,
            "function_reasoning": 94.4,
            "future_prediction": 72.0,
            "identity_reasoning": 96.1,
            "image_emotion": 51.1,
            "image_quality": 59.7,
            "image_scene": 86.8,
            "image_style": 69.6,
            "image_topic": 98.9,
            "nature_relation": 84.8,
            "object_localization": 76.2,
            "ocr": 95.6,
            "physical_property_reasoning": 74.7,
            "physical_relation": 68.0,
            "social_relation": 80.2,
            "spatial_relationship": 50.7,
            "structuralized_imagetext_understanding": 66.1,
            "Method": [
                "Aria",
                "https://huggingface.co/rhymes-ai/Aria"
            ],
            "Parameters": "25.3B",
            "Language Model": "Aria-MoE",
            "Vision Model": "SigLIP-400M",
            "Org": "Rhymes AI",
            "Time": "2024/12/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Aria",
            "key": 401
        },
        {
            "Overall": 81.2,
            "AR": 87.8,
            "CP": 79.8,
            "FP-C": 76.0,
            "FP-S": 88.2,
            "LR": 66.3,
            "RR": 82.2,
            "action_recognition": 84.6,
            "attribute_comparison": 78.7,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 89.1,
            "function_reasoning": 94.4,
            "future_prediction": 74.7,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 55.6,
            "image_scene": 86.8,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 92.4,
            "object_localization": 78.1,
            "ocr": 92.2,
            "physical_property_reasoning": 70.9,
            "physical_relation": 60.0,
            "social_relation": 90.1,
            "spatial_relationship": 60.0,
            "structuralized_imagetext_understanding": 60.6,
            "Method": [
                "POINTS1.5-Qwen2.5-7B",
                "https://huggingface.co/WePOINTS/POINTS-1-5-Qwen-2-5-7B-Chat"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen-2.5-7B",
            "Vision Model": "NaViT",
            "Org": "WeChat",
            "Time": "2024/12/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTSV15-Qwen-2.5-7B-Chat",
            "key": 403
        },
        {
            "Overall": 83.9,
            "AR": 89.8,
            "CP": 83.3,
            "FP-C": 80.9,
            "FP-S": 88.9,
            "LR": 75.0,
            "RR": 80.6,
            "action_recognition": 92.3,
            "attribute_comparison": 81.3,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 85.0,
            "function_reasoning": 96.7,
            "future_prediction": 77.3,
            "identity_reasoning": 96.1,
            "image_emotion": 82.2,
            "image_quality": 67.7,
            "image_scene": 91.0,
            "image_style": 79.3,
            "image_topic": 97.8,
            "nature_relation": 85.9,
            "object_localization": 83.8,
            "ocr": 94.4,
            "physical_property_reasoning": 75.9,
            "physical_relation": 70.7,
            "social_relation": 83.5,
            "spatial_relationship": 62.7,
            "structuralized_imagetext_understanding": 73.4,
            "Method": [
                "BailingMM-Lite-1203",
                "https://zxb.alipay.com/llm/landing"
            ],
            "Parameters": "21B",
            "Language Model": "Bailing-20B",
            "Vision Model": "SigLIP-400M",
            "Org": "Ant Group",
            "Time": "2024/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "bailingMM-Lite",
            "key": 404
        },
        {
            "Overall": 79.7,
            "AR": 88.2,
            "CP": 74.4,
            "FP-C": 81.3,
            "FP-S": 87.0,
            "LR": 76.1,
            "RR": 71.7,
            "action_recognition": 87.2,
            "attribute_comparison": 82.7,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 79.6,
            "function_reasoning": 95.6,
            "future_prediction": 76.0,
            "identity_reasoning": 94.7,
            "image_emotion": 51.1,
            "image_quality": 48.4,
            "image_scene": 91.0,
            "image_style": 84.8,
            "image_topic": 96.7,
            "nature_relation": 87.0,
            "object_localization": 81.9,
            "ocr": 98.9,
            "physical_property_reasoning": 73.4,
            "physical_relation": 65.3,
            "social_relation": 61.5,
            "spatial_relationship": 70.7,
            "structuralized_imagetext_understanding": 76.1,
            "Method": [
                "GLM-4v-Plus",
                "https://open.bigmodel.cn/dev/api/normal-model/glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GLM4V_PLUS",
            "key": 412
        },
        {
            "Overall": 79.8,
            "AR": 84.5,
            "CP": 79.3,
            "FP-C": 73.0,
            "FP-S": 89.8,
            "LR": 66.3,
            "RR": 76.7,
            "action_recognition": 87.2,
            "attribute_comparison": 77.3,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 95.2,
            "function_reasoning": 95.6,
            "future_prediction": 82.7,
            "identity_reasoning": 100.0,
            "image_emotion": 76.7,
            "image_quality": 50.0,
            "image_scene": 88.9,
            "image_style": 88.0,
            "image_topic": 97.8,
            "nature_relation": 89.1,
            "object_localization": 79.0,
            "ocr": 95.6,
            "physical_property_reasoning": 57.0,
            "physical_relation": 54.7,
            "social_relation": 82.4,
            "spatial_relationship": 46.7,
            "structuralized_imagetext_understanding": 55.0,
            "Method": [
                "Step-1.5V-mini",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "StepFun",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Step1.5V-mini",
            "key": 413
        },
        {
            "Overall": 57.9,
            "AR": 66.1,
            "CP": 68.5,
            "FP-C": 46.8,
            "FP-S": 57.3,
            "LR": 45.1,
            "RR": 49.2,
            "action_recognition": 78.6,
            "attribute_comparison": 14.7,
            "attribute_recognition": 73.0,
            "celebrity_recognition": 36.1,
            "function_reasoning": 74.4,
            "future_prediction": 52.0,
            "identity_reasoning": 82.9,
            "image_emotion": 68.9,
            "image_quality": 33.9,
            "image_scene": 86.1,
            "image_style": 62.0,
            "image_topic": 94.4,
            "nature_relation": 59.8,
            "object_localization": 42.9,
            "ocr": 93.3,
            "physical_property_reasoning": 40.5,
            "physical_relation": 26.7,
            "social_relation": 57.1,
            "spatial_relationship": 29.3,
            "structuralized_imagetext_understanding": 40.4,
            "Method": [
                "abab6.5s",
                "https://www.minimaxi.com/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "MiniMax",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "abab6.5s",
            "key": 414
        },
        {
            "Overall": 83.4,
            "AR": 85.7,
            "CP": 80.4,
            "FP-C": 83.5,
            "FP-S": 89.8,
            "LR": 76.6,
            "RR": 81.4,
            "action_recognition": 85.5,
            "attribute_comparison": 86.7,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 83.0,
            "function_reasoning": 94.4,
            "future_prediction": 84.0,
            "identity_reasoning": 88.2,
            "image_emotion": 76.7,
            "image_quality": 64.5,
            "image_scene": 88.9,
            "image_style": 75.0,
            "image_topic": 97.8,
            "nature_relation": 91.3,
            "object_localization": 89.5,
            "ocr": 97.8,
            "physical_property_reasoning": 73.4,
            "physical_relation": 64.0,
            "social_relation": 85.7,
            "spatial_relationship": 77.3,
            "structuralized_imagetext_understanding": 71.6,
            "Method": [
                "abab7-preview",
                "https://www.minimaxi.com/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "MiniMax",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "abab7-preview",
            "key": 415
        },
        {
            "Overall": 86.1,
            "AR": 86.9,
            "CP": 82.4,
            "FP-C": 86.9,
            "FP-S": 93.0,
            "LR": 82.6,
            "RR": 83.3,
            "action_recognition": 88.0,
            "attribute_comparison": 90.7,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 89.1,
            "function_reasoning": 94.4,
            "future_prediction": 81.3,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 62.9,
            "image_scene": 88.9,
            "image_style": 84.8,
            "image_topic": 96.7,
            "nature_relation": 85.9,
            "object_localization": 91.4,
            "ocr": 97.8,
            "physical_property_reasoning": 68.4,
            "physical_relation": 76.0,
            "social_relation": 86.8,
            "spatial_relationship": 81.3,
            "structuralized_imagetext_understanding": 83.5,
            "Method": [
                "SenseNova",
                "https://platform.sensenova.cn/home"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "SenseTime",
            "Time": "2024/12/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SenseChat-Vision",
            "key": 416
        },
        {
            "Overall": 84.7,
            "AR": 86.9,
            "CP": 82.2,
            "FP-C": 83.9,
            "FP-S": 91.2,
            "LR": 72.8,
            "RR": 86.0,
            "action_recognition": 92.3,
            "attribute_comparison": 86.7,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 92.5,
            "function_reasoning": 94.4,
            "future_prediction": 76.0,
            "identity_reasoning": 97.4,
            "image_emotion": 81.1,
            "image_quality": 63.7,
            "image_scene": 90.3,
            "image_style": 80.4,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 81.9,
            "ocr": 95.6,
            "physical_property_reasoning": 68.4,
            "physical_relation": 72.0,
            "social_relation": 90.1,
            "spatial_relationship": 68.0,
            "structuralized_imagetext_understanding": 70.6,
            "Method": [
                "Taiyi",
                "https://taiyi.megvii.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Megvii & StepFun",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Taiyi",
            "key": 383
        },
        {
            "Overall": 68.2,
            "AR": 76.7,
            "CP": 75.6,
            "FP-C": 59.9,
            "FP-S": 71.2,
            "LR": 47.8,
            "RR": 62.8,
            "action_recognition": 89.7,
            "attribute_comparison": 40.0,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 64.6,
            "function_reasoning": 82.2,
            "future_prediction": 57.3,
            "identity_reasoning": 92.1,
            "image_emotion": 76.7,
            "image_quality": 51.6,
            "image_scene": 84.7,
            "image_style": 70.7,
            "image_topic": 97.8,
            "nature_relation": 62.0,
            "object_localization": 54.3,
            "ocr": 87.8,
            "physical_property_reasoning": 55.7,
            "physical_relation": 49.3,
            "social_relation": 74.7,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 41.3,
            "Method": [
                "InternVL2.5-1B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-1B"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen-2.5-0.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-1B",
            "key": 417
        },
        {
            "Overall": 72.4,
            "AR": 74.3,
            "CP": 77.8,
            "FP-C": 65.5,
            "FP-S": 76.1,
            "LR": 54.3,
            "RR": 73.3,
            "action_recognition": 88.9,
            "attribute_comparison": 54.7,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 67.3,
            "function_reasoning": 83.3,
            "future_prediction": 61.3,
            "identity_reasoning": 94.7,
            "image_emotion": 77.8,
            "image_quality": 53.2,
            "image_scene": 88.9,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 67.4,
            "object_localization": 60.0,
            "ocr": 88.9,
            "physical_property_reasoning": 44.3,
            "physical_relation": 58.7,
            "social_relation": 91.2,
            "spatial_relationship": 40.0,
            "structuralized_imagetext_understanding": 49.5,
            "Method": [
                "InternVL2.5-2B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-2B"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2.5-1.8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-2B",
            "key": 418
        },
        {
            "Overall": 78.8,
            "AR": 83.7,
            "CP": 81.5,
            "FP-C": 73.4,
            "FP-S": 82.8,
            "LR": 68.5,
            "RR": 74.4,
            "action_recognition": 85.5,
            "attribute_comparison": 80.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 78.2,
            "function_reasoning": 87.8,
            "future_prediction": 80.0,
            "identity_reasoning": 96.1,
            "image_emotion": 83.3,
            "image_quality": 57.3,
            "image_scene": 88.9,
            "image_style": 84.8,
            "image_topic": 97.8,
            "nature_relation": 67.4,
            "object_localization": 69.5,
            "ocr": 95.6,
            "physical_property_reasoning": 67.1,
            "physical_relation": 64.0,
            "social_relation": 90.1,
            "spatial_relationship": 48.0,
            "structuralized_imagetext_understanding": 60.6,
            "Method": [
                "InternVL2.5-4B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-4B"
            ],
            "Parameters": "4B",
            "Language Model": "Qwen-2.5-3B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-4B",
            "key": 419
        },
        {
            "Overall": 83.2,
            "AR": 85.3,
            "CP": 81.3,
            "FP-C": 81.3,
            "FP-S": 90.0,
            "LR": 72.8,
            "RR": 82.9,
            "action_recognition": 93.2,
            "attribute_comparison": 88.0,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 85.7,
            "function_reasoning": 91.1,
            "future_prediction": 81.3,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 55.6,
            "image_scene": 91.7,
            "image_style": 82.6,
            "image_topic": 97.8,
            "nature_relation": 88.0,
            "object_localization": 85.7,
            "ocr": 96.7,
            "physical_property_reasoning": 67.1,
            "physical_relation": 70.7,
            "social_relation": 87.9,
            "spatial_relationship": 56.0,
            "structuralized_imagetext_understanding": 67.0,
            "Method": [
                "InternVL2.5-8B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-8B"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-8B",
            "key": 420
        },
        {
            "Overall": 84.4,
            "AR": 86.5,
            "CP": 83.3,
            "FP-C": 82.0,
            "FP-S": 90.0,
            "LR": 73.9,
            "RR": 85.3,
            "action_recognition": 93.2,
            "attribute_comparison": 85.3,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 85.7,
            "function_reasoning": 96.7,
            "future_prediction": 80.0,
            "identity_reasoning": 96.1,
            "image_emotion": 83.3,
            "image_quality": 62.1,
            "image_scene": 91.0,
            "image_style": 85.9,
            "image_topic": 97.8,
            "nature_relation": 89.1,
            "object_localization": 86.7,
            "ocr": 95.6,
            "physical_property_reasoning": 65.8,
            "physical_relation": 74.7,
            "social_relation": 90.1,
            "spatial_relationship": 61.3,
            "structuralized_imagetext_understanding": 69.7,
            "Method": [
                "InternVL2.5-26B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-26B"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2.5-20B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-26B",
            "key": 421
        },
        {
            "Overall": 85.3,
            "AR": 89.0,
            "CP": 81.3,
            "FP-C": 82.0,
            "FP-S": 91.6,
            "LR": 83.2,
            "RR": 84.5,
            "action_recognition": 93.2,
            "attribute_comparison": 78.7,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 87.1,
            "function_reasoning": 94.4,
            "future_prediction": 82.7,
            "identity_reasoning": 96.1,
            "image_emotion": 78.9,
            "image_quality": 56.5,
            "image_scene": 92.4,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 88.0,
            "object_localization": 88.6,
            "ocr": 98.9,
            "physical_property_reasoning": 75.9,
            "physical_relation": 74.7,
            "social_relation": 89.0,
            "spatial_relationship": 68.0,
            "structuralized_imagetext_understanding": 83.5,
            "Method": [
                "InternVL2.5-38B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-38B"
            ],
            "Parameters": "38B",
            "Language Model": "Qwen-2.5-32B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-38B",
            "key": 422
        },
        {
            "Overall": 87.3,
            "AR": 89.4,
            "CP": 84.1,
            "FP-C": 87.3,
            "FP-S": 92.3,
            "LR": 83.2,
            "RR": 86.4,
            "action_recognition": 93.2,
            "attribute_comparison": 86.7,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 89.1,
            "function_reasoning": 98.9,
            "future_prediction": 86.7,
            "identity_reasoning": 98.7,
            "image_emotion": 85.6,
            "image_quality": 63.7,
            "image_scene": 92.4,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 91.3,
            "object_localization": 88.6,
            "ocr": 97.8,
            "physical_property_reasoning": 69.6,
            "physical_relation": 76.0,
            "social_relation": 90.1,
            "spatial_relationship": 78.7,
            "structuralized_imagetext_understanding": 80.7,
            "Method": [
                "InternVL2.5-78B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-78B"
            ],
            "Parameters": "78B",
            "Language Model": "Qwen-2.5-72B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-78B",
            "key": 423
        },
        {
            "Overall": 75.5,
            "AR": 84.5,
            "CP": 77.4,
            "FP-C": 68.2,
            "FP-S": 80.5,
            "LR": 58.7,
            "RR": 74.4,
            "action_recognition": 82.9,
            "attribute_comparison": 77.3,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 74.1,
            "function_reasoning": 88.9,
            "future_prediction": 69.3,
            "identity_reasoning": 97.4,
            "image_emotion": 74.4,
            "image_quality": 53.2,
            "image_scene": 86.1,
            "image_style": 80.4,
            "image_topic": 96.7,
            "nature_relation": 83.7,
            "object_localization": 67.6,
            "ocr": 92.2,
            "physical_property_reasoning": 67.1,
            "physical_relation": 50.7,
            "social_relation": 84.6,
            "spatial_relationship": 36.0,
            "structuralized_imagetext_understanding": 51.4,
            "Method": [
                "SAIL-VL-2B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL-2B"
            ],
            "Parameters": "2.1B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "InternViT-300M",
            "Org": "ByteDance",
            "Time": "2024/12/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL-2B",
            "key": 424
        },
        {
            "Overall": 67.2,
            "AR": 74.3,
            "CP": 74.3,
            "FP-C": 57.7,
            "FP-S": 71.9,
            "LR": 45.1,
            "RR": 63.2,
            "action_recognition": 85.5,
            "attribute_comparison": 45.3,
            "attribute_recognition": 83.1,
            "celebrity_recognition": 63.9,
            "function_reasoning": 81.1,
            "future_prediction": 54.7,
            "identity_reasoning": 92.1,
            "image_emotion": 77.8,
            "image_quality": 50.8,
            "image_scene": 84.0,
            "image_style": 65.2,
            "image_topic": 96.7,
            "nature_relation": 62.0,
            "object_localization": 58.1,
            "ocr": 90.0,
            "physical_property_reasoning": 49.4,
            "physical_relation": 49.3,
            "social_relation": 75.8,
            "spatial_relationship": 26.7,
            "structuralized_imagetext_understanding": 38.5,
            "Method": [
                "InternVL2.5-1B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-1B-MPO"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen-2.5-0.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-1B-MPO",
            "key": 425
        },
        {
            "Overall": 71.9,
            "AR": 71.4,
            "CP": 77.4,
            "FP-C": 63.7,
            "FP-S": 77.0,
            "LR": 54.9,
            "RR": 73.3,
            "action_recognition": 82.9,
            "attribute_comparison": 58.7,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 69.4,
            "function_reasoning": 81.1,
            "future_prediction": 66.7,
            "identity_reasoning": 93.4,
            "image_emotion": 78.9,
            "image_quality": 51.6,
            "image_scene": 88.9,
            "image_style": 72.8,
            "image_topic": 97.8,
            "nature_relation": 64.1,
            "object_localization": 62.9,
            "ocr": 87.8,
            "physical_property_reasoning": 39.2,
            "physical_relation": 62.7,
            "social_relation": 91.2,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 46.8,
            "Method": [
                "InternVL2.5-2B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-2B-MPO"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2.5-1.8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-2B-MPO",
            "key": 426
        },
        {
            "Overall": 78.6,
            "AR": 82.0,
            "CP": 80.7,
            "FP-C": 74.9,
            "FP-S": 83.3,
            "LR": 66.8,
            "RR": 75.6,
            "action_recognition": 86.3,
            "attribute_comparison": 80.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 76.9,
            "function_reasoning": 87.8,
            "future_prediction": 78.7,
            "identity_reasoning": 96.1,
            "image_emotion": 78.9,
            "image_quality": 58.1,
            "image_scene": 90.3,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 69.6,
            "object_localization": 73.3,
            "ocr": 95.6,
            "physical_property_reasoning": 62.0,
            "physical_relation": 66.7,
            "social_relation": 89.0,
            "spatial_relationship": 52.0,
            "structuralized_imagetext_understanding": 58.7,
            "Method": [
                "InternVL2.5-4B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-4B-MPO"
            ],
            "Parameters": "4B",
            "Language Model": "Qwen-2.5-3B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-4B-MPO",
            "key": 427
        },
        {
            "Overall": 82.4,
            "AR": 84.1,
            "CP": 80.9,
            "FP-C": 78.3,
            "FP-S": 89.1,
            "LR": 72.8,
            "RR": 83.7,
            "action_recognition": 88.9,
            "attribute_comparison": 84.0,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 84.4,
            "function_reasoning": 90.0,
            "future_prediction": 80.0,
            "identity_reasoning": 97.4,
            "image_emotion": 83.3,
            "image_quality": 56.5,
            "image_scene": 90.3,
            "image_style": 80.4,
            "image_topic": 97.8,
            "nature_relation": 85.9,
            "object_localization": 82.9,
            "ocr": 96.7,
            "physical_property_reasoning": 64.6,
            "physical_relation": 72.0,
            "social_relation": 91.2,
            "spatial_relationship": 56.0,
            "structuralized_imagetext_understanding": 67.9,
            "Method": [
                "InternVL2.5-8B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-8B-MPO",
            "key": 428
        },
        {
            "Overall": 84.3,
            "AR": 87.8,
            "CP": 81.9,
            "FP-C": 82.0,
            "FP-S": 90.5,
            "LR": 72.8,
            "RR": 86.0,
            "action_recognition": 90.6,
            "attribute_comparison": 86.7,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 86.4,
            "function_reasoning": 97.8,
            "future_prediction": 80.0,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 60.5,
            "image_scene": 87.5,
            "image_style": 85.9,
            "image_topic": 97.8,
            "nature_relation": 90.2,
            "object_localization": 87.6,
            "ocr": 95.6,
            "physical_property_reasoning": 67.1,
            "physical_relation": 74.7,
            "social_relation": 91.2,
            "spatial_relationship": 64.0,
            "structuralized_imagetext_understanding": 67.9,
            "Method": [
                "InternVL2.5-26B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-26B-MPO"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2.5-20B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-26B-MPO",
            "key": 429
        },
        {
            "Overall": 85.4,
            "AR": 88.2,
            "CP": 81.7,
            "FP-C": 83.5,
            "FP-S": 91.2,
            "LR": 83.7,
            "RR": 83.7,
            "action_recognition": 91.5,
            "attribute_comparison": 80.0,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 86.4,
            "function_reasoning": 94.4,
            "future_prediction": 82.7,
            "identity_reasoning": 96.1,
            "image_emotion": 80.0,
            "image_quality": 55.6,
            "image_scene": 92.4,
            "image_style": 85.9,
            "image_topic": 97.8,
            "nature_relation": 90.2,
            "object_localization": 87.6,
            "ocr": 98.9,
            "physical_property_reasoning": 73.4,
            "physical_relation": 70.7,
            "social_relation": 87.9,
            "spatial_relationship": 74.7,
            "structuralized_imagetext_understanding": 84.4,
            "Method": [
                "InternVL2.5-38B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-38B-MPO"
            ],
            "Parameters": "38B",
            "Language Model": "Qwen-2.5-32B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-38B-MPO",
            "key": 430
        },
        {
            "Overall": 81.4,
            "AR": 87.8,
            "CP": 79.1,
            "FP-C": 76.4,
            "FP-S": 89.3,
            "LR": 70.1,
            "RR": 80.2,
            "action_recognition": 89.7,
            "attribute_comparison": 74.7,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 90.5,
            "function_reasoning": 96.7,
            "future_prediction": 82.7,
            "identity_reasoning": 94.7,
            "image_emotion": 76.7,
            "image_quality": 55.6,
            "image_scene": 87.5,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 91.3,
            "object_localization": 78.1,
            "ocr": 96.7,
            "physical_property_reasoning": 70.9,
            "physical_relation": 57.3,
            "social_relation": 87.9,
            "spatial_relationship": 57.3,
            "structuralized_imagetext_understanding": 61.5,
            "Method": [
                "Valley-Eagle",
                "https://huggingface.co/bytedance-research/Valley-Eagle-7B"
            ],
            "Parameters": "8.9B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "Qwen-ViT\nSigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/12/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "valley_eagle",
            "key": 431
        },
        {
            "Overall": 87.9,
            "AR": 89.0,
            "CP": 84.6,
            "FP-C": 88.4,
            "FP-S": 93.3,
            "LR": 84.2,
            "RR": 87.2,
            "action_recognition": 91.5,
            "attribute_comparison": 90.7,
            "attribute_recognition": 97.8,
            "celebrity_recognition": 88.4,
            "function_reasoning": 96.7,
            "future_prediction": 88.0,
            "identity_reasoning": 98.7,
            "image_emotion": 83.3,
            "image_quality": 65.3,
            "image_scene": 92.4,
            "image_style": 87.0,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 92.4,
            "ocr": 97.8,
            "physical_property_reasoning": 70.9,
            "physical_relation": 74.7,
            "social_relation": 91.2,
            "spatial_relationship": 81.3,
            "structuralized_imagetext_understanding": 81.7,
            "Method": [
                "InternVL2.5-78B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-78B-MPO"
            ],
            "Parameters": "78B",
            "Language Model": "Qwen-2.5-72B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-78B-MPO",
            "key": 432
        },
        {
            "Overall": 81.6,
            "AR": 86.1,
            "CP": 78.7,
            "FP-C": 82.8,
            "FP-S": 86.8,
            "LR": 77.7,
            "RR": 76.0,
            "action_recognition": 85.5,
            "attribute_comparison": 88.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 85.7,
            "function_reasoning": 92.2,
            "future_prediction": 81.3,
            "identity_reasoning": 93.4,
            "image_emotion": 76.7,
            "image_quality": 58.9,
            "image_scene": 88.2,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 81.5,
            "object_localization": 76.2,
            "ocr": 94.4,
            "physical_property_reasoning": 72.2,
            "physical_relation": 60.0,
            "social_relation": 83.5,
            "spatial_relationship": 73.3,
            "structuralized_imagetext_understanding": 75.2,
            "Method": [
                "TeleMM",
                "https://docs.siliconflow.cn/api-reference/chat-completions/chat-completions"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "China Telecom",
            "Time": "2024/12/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "TeleMM",
            "key": 397
        },
        {
            "Overall": 71.7,
            "AR": 80.4,
            "CP": 75.0,
            "FP-C": 68.2,
            "FP-S": 77.3,
            "LR": 49.5,
            "RR": 66.7,
            "action_recognition": 84.6,
            "attribute_comparison": 72.0,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 77.6,
            "function_reasoning": 88.9,
            "future_prediction": 61.3,
            "identity_reasoning": 97.4,
            "image_emotion": 72.2,
            "image_quality": 42.7,
            "image_scene": 84.7,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 62.0,
            "object_localization": 55.2,
            "ocr": 88.9,
            "physical_property_reasoning": 54.4,
            "physical_relation": 57.3,
            "social_relation": 79.1,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 41.3,
            "Method": [
                "DeepSeek-VL2-Tiny",
                "https://huggingface.co/deepseek-ai/deepseek-vl2-tiny"
            ],
            "Parameters": "3.4B",
            "Language Model": "DeepSeekMoE-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2_tiny",
            "key": 433
        },
        {
            "Overall": 80.7,
            "AR": 82.0,
            "CP": 81.9,
            "FP-C": 76.4,
            "FP-S": 87.5,
            "LR": 68.5,
            "RR": 78.7,
            "action_recognition": 86.3,
            "attribute_comparison": 84.0,
            "attribute_recognition": 97.8,
            "celebrity_recognition": 85.7,
            "function_reasoning": 93.3,
            "future_prediction": 78.7,
            "identity_reasoning": 97.4,
            "image_emotion": 76.7,
            "image_quality": 61.3,
            "image_scene": 89.6,
            "image_style": 87.0,
            "image_topic": 97.8,
            "nature_relation": 85.9,
            "object_localization": 77.1,
            "ocr": 92.2,
            "physical_property_reasoning": 54.4,
            "physical_relation": 61.3,
            "social_relation": 85.7,
            "spatial_relationship": 53.3,
            "structuralized_imagetext_understanding": 61.5,
            "Method": [
                "DeepSeek-VL2-Small",
                "https://huggingface.co/deepseek-ai/deepseek-vl2-small"
            ],
            "Parameters": "16.1B",
            "Language Model": "DeepSeekMoE-16B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2_small",
            "key": 434
        },
        {
            "Overall": 82.3,
            "AR": 87.8,
            "CP": 79.8,
            "FP-C": 80.9,
            "FP-S": 88.6,
            "LR": 74.5,
            "RR": 79.1,
            "action_recognition": 82.1,
            "attribute_comparison": 92.0,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 83.0,
            "function_reasoning": 93.3,
            "future_prediction": 77.3,
            "identity_reasoning": 97.4,
            "image_emotion": 77.8,
            "image_quality": 58.1,
            "image_scene": 90.3,
            "image_style": 77.2,
            "image_topic": 97.8,
            "nature_relation": 81.5,
            "object_localization": 84.8,
            "ocr": 95.6,
            "physical_property_reasoning": 72.2,
            "physical_relation": 68.0,
            "social_relation": 85.7,
            "spatial_relationship": 68.0,
            "structuralized_imagetext_understanding": 72.5,
            "Method": [
                "VARCO-VISION-14B",
                "https://huggingface.co/NCSOFT/VARCO-VISION-14B-HF"
            ],
            "Parameters": "15.2B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "SigLIP-400M",
            "Org": "NC Research",
            "Time": "2025/01/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "varco-vision-hf",
            "key": 437
        },
        {
            "Overall": 70.4,
            "AR": 73.5,
            "CP": 67.2,
            "FP-C": 78.3,
            "FP-S": 71.0,
            "LR": 63.6,
            "RR": 69.8,
            "action_recognition": 86.3,
            "attribute_comparison": 78.7,
            "attribute_recognition": 70.8,
            "celebrity_recognition": 72.1,
            "function_reasoning": 80.0,
            "future_prediction": 64.0,
            "identity_reasoning": 78.9,
            "image_emotion": 64.4,
            "image_quality": 54.0,
            "image_scene": 74.3,
            "image_style": 65.2,
            "image_topic": 78.9,
            "nature_relation": 79.3,
            "object_localization": 66.7,
            "ocr": 74.4,
            "physical_property_reasoning": 60.8,
            "physical_relation": 50.7,
            "social_relation": 75.8,
            "spatial_relationship": 65.3,
            "structuralized_imagetext_understanding": 63.3,
            "Method": [
                "Gemini-2.0-Flash",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2025/01/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GeminiFlash2-0",
            "key": 438
        },
        {
            "Overall": 74.4,
            "AR": 85.3,
            "CP": 73.0,
            "FP-C": 66.7,
            "FP-S": 82.8,
            "LR": 56.5,
            "RR": 73.6,
            "action_recognition": 81.2,
            "attribute_comparison": 62.7,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 89.1,
            "function_reasoning": 90.0,
            "future_prediction": 66.7,
            "identity_reasoning": 98.7,
            "image_emotion": 74.4,
            "image_quality": 46.8,
            "image_scene": 83.3,
            "image_style": 75.0,
            "image_topic": 88.9,
            "nature_relation": 79.3,
            "object_localization": 62.9,
            "ocr": 92.2,
            "physical_property_reasoning": 67.1,
            "physical_relation": 56.0,
            "social_relation": 82.4,
            "spatial_relationship": 48.0,
            "structuralized_imagetext_understanding": 49.5,
            "Method": [
                "LLaVA-CoT",
                "https://huggingface.co/Xkev/Llama-3.2V-11B-cot"
            ],
            "Parameters": "11B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Peking University",
            "Time": "2025/01/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "LLaVA-CoT",
            "key": 402
        },
        {
            "Overall": 87.6,
            "AR": 89.8,
            "CP": 82.6,
            "FP-C": 89.5,
            "FP-S": 94.4,
            "LR": 82.1,
            "RR": 86.8,
            "action_recognition": 94.9,
            "attribute_comparison": 92.0,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 98.6,
            "function_reasoning": 96.7,
            "future_prediction": 88.0,
            "identity_reasoning": 98.7,
            "image_emotion": 78.9,
            "image_quality": 65.3,
            "image_scene": 88.9,
            "image_style": 84.8,
            "image_topic": 97.8,
            "nature_relation": 94.6,
            "object_localization": 83.8,
            "ocr": 97.8,
            "physical_property_reasoning": 73.4,
            "physical_relation": 74.7,
            "social_relation": 89.0,
            "spatial_relationship": 78.7,
            "structuralized_imagetext_understanding": 78.0,
            "Method": [
                "Step-1o",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "StepFun",
            "Time": "2025/01/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Step1o",
            "key": 439
        },
        {
            "Overall": 83.9,
            "AR": 87.3,
            "CP": 80.7,
            "FP-C": 83.5,
            "FP-S": 90.7,
            "LR": 76.6,
            "RR": 81.8,
            "action_recognition": 92.3,
            "attribute_comparison": 74.7,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 94.6,
            "function_reasoning": 88.9,
            "future_prediction": 76.0,
            "identity_reasoning": 92.1,
            "image_emotion": 80.0,
            "image_quality": 60.5,
            "image_scene": 89.6,
            "image_style": 80.4,
            "image_topic": 95.6,
            "nature_relation": 88.0,
            "object_localization": 79.0,
            "ocr": 96.7,
            "physical_property_reasoning": 81.0,
            "physical_relation": 68.0,
            "social_relation": 86.8,
            "spatial_relationship": 78.7,
            "structuralized_imagetext_understanding": 77.1,
            "Method": [
                "HunYuan-Standard-Vision",
                "https://cloud.tencent.com/document/product/1729/104753"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Tencent",
            "Time": "2025/01/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "HunYuan-Standard-Vision",
            "key": 440
        },
        {
            "Overall": 77.1,
            "AR": 88.6,
            "CP": 78.7,
            "FP-C": 70.4,
            "FP-S": 81.2,
            "LR": 61.4,
            "RR": 74.0,
            "action_recognition": 88.9,
            "attribute_comparison": 77.3,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 80.3,
            "function_reasoning": 92.2,
            "future_prediction": 78.7,
            "identity_reasoning": 96.1,
            "image_emotion": 78.9,
            "image_quality": 51.6,
            "image_scene": 88.9,
            "image_style": 79.3,
            "image_topic": 98.9,
            "nature_relation": 79.3,
            "object_localization": 63.8,
            "ocr": 88.9,
            "physical_property_reasoning": 77.2,
            "physical_relation": 48.0,
            "social_relation": 90.1,
            "spatial_relationship": 34.7,
            "structuralized_imagetext_understanding": 49.5,
            "Method": [
                "Ross-Qwen2-7B",
                "https://huggingface.co/HaochenWang/ross-qwen2-7b"
            ],
            "Parameters": "8.2B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "CASIA",
            "Time": "2025/01/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "ross-qwen2-7b",
            "key": 441
        },
        {
            "Overall": 77.5,
            "AR": 82.9,
            "CP": 77.8,
            "FP-C": 73.0,
            "FP-S": 84.5,
            "LR": 64.1,
            "RR": 74.4,
            "action_recognition": 86.3,
            "attribute_comparison": 73.3,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 76.2,
            "function_reasoning": 84.4,
            "future_prediction": 72.0,
            "identity_reasoning": 96.1,
            "image_emotion": 74.4,
            "image_quality": 51.6,
            "image_scene": 89.6,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 77.2,
            "object_localization": 77.1,
            "ocr": 100.0,
            "physical_property_reasoning": 68.4,
            "physical_relation": 60.0,
            "social_relation": 83.5,
            "spatial_relationship": 52.0,
            "structuralized_imagetext_understanding": 58.7,
            "Method": [
                "VITA-1.5",
                "https://huggingface.co/VITA-MLLM/VITA-1.5"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "InternViT-300M",
            "Org": "NJU",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "vita_qwen2",
            "key": 442
        },
        {
            "Overall": 70.8,
            "AR": 79.6,
            "CP": 74.1,
            "FP-C": 58.8,
            "FP-S": 72.9,
            "LR": 59.8,
            "RR": 72.5,
            "action_recognition": 78.6,
            "attribute_comparison": 48.0,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 71.4,
            "function_reasoning": 87.8,
            "future_prediction": 74.7,
            "identity_reasoning": 94.7,
            "image_emotion": 72.2,
            "image_quality": 45.2,
            "image_scene": 86.1,
            "image_style": 73.9,
            "image_topic": 96.7,
            "nature_relation": 76.1,
            "object_localization": 55.2,
            "ocr": 88.9,
            "physical_property_reasoning": 55.7,
            "physical_relation": 50.7,
            "social_relation": 86.8,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 49.5,
            "Method": [
                "VITA",
                "https://huggingface.co/VITA-MLLM/VITA"
            ],
            "Parameters": "47B",
            "Language Model": "Mixtral-8x7B",
            "Vision Model": "InternViT-300M",
            "Org": "NJU",
            "Time": "2025/01/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "vita",
            "key": 443
        },
        {
            "Overall": 81.3,
            "AR": 84.5,
            "CP": 81.1,
            "FP-C": 72.3,
            "FP-S": 89.8,
            "LR": 68.5,
            "RR": 82.9,
            "action_recognition": 80.3,
            "attribute_comparison": 81.3,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 87.8,
            "function_reasoning": 95.6,
            "future_prediction": 76.0,
            "identity_reasoning": 96.1,
            "image_emotion": 80.0,
            "image_quality": 60.5,
            "image_scene": 88.2,
            "image_style": 81.5,
            "image_topic": 98.9,
            "nature_relation": 89.1,
            "object_localization": 82.9,
            "ocr": 95.6,
            "physical_property_reasoning": 60.8,
            "physical_relation": 68.0,
            "social_relation": 89.0,
            "spatial_relationship": 50.7,
            "structuralized_imagetext_understanding": 63.3,
            "Method": [
                "MiniCPM-o-2.6",
                "https://huggingface.co/openbmb/MiniCPM-o-2_6"
            ],
            "Parameters": "8.67B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "OpenBMB",
            "Time": "2025/01/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MiniCPM-o-2_6",
            "key": 444
        },
        {
            "Overall": 87.7,
            "AR": 94.3,
            "CP": 84.6,
            "FP-C": 82.4,
            "FP-S": 94.4,
            "LR": 81.5,
            "RR": 86.8,
            "action_recognition": 87.2,
            "attribute_comparison": 82.7,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 96.6,
            "function_reasoning": 96.7,
            "future_prediction": 85.3,
            "identity_reasoning": 98.7,
            "image_emotion": 78.9,
            "image_quality": 68.5,
            "image_scene": 91.0,
            "image_style": 89.1,
            "image_topic": 97.8,
            "nature_relation": 91.3,
            "object_localization": 87.6,
            "ocr": 96.7,
            "physical_property_reasoning": 87.3,
            "physical_relation": 73.3,
            "social_relation": 93.4,
            "spatial_relationship": 74.7,
            "structuralized_imagetext_understanding": 78.9,
            "Method": [
                "BailingMM-Pro-0120",
                "https://zxb.alipay.com/llm/landing"
            ],
            "Parameters": "81B",
            "Language Model": "Bailing-80B",
            "Vision Model": "SigLIP-400M",
            "Org": "Ant Group",
            "Time": "2025/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "BailingMM-Pro-0120",
            "key": 445
        },
        {
            "Overall": 80.3,
            "AR": 78.8,
            "CP": 81.1,
            "FP-C": 85.8,
            "FP-S": 87.5,
            "LR": 75.5,
            "RR": 65.9,
            "action_recognition": 86.3,
            "attribute_comparison": 86.7,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 89.8,
            "function_reasoning": 84.4,
            "future_prediction": 72.0,
            "identity_reasoning": 100.0,
            "image_emotion": 77.8,
            "image_quality": 69.4,
            "image_scene": 84.0,
            "image_style": 82.6,
            "image_topic": 94.4,
            "nature_relation": 62.0,
            "object_localization": 80.0,
            "ocr": 91.1,
            "physical_property_reasoning": 51.9,
            "physical_relation": 60.0,
            "social_relation": 74.7,
            "spatial_relationship": 84.0,
            "structuralized_imagetext_understanding": 78.0,
            "Method": [
                "Doubao-1.5-Pro",
                "https://team.doubao.com/zh/special/doubao_1_5_pro"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "ByteDance",
            "Time": "2025/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "DoubaoVL",
            "key": 446
        },
        {
            "Overall": 87.8,
            "AR": 89.4,
            "CP": 83.5,
            "FP-C": 89.5,
            "FP-S": 93.7,
            "LR": 86.4,
            "RR": 84.5,
            "action_recognition": 88.9,
            "attribute_comparison": 92.0,
            "attribute_recognition": 98.9,
            "celebrity_recognition": 89.1,
            "function_reasoning": 93.3,
            "future_prediction": 82.7,
            "identity_reasoning": 96.1,
            "image_emotion": 77.8,
            "image_quality": 65.3,
            "image_scene": 93.1,
            "image_style": 84.8,
            "image_topic": 97.8,
            "nature_relation": 94.6,
            "object_localization": 92.4,
            "ocr": 97.8,
            "physical_property_reasoning": 78.5,
            "physical_relation": 68.0,
            "social_relation": 87.9,
            "spatial_relationship": 88.0,
            "structuralized_imagetext_understanding": 89.0,
            "Method": [
                "GLM-4v-Plus-20250111",
                "https://open.bigmodel.cn/dev/api/normal-model/glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2025/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GLM4V_PLUS_20250111",
            "key": 447
        },
        {
            "Overall": 59.3,
            "AR": 63.3,
            "CP": 66.5,
            "FP-C": 63.3,
            "FP-S": 61.0,
            "LR": 31.0,
            "RR": 53.5,
            "action_recognition": 77.8,
            "attribute_comparison": 62.7,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 38.8,
            "function_reasoning": 53.3,
            "future_prediction": 41.3,
            "identity_reasoning": 86.8,
            "image_emotion": 60.0,
            "image_quality": 33.1,
            "image_scene": 83.3,
            "image_style": 64.1,
            "image_topic": 94.4,
            "nature_relation": 38.0,
            "object_localization": 62.9,
            "ocr": 76.7,
            "physical_property_reasoning": 51.9,
            "physical_relation": 61.3,
            "social_relation": 62.6,
            "spatial_relationship": 41.3,
            "structuralized_imagetext_understanding": 23.9,
            "Method": [
                "Emu3_chat",
                "https://huggingface.co/BAAI/Emu3-Chat"
            ],
            "Parameters": "8.49B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Beijing Academy of Artificial Intelligence",
            "Time": "2025/01/26",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "dir_name": "emu3_chat",
            "key": 448
        },
        {
            "Overall": 64.4,
            "AR": 78.4,
            "CP": 67.6,
            "FP-C": 53.6,
            "FP-S": 70.1,
            "LR": 46.2,
            "RR": 59.3,
            "action_recognition": 84.6,
            "attribute_comparison": 28.0,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 72.1,
            "function_reasoning": 88.9,
            "future_prediction": 62.7,
            "identity_reasoning": 92.1,
            "image_emotion": 73.3,
            "image_quality": 29.0,
            "image_scene": 77.1,
            "image_style": 71.7,
            "image_topic": 95.6,
            "nature_relation": 58.7,
            "object_localization": 37.1,
            "ocr": 88.9,
            "physical_property_reasoning": 53.2,
            "physical_relation": 40.0,
            "social_relation": 75.8,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 34.9,
            "Method": [
                "SmolVLM-Instruct",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM",
            "key": 392
        },
        {
            "Overall": 62.6,
            "AR": 78.0,
            "CP": 64.6,
            "FP-C": 53.9,
            "FP-S": 68.0,
            "LR": 41.3,
            "RR": 59.3,
            "action_recognition": 86.3,
            "attribute_comparison": 26.7,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 70.1,
            "function_reasoning": 85.6,
            "future_prediction": 61.3,
            "identity_reasoning": 93.4,
            "image_emotion": 72.2,
            "image_quality": 24.2,
            "image_scene": 75.0,
            "image_style": 66.3,
            "image_topic": 94.4,
            "nature_relation": 57.6,
            "object_localization": 31.4,
            "ocr": 91.1,
            "physical_property_reasoning": 54.4,
            "physical_relation": 37.3,
            "social_relation": 79.1,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 27.5,
            "Method": [
                "SmolVLM-Instruct-DPO",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct-DPO"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-DPO",
            "key": 393
        },
        {
            "Overall": 51.0,
            "AR": 69.4,
            "CP": 59.3,
            "FP-C": 39.7,
            "FP-S": 53.6,
            "LR": 27.2,
            "RR": 40.3,
            "action_recognition": 73.5,
            "attribute_comparison": 12.0,
            "attribute_recognition": 70.8,
            "celebrity_recognition": 58.5,
            "function_reasoning": 84.4,
            "future_prediction": 50.7,
            "identity_reasoning": 92.1,
            "image_emotion": 70.0,
            "image_quality": 4.0,
            "image_scene": 73.6,
            "image_style": 68.5,
            "image_topic": 92.2,
            "nature_relation": 48.9,
            "object_localization": 15.2,
            "ocr": 73.3,
            "physical_property_reasoning": 30.4,
            "physical_relation": 6.7,
            "social_relation": 59.3,
            "spatial_relationship": 14.7,
            "structuralized_imagetext_understanding": 11.0,
            "Method": [
                "SmolVLM-Synthetic",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Synthetic"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-Synthetic",
            "key": 394
        },
        {
            "Overall": 39.4,
            "AR": 50.6,
            "CP": 49.4,
            "FP-C": 30.7,
            "FP-S": 41.1,
            "LR": 11.4,
            "RR": 34.1,
            "action_recognition": 61.5,
            "attribute_comparison": 6.7,
            "attribute_recognition": 64.0,
            "celebrity_recognition": 26.5,
            "function_reasoning": 47.8,
            "future_prediction": 18.7,
            "identity_reasoning": 78.9,
            "image_emotion": 54.4,
            "image_quality": 4.0,
            "image_scene": 69.4,
            "image_style": 33.7,
            "image_topic": 91.1,
            "nature_relation": 32.6,
            "object_localization": 19.0,
            "ocr": 67.8,
            "physical_property_reasoning": 26.6,
            "physical_relation": 17.3,
            "social_relation": 49.5,
            "spatial_relationship": 6.7,
            "structuralized_imagetext_understanding": 6.4,
            "Method": [
                "SmolVLM-256M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct"
            ],
            "Parameters": "0.26B",
            "Language Model": "SmolLM2-135M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-256M",
            "key": 449
        },
        {
            "Overall": 50.0,
            "AR": 65.7,
            "CP": 60.4,
            "FP-C": 39.3,
            "FP-S": 49.4,
            "LR": 25.5,
            "RR": 43.0,
            "action_recognition": 71.8,
            "attribute_comparison": 16.0,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 34.0,
            "function_reasoning": 65.6,
            "future_prediction": 52.0,
            "identity_reasoning": 84.2,
            "image_emotion": 58.9,
            "image_quality": 8.1,
            "image_scene": 78.5,
            "image_style": 67.4,
            "image_topic": 97.8,
            "nature_relation": 51.1,
            "object_localization": 27.6,
            "ocr": 70.0,
            "physical_property_reasoning": 48.1,
            "physical_relation": 26.7,
            "social_relation": 48.4,
            "spatial_relationship": 12.0,
            "structuralized_imagetext_understanding": 7.3,
            "Method": [
                "SmolVLM-500M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-500M-Instruct"
            ],
            "Parameters": "0.51B",
            "Language Model": "SmolLM2-360M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-500M",
            "key": 450
        },
        {
            "Overall": 60.0,
            "AR": 69.8,
            "CP": 65.0,
            "FP-C": 53.6,
            "FP-S": 63.3,
            "LR": 33.7,
            "RR": 60.1,
            "action_recognition": 76.1,
            "attribute_comparison": 36.0,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 53.1,
            "function_reasoning": 67.8,
            "future_prediction": 50.7,
            "identity_reasoning": 96.1,
            "image_emotion": 58.9,
            "image_quality": 24.2,
            "image_scene": 81.2,
            "image_style": 75.0,
            "image_topic": 91.1,
            "nature_relation": 58.7,
            "object_localization": 39.0,
            "ocr": 83.3,
            "physical_property_reasoning": 46.8,
            "physical_relation": 50.7,
            "social_relation": 69.2,
            "spatial_relationship": 36.0,
            "structuralized_imagetext_understanding": 22.0,
            "Method": [
                "Janus-Pro-7B",
                "https://huggingface.co/deepseek-ai/Janus-Pro-7B"
            ],
            "Parameters": "7.42B",
            "Language Model": "DeepSeek-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "deepseek",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Janus-Pro-7B",
            "key": 454
        },
        {
            "Overall": 85.5,
            "AR": 91.8,
            "CP": 81.5,
            "FP-C": 84.6,
            "FP-S": 91.4,
            "LR": 74.5,
            "RR": 86.8,
            "action_recognition": 91.5,
            "attribute_comparison": 85.3,
            "attribute_recognition": 97.8,
            "celebrity_recognition": 89.1,
            "function_reasoning": 95.6,
            "future_prediction": 82.7,
            "identity_reasoning": 98.7,
            "image_emotion": 80.0,
            "image_quality": 58.1,
            "image_scene": 90.3,
            "image_style": 84.8,
            "image_topic": 97.8,
            "nature_relation": 95.7,
            "object_localization": 84.8,
            "ocr": 96.7,
            "physical_property_reasoning": 81.0,
            "physical_relation": 72.0,
            "social_relation": 90.1,
            "spatial_relationship": 73.3,
            "structuralized_imagetext_understanding": 68.8,
            "Method": [
                "Ola-7b",
                "https://huggingface.co/THUdyh/Ola-7b"
            ],
            "Parameters": "8.88B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "Oryx-ViT",
            "Org": "THU",
            "Time": "2025/02/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "ola",
            "key": 455
        },
        {
            "Overall": 70.1,
            "AR": 79.6,
            "CP": 74.3,
            "FP-C": 61.8,
            "FP-S": 75.9,
            "LR": 46.2,
            "RR": 68.2,
            "action_recognition": 87.2,
            "attribute_comparison": 53.3,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 63.3,
            "function_reasoning": 87.8,
            "future_prediction": 65.3,
            "identity_reasoning": 93.4,
            "image_emotion": 70.0,
            "image_quality": 49.2,
            "image_scene": 86.1,
            "image_style": 70.7,
            "image_topic": 97.8,
            "nature_relation": 68.5,
            "object_localization": 63.8,
            "ocr": 94.4,
            "physical_property_reasoning": 57.0,
            "physical_relation": 58.7,
            "social_relation": 75.8,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 33.0,
            "Method": [
                "Ovis2-1B",
                "https://huggingface.co/AIDC-AI/Ovis2-1B"
            ],
            "Parameters": "1.27B",
            "Language Model": "Qwen2.5-0.5B",
            "Vision Model": "AIMv2 Large",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-1B",
            "key": 456
        },
        {
            "Overall": 77.1,
            "AR": 82.4,
            "CP": 79.1,
            "FP-C": 73.4,
            "FP-S": 80.3,
            "LR": 64.7,
            "RR": 75.2,
            "action_recognition": 86.3,
            "attribute_comparison": 81.3,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 68.7,
            "function_reasoning": 86.7,
            "future_prediction": 76.0,
            "identity_reasoning": 98.7,
            "image_emotion": 78.9,
            "image_quality": 55.6,
            "image_scene": 88.9,
            "image_style": 77.2,
            "image_topic": 97.8,
            "nature_relation": 79.3,
            "object_localization": 72.4,
            "ocr": 95.6,
            "physical_property_reasoning": 62.0,
            "physical_relation": 64.0,
            "social_relation": 80.2,
            "spatial_relationship": 45.3,
            "structuralized_imagetext_understanding": 56.9,
            "Method": [
                "Ovis2-2B",
                "https://huggingface.co/AIDC-AI/Ovis2-2B"
            ],
            "Parameters": "2.46B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "AIMv2 Large",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-2B",
            "key": 457
        },
        {
            "Overall": 81.8,
            "AR": 86.5,
            "CP": 81.3,
            "FP-C": 80.5,
            "FP-S": 87.5,
            "LR": 71.7,
            "RR": 77.5,
            "action_recognition": 91.5,
            "attribute_comparison": 89.3,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 80.3,
            "function_reasoning": 93.3,
            "future_prediction": 78.7,
            "identity_reasoning": 97.4,
            "image_emotion": 81.1,
            "image_quality": 60.5,
            "image_scene": 88.2,
            "image_style": 82.6,
            "image_topic": 97.8,
            "nature_relation": 79.3,
            "object_localization": 84.8,
            "ocr": 96.7,
            "physical_property_reasoning": 68.4,
            "physical_relation": 66.7,
            "social_relation": 84.6,
            "spatial_relationship": 54.7,
            "structuralized_imagetext_understanding": 67.0,
            "Method": [
                "Ovis2-4B",
                "https://huggingface.co/AIDC-AI/Ovis2-4B"
            ],
            "Parameters": "4.62B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-4B",
            "key": 458
        },
        {
            "Overall": 83.8,
            "AR": 90.2,
            "CP": 81.7,
            "FP-C": 82.4,
            "FP-S": 87.9,
            "LR": 73.4,
            "RR": 84.1,
            "action_recognition": 91.5,
            "attribute_comparison": 90.7,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 81.6,
            "function_reasoning": 94.4,
            "future_prediction": 82.7,
            "identity_reasoning": 98.7,
            "image_emotion": 84.4,
            "image_quality": 62.1,
            "image_scene": 88.2,
            "image_style": 78.3,
            "image_topic": 98.9,
            "nature_relation": 91.3,
            "object_localization": 81.9,
            "ocr": 97.8,
            "physical_property_reasoning": 77.2,
            "physical_relation": 73.3,
            "social_relation": 85.7,
            "spatial_relationship": 60.0,
            "structuralized_imagetext_understanding": 67.0,
            "Method": [
                "Ovis2-8B",
                "https://huggingface.co/AIDC-AI/Ovis2-8B"
            ],
            "Parameters": "8.94B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-8B",
            "key": 459
        },
        {
            "Overall": 85.8,
            "AR": 91.0,
            "CP": 82.2,
            "FP-C": 88.4,
            "FP-S": 90.5,
            "LR": 79.9,
            "RR": 82.2,
            "action_recognition": 88.9,
            "attribute_comparison": 97.3,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 85.0,
            "function_reasoning": 95.6,
            "future_prediction": 82.7,
            "identity_reasoning": 96.1,
            "image_emotion": 83.3,
            "image_quality": 63.7,
            "image_scene": 89.6,
            "image_style": 79.3,
            "image_topic": 97.8,
            "nature_relation": 88.0,
            "object_localization": 86.7,
            "ocr": 100.0,
            "physical_property_reasoning": 81.0,
            "physical_relation": 74.7,
            "social_relation": 82.4,
            "spatial_relationship": 78.7,
            "structuralized_imagetext_understanding": 78.0,
            "Method": [
                "Ovis2-16B",
                "https://huggingface.co/AIDC-AI/Ovis2-16B"
            ],
            "Parameters": "16.2B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-16B",
            "key": 460
        },
        {
            "Overall": 86.6,
            "AR": 91.8,
            "CP": 82.2,
            "FP-C": 89.9,
            "FP-S": 90.3,
            "LR": 78.8,
            "RR": 87.2,
            "action_recognition": 91.5,
            "attribute_comparison": 93.3,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 84.4,
            "function_reasoning": 95.6,
            "future_prediction": 81.3,
            "identity_reasoning": 98.7,
            "image_emotion": 80.0,
            "image_quality": 62.1,
            "image_scene": 91.0,
            "image_style": 81.5,
            "image_topic": 98.9,
            "nature_relation": 96.7,
            "object_localization": 87.6,
            "ocr": 98.9,
            "physical_property_reasoning": 81.0,
            "physical_relation": 73.3,
            "social_relation": 89.0,
            "spatial_relationship": 84.0,
            "structuralized_imagetext_understanding": 77.1,
            "Method": [
                "Ovis2-34B",
                "https://huggingface.co/AIDC-AI/Ovis2-34B"
            ],
            "Parameters": "34.9B",
            "Language Model": "Qwen2.5-32B",
            "Vision Model": "AIMv2-1B",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-34B",
            "key": 461
        },
        {
            "Overall": 77.0,
            "AR": 83.3,
            "CP": 77.2,
            "FP-C": 69.3,
            "FP-S": 85.4,
            "LR": 67.4,
            "RR": 71.7,
            "action_recognition": 83.8,
            "attribute_comparison": 74.7,
            "attribute_recognition": 83.1,
            "celebrity_recognition": 91.8,
            "function_reasoning": 95.6,
            "future_prediction": 68.0,
            "identity_reasoning": 97.4,
            "image_emotion": 73.3,
            "image_quality": 48.4,
            "image_scene": 91.0,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 76.1,
            "object_localization": 69.5,
            "ocr": 95.6,
            "physical_property_reasoning": 55.7,
            "physical_relation": 46.7,
            "social_relation": 87.9,
            "spatial_relationship": 41.3,
            "structuralized_imagetext_understanding": 67.0,
            "Method": [
                "Qwen2.5-VL-3B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct"
            ],
            "Parameters": "3.75B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-3B-Instruct",
            "key": 462
        },
        {
            "Overall": 82.4,
            "AR": 84.9,
            "CP": 81.3,
            "FP-C": 80.1,
            "FP-S": 89.8,
            "LR": 71.7,
            "RR": 80.2,
            "action_recognition": 86.3,
            "attribute_comparison": 84.0,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 91.2,
            "function_reasoning": 95.6,
            "future_prediction": 77.3,
            "identity_reasoning": 96.1,
            "image_emotion": 78.9,
            "image_quality": 60.5,
            "image_scene": 90.3,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 89.1,
            "object_localization": 81.9,
            "ocr": 95.6,
            "physical_property_reasoning": 62.0,
            "physical_relation": 56.0,
            "social_relation": 91.2,
            "spatial_relationship": 66.7,
            "structuralized_imagetext_understanding": 67.9,
            "Method": [
                "Qwen2.5-VL-7B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct"
            ],
            "Parameters": "8.29B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-7B-Instruct",
            "key": 463
        },
        {
            "Overall": 88.3,
            "AR": 88.2,
            "CP": 85.7,
            "FP-C": 86.5,
            "FP-S": 95.1,
            "LR": 86.4,
            "RR": 85.3,
            "action_recognition": 85.5,
            "attribute_comparison": 90.7,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 96.6,
            "function_reasoning": 95.6,
            "future_prediction": 86.7,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 71.0,
            "image_scene": 93.8,
            "image_style": 83.7,
            "image_topic": 98.9,
            "nature_relation": 93.5,
            "object_localization": 89.5,
            "ocr": 100.0,
            "physical_property_reasoning": 70.9,
            "physical_relation": 66.7,
            "social_relation": 92.3,
            "spatial_relationship": 84.0,
            "structuralized_imagetext_understanding": 86.2,
            "Method": [
                "Qwen2.5-VL-72B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct"
            ],
            "Parameters": "73.4B",
            "Language Model": "Qwen2.5-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-72B-Instruct",
            "key": 464
        },
        {
            "Overall": 82.4,
            "AR": 84.5,
            "CP": 78.9,
            "FP-C": 83.5,
            "FP-S": 89.8,
            "LR": 72.8,
            "RR": 81.0,
            "action_recognition": 91.5,
            "attribute_comparison": 80.0,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 95.2,
            "function_reasoning": 93.3,
            "future_prediction": 77.3,
            "identity_reasoning": 96.1,
            "image_emotion": 81.1,
            "image_quality": 54.8,
            "image_scene": 84.7,
            "image_style": 83.7,
            "image_topic": 95.6,
            "nature_relation": 93.5,
            "object_localization": 81.9,
            "ocr": 91.1,
            "physical_property_reasoning": 63.3,
            "physical_relation": 58.7,
            "social_relation": 86.8,
            "spatial_relationship": 74.7,
            "structuralized_imagetext_understanding": 69.7,
            "Method": [
                "Gemini-2.0-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2025/02/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GeminiPro2-0",
            "key": 465
        },
        {
            "Overall": 79.8,
            "AR": 84.9,
            "CP": 77.4,
            "FP-C": 82.4,
            "FP-S": 81.7,
            "LR": 77.7,
            "RR": 75.6,
            "action_recognition": 80.3,
            "attribute_comparison": 90.7,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 66.0,
            "function_reasoning": 92.2,
            "future_prediction": 68.0,
            "identity_reasoning": 96.1,
            "image_emotion": 71.1,
            "image_quality": 53.2,
            "image_scene": 88.9,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 92.4,
            "object_localization": 81.9,
            "ocr": 97.8,
            "physical_property_reasoning": 65.8,
            "physical_relation": 53.3,
            "social_relation": 76.9,
            "spatial_relationship": 77.3,
            "structuralized_imagetext_understanding": 84.4,
            "Method": [
                "Claude3.7-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2025/02/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Claude3-7V_Sonnet",
            "key": 466
        },
        {
            "Overall": 76.8,
            "AR": 77.6,
            "CP": 78.7,
            "FP-C": 69.3,
            "FP-S": 83.8,
            "LR": 67.4,
            "RR": 75.2,
            "action_recognition": 76.9,
            "attribute_comparison": 73.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 76.9,
            "function_reasoning": 90.0,
            "future_prediction": 72.0,
            "identity_reasoning": 94.7,
            "image_emotion": 72.2,
            "image_quality": 57.3,
            "image_scene": 89.6,
            "image_style": 79.3,
            "image_topic": 96.7,
            "nature_relation": 85.9,
            "object_localization": 80.0,
            "ocr": 94.4,
            "physical_property_reasoning": 46.8,
            "physical_relation": 60.0,
            "social_relation": 76.9,
            "spatial_relationship": 53.3,
            "structuralized_imagetext_understanding": 64.2,
            "Method": [
                "moonshot-v1-8k",
                "https://platform.moonshot.cn/docs/api/chat"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Moonshot AI",
            "Time": "2025/03/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "moonshot-v1-8k",
            "key": 467
        },
        {
            "Overall": 83.3,
            "AR": 89.0,
            "CP": 79.8,
            "FP-C": 82.8,
            "FP-S": 91.2,
            "LR": 73.4,
            "RR": 79.5,
            "action_recognition": 88.0,
            "attribute_comparison": 81.3,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 89.8,
            "function_reasoning": 96.7,
            "future_prediction": 82.7,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 55.6,
            "image_scene": 89.6,
            "image_style": 80.4,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 83.8,
            "ocr": 100.0,
            "physical_property_reasoning": 72.2,
            "physical_relation": 56.0,
            "social_relation": 84.6,
            "spatial_relationship": 76.0,
            "structuralized_imagetext_understanding": 67.0,
            "Method": [
                "grok-2-vision-1212",
                "https://docs.x.ai/docs/overview"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "xAI",
            "Time": "2025/03/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "grok-2-vision-1212",
            "key": 468
        },
        {
            "Overall": 82.3,
            "AR": 87.3,
            "CP": 82.0,
            "FP-C": 76.8,
            "FP-S": 88.4,
            "LR": 73.4,
            "RR": 79.8,
            "action_recognition": 84.6,
            "attribute_comparison": 86.7,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 87.8,
            "function_reasoning": 96.7,
            "future_prediction": 85.3,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 62.9,
            "image_scene": 88.2,
            "image_style": 85.9,
            "image_topic": 97.8,
            "nature_relation": 85.9,
            "object_localization": 76.2,
            "ocr": 95.6,
            "physical_property_reasoning": 67.1,
            "physical_relation": 70.7,
            "social_relation": 81.3,
            "spatial_relationship": 54.7,
            "structuralized_imagetext_understanding": 65.1,
            "Method": [
                "DeepSeek-VL2",
                "https://huggingface.co/deepseek-ai/deepseek-vl2"
            ],
            "Parameters": "27.5B",
            "Language Model": "DeepSeekMoE-27B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2",
            "key": 469
        },
        {
            "Overall": 69.1,
            "AR": 79.6,
            "CP": 73.7,
            "FP-C": 64.0,
            "FP-S": 71.5,
            "LR": 51.1,
            "RR": 63.6,
            "action_recognition": 89.7,
            "attribute_comparison": 49.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 69.4,
            "function_reasoning": 86.7,
            "future_prediction": 65.3,
            "identity_reasoning": 93.4,
            "image_emotion": 72.2,
            "image_quality": 44.4,
            "image_scene": 84.7,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 55.4,
            "object_localization": 44.8,
            "ocr": 88.9,
            "physical_property_reasoning": 58.2,
            "physical_relation": 58.7,
            "social_relation": 75.8,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 41.3,
            "Method": [
                "SmolVLM2",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct"
            ],
            "Parameters": "2.25B",
            "Language Model": "SmolLM2-1.7M",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2",
            "key": 470
        },
        {
            "Overall": 11.0,
            "AR": 21.2,
            "CP": 14.6,
            "FP-C": 3.0,
            "FP-S": 13.9,
            "LR": 4.9,
            "RR": 1.6,
            "action_recognition": 4.3,
            "attribute_comparison": 4.0,
            "attribute_recognition": 31.5,
            "celebrity_recognition": 4.1,
            "function_reasoning": 13.3,
            "future_prediction": 10.7,
            "identity_reasoning": 34.2,
            "image_emotion": 1.1,
            "image_quality": 4.0,
            "image_scene": 24.3,
            "image_style": 1.1,
            "image_topic": 41.1,
            "nature_relation": 2.2,
            "object_localization": 4.8,
            "ocr": 23.3,
            "physical_property_reasoning": 17.7,
            "physical_relation": 0.0,
            "social_relation": 2.2,
            "spatial_relationship": 0.0,
            "structuralized_imagetext_understanding": 0.9,
            "Method": [
                "SmolVLM2-256M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-256M-Video-Instruct"
            ],
            "Parameters": "0.26B",
            "Language Model": "SmolLM2-135M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2-256M",
            "key": 471
        },
        {
            "Overall": 49.8,
            "AR": 68.6,
            "CP": 58.3,
            "FP-C": 40.4,
            "FP-S": 49.0,
            "LR": 23.9,
            "RR": 43.8,
            "action_recognition": 74.4,
            "attribute_comparison": 17.3,
            "attribute_recognition": 76.4,
            "celebrity_recognition": 34.7,
            "function_reasoning": 70.0,
            "future_prediction": 53.3,
            "identity_reasoning": 90.8,
            "image_emotion": 58.9,
            "image_quality": 2.4,
            "image_scene": 78.5,
            "image_style": 66.3,
            "image_topic": 94.4,
            "nature_relation": 43.5,
            "object_localization": 21.9,
            "ocr": 76.7,
            "physical_property_reasoning": 45.6,
            "physical_relation": 22.7,
            "social_relation": 61.5,
            "spatial_relationship": 10.7,
            "structuralized_imagetext_understanding": 3.7,
            "Method": [
                "SmolVLM2-500M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
            ],
            "Parameters": "0.51B",
            "Language Model": "SmolLM2-360M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2-500M",
            "key": 472
        },
        {
            "Overall": 79.5,
            "AR": 84.5,
            "CP": 80.7,
            "FP-C": 71.5,
            "FP-S": 85.2,
            "LR": 69.6,
            "RR": 78.3,
            "action_recognition": 78.6,
            "attribute_comparison": 81.3,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 82.3,
            "function_reasoning": 94.4,
            "future_prediction": 73.3,
            "identity_reasoning": 92.1,
            "image_emotion": 78.9,
            "image_quality": 57.3,
            "image_scene": 89.6,
            "image_style": 82.6,
            "image_topic": 98.9,
            "nature_relation": 87.0,
            "object_localization": 77.1,
            "ocr": 91.1,
            "physical_property_reasoning": 65.8,
            "physical_relation": 57.3,
            "social_relation": 86.8,
            "spatial_relationship": 50.7,
            "structuralized_imagetext_understanding": 67.0,
            "Method": [
                "Phi-4-MultiModal",
                "https://huggingface.co/microsoft/Phi-4-multimodal-instruct"
            ],
            "Parameters": "5.57B",
            "Language Model": "Phi-4-Mini",
            "Vision Model": "SigLIP-400M",
            "Org": "Microsoft",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Phi-4-Vision",
            "key": 473
        },
        {
            "Overall": 81.9,
            "AR": 82.9,
            "CP": 80.7,
            "FP-C": 79.8,
            "FP-S": 88.4,
            "LR": 73.4,
            "RR": 81.0,
            "action_recognition": 90.6,
            "attribute_comparison": 84.0,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 82.3,
            "function_reasoning": 90.0,
            "future_prediction": 81.3,
            "identity_reasoning": 97.4,
            "image_emotion": 83.3,
            "image_quality": 58.9,
            "image_scene": 90.3,
            "image_style": 76.1,
            "image_topic": 97.8,
            "nature_relation": 84.8,
            "object_localization": 83.8,
            "ocr": 96.7,
            "physical_property_reasoning": 60.8,
            "physical_relation": 64.0,
            "social_relation": 91.2,
            "spatial_relationship": 58.7,
            "structuralized_imagetext_understanding": 67.9,
            "Method": [
                "MUG-U-7B",
                "https://github.com/Shopee-MUG/MUG-U"
            ],
            "Parameters": "7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Shopee",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MUG-U-7B",
            "key": 474
        },
        {
            "Overall": 66.1,
            "AR": 78.4,
            "CP": 71.1,
            "FP-C": 55.8,
            "FP-S": 66.6,
            "LR": 50.5,
            "RR": 64.7,
            "action_recognition": 82.9,
            "attribute_comparison": 42.7,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 78.9,
            "function_reasoning": 87.8,
            "future_prediction": 72.0,
            "identity_reasoning": 94.7,
            "image_emotion": 75.6,
            "image_quality": 35.5,
            "image_scene": 79.9,
            "image_style": 76.1,
            "image_topic": 96.7,
            "nature_relation": 70.7,
            "object_localization": 17.1,
            "ocr": 86.7,
            "physical_property_reasoning": 51.9,
            "physical_relation": 29.3,
            "social_relation": 87.9,
            "spatial_relationship": 26.7,
            "structuralized_imagetext_understanding": 35.8,
            "Method": [
                "Gemma3-4B",
                "https://huggingface.co/google/gemma-3-4b-it"
            ],
            "Parameters": "4.3B",
            "Language Model": "Gemma3-4B",
            "Vision Model": "SigLIP-400M",
            "Org": "Google",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Gemma3-4B",
            "key": 475
        },
        {
            "Overall": 74.9,
            "AR": 84.9,
            "CP": 75.4,
            "FP-C": 67.4,
            "FP-S": 79.8,
            "LR": 67.9,
            "RR": 68.6,
            "action_recognition": 82.9,
            "attribute_comparison": 65.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 85.0,
            "function_reasoning": 95.6,
            "future_prediction": 78.7,
            "identity_reasoning": 93.4,
            "image_emotion": 72.2,
            "image_quality": 48.4,
            "image_scene": 85.4,
            "image_style": 77.2,
            "image_topic": 97.8,
            "nature_relation": 83.7,
            "object_localization": 53.3,
            "ocr": 93.3,
            "physical_property_reasoning": 64.6,
            "physical_relation": 40.0,
            "social_relation": 76.9,
            "spatial_relationship": 45.3,
            "structuralized_imagetext_understanding": 60.6,
            "Method": [
                "Gemma3-12B",
                "https://huggingface.co/google/gemma-3-12b-it"
            ],
            "Parameters": "12.2B",
            "Language Model": "Gemma3-12B",
            "Vision Model": "SigLIP-400M",
            "Org": "Google",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Gemma3-12B",
            "key": 476
        },
        {
            "Overall": 79.6,
            "AR": 86.9,
            "CP": 79.8,
            "FP-C": 73.4,
            "FP-S": 85.6,
            "LR": 67.9,
            "RR": 77.1,
            "action_recognition": 86.3,
            "attribute_comparison": 69.3,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 90.5,
            "function_reasoning": 92.2,
            "future_prediction": 76.0,
            "identity_reasoning": 98.7,
            "image_emotion": 80.0,
            "image_quality": 54.8,
            "image_scene": 87.5,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 90.2,
            "object_localization": 69.5,
            "ocr": 95.6,
            "physical_property_reasoning": 69.6,
            "physical_relation": 49.3,
            "social_relation": 86.8,
            "spatial_relationship": 57.3,
            "structuralized_imagetext_understanding": 62.4,
            "Method": [
                "Gemma3-27B",
                "https://huggingface.co/google/gemma-3-27b-it"
            ],
            "Parameters": "27.4B",
            "Language Model": "Gemma3-27B",
            "Vision Model": "SigLIP-400M",
            "Org": "Google",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Gemma3-27B",
            "key": 477
        },
        {
            "Overall": 65.9,
            "AR": 79.2,
            "CP": 72.0,
            "FP-C": 57.7,
            "FP-S": 67.7,
            "LR": 36.4,
            "RR": 67.1,
            "action_recognition": 83.8,
            "attribute_comparison": 38.7,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 72.1,
            "function_reasoning": 90.0,
            "future_prediction": 64.0,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 21.8,
            "image_scene": 87.5,
            "image_style": 79.3,
            "image_topic": 98.9,
            "nature_relation": 76.1,
            "object_localization": 39.0,
            "ocr": 74.4,
            "physical_property_reasoning": 49.4,
            "physical_relation": 37.3,
            "social_relation": 82.4,
            "spatial_relationship": 36.0,
            "structuralized_imagetext_understanding": 17.4,
            "Method": [
                "AKI-4B",
                "https://huggingface.co/Sony/AKI-4B-phi-3.5-mini"
            ],
            "Parameters": "4.33B",
            "Language Model": "Phi-3.5",
            "Vision Model": "SigLIP-400M",
            "Org": "Sony",
            "Time": "2025/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "AKI",
            "key": 478
        },
        {
            "Overall": 83.5,
            "AR": 89.8,
            "CP": 82.6,
            "FP-C": 89.9,
            "FP-S": 81.2,
            "LR": 76.1,
            "RR": 82.2,
            "action_recognition": 94.0,
            "attribute_comparison": 84.0,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 69.4,
            "function_reasoning": 94.4,
            "future_prediction": 77.3,
            "identity_reasoning": 97.4,
            "image_emotion": 83.3,
            "image_quality": 61.3,
            "image_scene": 88.2,
            "image_style": 87.0,
            "image_topic": 97.8,
            "nature_relation": 94.6,
            "object_localization": 80.0,
            "ocr": 88.9,
            "physical_property_reasoning": 77.2,
            "physical_relation": 62.7,
            "social_relation": 85.7,
            "spatial_relationship": 89.3,
            "structuralized_imagetext_understanding": 75.2,
            "Method": [
                "GPT-4.5",
                "https://openai.com/index/introducing-gpt-4-5/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/03/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GPT4.5",
            "key": 479
        },
        {
            "Overall": 81.2,
            "AR": 88.2,
            "CP": 82.0,
            "FP-C": 76.0,
            "FP-S": 86.3,
            "LR": 67.4,
            "RR": 79.5,
            "action_recognition": 88.9,
            "attribute_comparison": 81.3,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 78.2,
            "function_reasoning": 93.3,
            "future_prediction": 76.0,
            "identity_reasoning": 96.1,
            "image_emotion": 84.4,
            "image_quality": 59.7,
            "image_scene": 88.9,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 77.2,
            "object_localization": 81.0,
            "ocr": 95.6,
            "physical_property_reasoning": 74.7,
            "physical_relation": 70.7,
            "social_relation": 89.0,
            "spatial_relationship": 50.7,
            "structuralized_imagetext_understanding": 61.5,
            "Method": [
                "Ristretto-3B",
                "https://huggingface.co/LiAutoAD/Ristretto-3B"
            ],
            "Parameters": "3.84B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "LiAutoAD",
            "Time": "2025/04/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ristretto-3B",
            "key": 480
        },
        {
            "Overall": 86.8,
            "AR": 91.4,
            "CP": 85.4,
            "FP-C": 91.0,
            "FP-S": 84.9,
            "LR": 87.5,
            "RR": 83.3,
            "action_recognition": 95.7,
            "attribute_comparison": 86.7,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 68.0,
            "function_reasoning": 94.4,
            "future_prediction": 88.0,
            "identity_reasoning": 98.7,
            "image_emotion": 81.1,
            "image_quality": 68.5,
            "image_scene": 90.3,
            "image_style": 92.4,
            "image_topic": 97.8,
            "nature_relation": 92.4,
            "object_localization": 85.7,
            "ocr": 100.0,
            "physical_property_reasoning": 81.0,
            "physical_relation": 62.7,
            "social_relation": 91.2,
            "spatial_relationship": 88.0,
            "structuralized_imagetext_understanding": 87.2,
            "Method": [
                "ChatGPT-4o-latest",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "ChatGPT4o",
            "key": 481
        },
        {
            "Overall": 88.5,
            "AR": 87.8,
            "CP": 83.7,
            "FP-C": 94.0,
            "FP-S": 94.2,
            "LR": 89.1,
            "RR": 83.7,
            "action_recognition": 92.3,
            "attribute_comparison": 96.0,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 94.6,
            "function_reasoning": 93.3,
            "future_prediction": 80.0,
            "identity_reasoning": 98.7,
            "image_emotion": 78.9,
            "image_quality": 71.8,
            "image_scene": 84.7,
            "image_style": 92.4,
            "image_topic": 94.4,
            "nature_relation": 89.1,
            "object_localization": 94.3,
            "ocr": 95.6,
            "physical_property_reasoning": 70.9,
            "physical_relation": 70.7,
            "social_relation": 89.0,
            "spatial_relationship": 94.7,
            "structuralized_imagetext_understanding": 95.4,
            "Method": [
                "Gemini-2.5-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2025/04/07",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "GeminiPro2-5",
            "key": 482
        },
        {
            "Overall": 80.9,
            "AR": 87.3,
            "CP": 79.4,
            "FP-C": 73.8,
            "FP-S": 89.3,
            "LR": 71.7,
            "RR": 77.5,
            "action_recognition": 86.3,
            "attribute_comparison": 84.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 89.1,
            "function_reasoning": 95.6,
            "future_prediction": 78.7,
            "identity_reasoning": 97.4,
            "image_emotion": 76.7,
            "image_quality": 59.7,
            "image_scene": 88.9,
            "image_style": 76.1,
            "image_topic": 97.8,
            "nature_relation": 81.5,
            "object_localization": 83.8,
            "ocr": 92.2,
            "physical_property_reasoning": 68.4,
            "physical_relation": 65.3,
            "social_relation": 83.5,
            "spatial_relationship": 44.0,
            "structuralized_imagetext_understanding": 67.0,
            "Method": [
                "Kimi-VL-A3B-Instruct",
                "https://huggingface.co/moonshotai/Kimi-VL-A3B-Instruct"
            ],
            "Parameters": "16.4B",
            "Language Model": "Moonlight-16B-A3B",
            "Vision Model": "MoonViT",
            "Org": "moonshot.ai",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kimi-VL-A3B-Instruct",
            "key": 483
        },
        {
            "Overall": 69.9,
            "AR": 74.3,
            "CP": 75.2,
            "FP-C": 62.5,
            "FP-S": 76.3,
            "LR": 51.1,
            "RR": 64.7,
            "action_recognition": 87.2,
            "attribute_comparison": 52.0,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 68.7,
            "function_reasoning": 80.0,
            "future_prediction": 70.7,
            "identity_reasoning": 93.4,
            "image_emotion": 76.7,
            "image_quality": 47.6,
            "image_scene": 85.4,
            "image_style": 71.7,
            "image_topic": 98.9,
            "nature_relation": 55.4,
            "object_localization": 63.8,
            "ocr": 87.8,
            "physical_property_reasoning": 49.4,
            "physical_relation": 54.7,
            "social_relation": 82.4,
            "spatial_relationship": 34.7,
            "structuralized_imagetext_understanding": 37.6,
            "Method": [
                "InternVL3-1B",
                "https://huggingface.co/OpenGVLab/InternVL3-1B"
            ],
            "Parameters": "0.94B",
            "Language Model": "Qwen2.5-0.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-1B",
            "key": 484
        },
        {
            "Overall": 79.0,
            "AR": 82.9,
            "CP": 79.4,
            "FP-C": 74.9,
            "FP-S": 83.3,
            "LR": 64.7,
            "RR": 81.4,
            "action_recognition": 90.6,
            "attribute_comparison": 82.7,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 77.6,
            "function_reasoning": 93.3,
            "future_prediction": 72.0,
            "identity_reasoning": 97.4,
            "image_emotion": 74.4,
            "image_quality": 56.5,
            "image_scene": 88.9,
            "image_style": 82.6,
            "image_topic": 97.8,
            "nature_relation": 85.9,
            "object_localization": 73.3,
            "ocr": 95.6,
            "physical_property_reasoning": 57.0,
            "physical_relation": 62.7,
            "social_relation": 92.3,
            "spatial_relationship": 42.7,
            "structuralized_imagetext_understanding": 59.6,
            "Method": [
                "InternVL3-2B",
                "https://huggingface.co/OpenGVLab/InternVL3-2B"
            ],
            "Parameters": "2.09B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-2B",
            "key": 485
        },
        {
            "Overall": 82.3,
            "AR": 84.1,
            "CP": 80.9,
            "FP-C": 81.3,
            "FP-S": 88.2,
            "LR": 71.2,
            "RR": 82.9,
            "action_recognition": 93.2,
            "attribute_comparison": 82.7,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 83.7,
            "function_reasoning": 88.9,
            "future_prediction": 77.3,
            "identity_reasoning": 98.7,
            "image_emotion": 82.2,
            "image_quality": 58.9,
            "image_scene": 88.9,
            "image_style": 80.4,
            "image_topic": 97.8,
            "nature_relation": 88.0,
            "object_localization": 81.9,
            "ocr": 96.7,
            "physical_property_reasoning": 64.6,
            "physical_relation": 72.0,
            "social_relation": 86.8,
            "spatial_relationship": 61.3,
            "structuralized_imagetext_understanding": 67.0,
            "Method": [
                "InternVL3-8B",
                "https://huggingface.co/OpenGVLab/InternVL3-8B"
            ],
            "Parameters": "7.94B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-8B",
            "key": 486
        },
        {
            "Overall": 81.9,
            "AR": 80.4,
            "CP": 81.5,
            "FP-C": 81.6,
            "FP-S": 87.5,
            "LR": 73.9,
            "RR": 81.0,
            "action_recognition": 89.7,
            "attribute_comparison": 89.3,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 82.3,
            "function_reasoning": 91.1,
            "future_prediction": 78.7,
            "identity_reasoning": 97.4,
            "image_emotion": 81.1,
            "image_quality": 58.9,
            "image_scene": 91.0,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 85.9,
            "object_localization": 81.0,
            "ocr": 95.6,
            "physical_property_reasoning": 51.9,
            "physical_relation": 64.0,
            "social_relation": 90.1,
            "spatial_relationship": 61.3,
            "structuralized_imagetext_understanding": 70.6,
            "Method": [
                "InternVL3-9B",
                "https://huggingface.co/OpenGVLab/InternVL3-9B"
            ],
            "Parameters": "9.14B",
            "Language Model": "InternLM3-8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-9B",
            "key": 487
        },
        {
            "Overall": 83.9,
            "AR": 87.8,
            "CP": 81.5,
            "FP-C": 80.5,
            "FP-S": 88.9,
            "LR": 81.5,
            "RR": 82.6,
            "action_recognition": 85.5,
            "attribute_comparison": 81.3,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 84.4,
            "function_reasoning": 91.1,
            "future_prediction": 81.3,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 57.3,
            "image_scene": 91.7,
            "image_style": 84.8,
            "image_topic": 97.8,
            "nature_relation": 85.9,
            "object_localization": 85.7,
            "ocr": 97.8,
            "physical_property_reasoning": 74.7,
            "physical_relation": 70.7,
            "social_relation": 89.0,
            "spatial_relationship": 72.0,
            "structuralized_imagetext_understanding": 81.7,
            "Method": [
                "InternVL3-14B",
                "https://huggingface.co/OpenGVLab/InternVL3-14B"
            ],
            "Parameters": "15.1B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-14B",
            "key": 488
        },
        {
            "Overall": 87.0,
            "AR": 89.4,
            "CP": 82.2,
            "FP-C": 86.5,
            "FP-S": 93.7,
            "LR": 83.7,
            "RR": 86.0,
            "action_recognition": 92.3,
            "attribute_comparison": 86.7,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 91.2,
            "function_reasoning": 94.4,
            "future_prediction": 85.3,
            "identity_reasoning": 96.1,
            "image_emotion": 83.3,
            "image_quality": 60.5,
            "image_scene": 89.6,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 88.0,
            "object_localization": 91.4,
            "ocr": 97.8,
            "physical_property_reasoning": 77.2,
            "physical_relation": 74.7,
            "social_relation": 93.4,
            "spatial_relationship": 77.3,
            "structuralized_imagetext_understanding": 82.6,
            "Method": [
                "InternVL3-38B",
                "https://huggingface.co/OpenGVLab/InternVL3-38B"
            ],
            "Parameters": "38.4B",
            "Language Model": "Qwen2.5-32B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-38B",
            "key": 489
        },
        {
            "Overall": 87.5,
            "AR": 90.2,
            "CP": 81.9,
            "FP-C": 89.9,
            "FP-S": 93.5,
            "LR": 82.6,
            "RR": 87.6,
            "action_recognition": 93.2,
            "attribute_comparison": 89.3,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 90.5,
            "function_reasoning": 95.6,
            "future_prediction": 85.3,
            "identity_reasoning": 98.7,
            "image_emotion": 78.9,
            "image_quality": 61.3,
            "image_scene": 91.0,
            "image_style": 82.6,
            "image_topic": 97.8,
            "nature_relation": 94.6,
            "object_localization": 90.5,
            "ocr": 98.9,
            "physical_property_reasoning": 75.9,
            "physical_relation": 77.3,
            "social_relation": 89.0,
            "spatial_relationship": 85.3,
            "structuralized_imagetext_understanding": 80.7,
            "Method": [
                "InternVL3-78B",
                "https://huggingface.co/OpenGVLab/InternVL3-78B"
            ],
            "Parameters": "78.4B",
            "Language Model": "Qwen2.5-72B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-78B",
            "key": 490
        },
        {
            "Overall": 86.9,
            "AR": 92.2,
            "CP": 84.1,
            "FP-C": 90.6,
            "FP-S": 87.2,
            "LR": 87.5,
            "RR": 82.6,
            "action_recognition": 96.6,
            "attribute_comparison": 92.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 74.8,
            "function_reasoning": 94.4,
            "future_prediction": 86.7,
            "identity_reasoning": 98.7,
            "image_emotion": 82.2,
            "image_quality": 66.9,
            "image_scene": 88.9,
            "image_style": 88.0,
            "image_topic": 97.8,
            "nature_relation": 94.6,
            "object_localization": 88.6,
            "ocr": 100.0,
            "physical_property_reasoning": 83.5,
            "physical_relation": 62.7,
            "social_relation": 86.8,
            "spatial_relationship": 80.0,
            "structuralized_imagetext_understanding": 88.1,
            "Method": [
                "GPT-4.1-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-2025-04-14",
            "key": 491
        },
        {
            "Overall": 83.2,
            "AR": 80.8,
            "CP": 82.6,
            "FP-C": 87.3,
            "FP-S": 88.6,
            "LR": 72.3,
            "RR": 81.0,
            "action_recognition": 91.5,
            "attribute_comparison": 88.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 85.7,
            "function_reasoning": 93.3,
            "future_prediction": 81.3,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 68.5,
            "image_scene": 86.1,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 90.2,
            "object_localization": 79.0,
            "ocr": 100.0,
            "physical_property_reasoning": 50.6,
            "physical_relation": 64.0,
            "social_relation": 85.7,
            "spatial_relationship": 80.0,
            "structuralized_imagetext_understanding": 66.1,
            "Method": [
                "GPT-4.1-mini-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-mini-2025-04-14",
            "key": 492
        },
        {
            "Overall": 64.4,
            "AR": 74.3,
            "CP": 70.7,
            "FP-C": 56.2,
            "FP-S": 63.1,
            "LR": 56.5,
            "RR": 57.8,
            "action_recognition": 71.8,
            "attribute_comparison": 58.7,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 48.3,
            "function_reasoning": 82.2,
            "future_prediction": 68.0,
            "identity_reasoning": 89.5,
            "image_emotion": 67.8,
            "image_quality": 46.0,
            "image_scene": 81.9,
            "image_style": 68.5,
            "image_topic": 92.2,
            "nature_relation": 54.3,
            "object_localization": 47.6,
            "ocr": 88.9,
            "physical_property_reasoning": 50.6,
            "physical_relation": 42.7,
            "social_relation": 73.6,
            "spatial_relationship": 29.3,
            "structuralized_imagetext_understanding": 48.6,
            "Method": [
                "GPT-4.1-nano-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-nano-2025-04-14",
            "key": 493
        },
        {
            "Overall": 72.5,
            "AR": 77.1,
            "CP": 71.3,
            "FP-C": 66.3,
            "FP-S": 78.9,
            "LR": 66.8,
            "RR": 70.2,
            "action_recognition": 74.4,
            "attribute_comparison": 65.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 79.6,
            "function_reasoning": 90.0,
            "future_prediction": 68.0,
            "identity_reasoning": 96.1,
            "image_emotion": 67.8,
            "image_quality": 45.2,
            "image_scene": 81.9,
            "image_style": 68.5,
            "image_topic": 96.7,
            "nature_relation": 78.3,
            "object_localization": 57.1,
            "ocr": 93.3,
            "physical_property_reasoning": 44.3,
            "physical_relation": 54.7,
            "social_relation": 74.7,
            "spatial_relationship": 54.7,
            "structuralized_imagetext_understanding": 66.1,
            "Method": [
                "Kimi-VL-A3B-Thinking",
                "https://huggingface.co/moonshotai/Kimi-VL-A3B-Thinking"
            ],
            "Parameters": "16.4B",
            "Language Model": "Moonlight-16B-A3B",
            "Vision Model": "MoonViT",
            "Org": "moonshot.ai",
            "Time": "2025/04/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kimi-VL-A3B-Thinking",
            "key": 494
        },
        {
            "Overall": 79.4,
            "AR": 86.5,
            "CP": 79.1,
            "FP-C": 75.7,
            "FP-S": 83.1,
            "LR": 69.0,
            "RR": 78.7,
            "action_recognition": 90.6,
            "attribute_comparison": 77.3,
            "attribute_recognition": 97.8,
            "celebrity_recognition": 77.6,
            "function_reasoning": 94.4,
            "future_prediction": 80.0,
            "identity_reasoning": 96.1,
            "image_emotion": 80.0,
            "image_quality": 52.4,
            "image_scene": 87.5,
            "image_style": 82.6,
            "image_topic": 97.8,
            "nature_relation": 83.7,
            "object_localization": 70.5,
            "ocr": 92.2,
            "physical_property_reasoning": 68.4,
            "physical_relation": 64.0,
            "social_relation": 85.7,
            "spatial_relationship": 50.7,
            "structuralized_imagetext_understanding": 61.5,
            "Method": [
                "SAIL-VL-1.5-2B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL-1d5-2B"
            ],
            "Parameters": "2.47B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "AIMv2 Huge",
            "Org": "ByteDance",
            "Time": "2025/04/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL-1.5-2B",
            "key": 495
        },
        {
            "Overall": 82.5,
            "AR": 86.1,
            "CP": 81.1,
            "FP-C": 80.5,
            "FP-S": 87.5,
            "LR": 76.1,
            "RR": 80.6,
            "action_recognition": 88.9,
            "attribute_comparison": 85.3,
            "attribute_recognition": 97.8,
            "celebrity_recognition": 77.6,
            "function_reasoning": 85.6,
            "future_prediction": 82.7,
            "identity_reasoning": 97.4,
            "image_emotion": 84.4,
            "image_quality": 59.7,
            "image_scene": 88.9,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 83.7,
            "object_localization": 81.9,
            "ocr": 100.0,
            "physical_property_reasoning": 75.9,
            "physical_relation": 70.7,
            "social_relation": 85.7,
            "spatial_relationship": 62.7,
            "structuralized_imagetext_understanding": 71.6,
            "Method": [
                "SAIL-VL-1.5-8B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL-1d5-8B"
            ],
            "Parameters": "7.95B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "InternViT-300B",
            "Org": "ByteDance",
            "Time": "2025/04/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL-1.5-8B",
            "key": 496
        },
        {
            "Overall": 84.3,
            "AR": 89.0,
            "CP": 83.0,
            "FP-C": 82.4,
            "FP-S": 88.4,
            "LR": 75.0,
            "RR": 84.5,
            "action_recognition": 94.0,
            "attribute_comparison": 81.3,
            "attribute_recognition": 98.9,
            "celebrity_recognition": 80.3,
            "function_reasoning": 93.3,
            "future_prediction": 82.7,
            "identity_reasoning": 97.4,
            "image_emotion": 85.6,
            "image_quality": 60.5,
            "image_scene": 92.4,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 91.3,
            "object_localization": 82.9,
            "ocr": 97.8,
            "physical_property_reasoning": 75.9,
            "physical_relation": 73.3,
            "social_relation": 86.8,
            "spatial_relationship": 65.3,
            "structuralized_imagetext_understanding": 69.7,
            "Method": [
                "SAIL-VL-1.6-8B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL-1d6-8B"
            ],
            "Parameters": "8.33B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "AIMv2 Huge",
            "Org": "ByteDance",
            "Time": "2025/04/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL-1.6-8B",
            "key": 497
        },
        {
            "Overall": 88.4,
            "AR": 89.4,
            "CP": 83.7,
            "FP-C": 89.1,
            "FP-S": 95.6,
            "LR": 85.3,
            "RR": 86.4,
            "action_recognition": 92.3,
            "attribute_comparison": 86.7,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 93.9,
            "function_reasoning": 95.6,
            "future_prediction": 84.0,
            "identity_reasoning": 96.1,
            "image_emotion": 84.4,
            "image_quality": 64.5,
            "image_scene": 91.0,
            "image_style": 84.8,
            "image_topic": 96.7,
            "nature_relation": 90.2,
            "object_localization": 95.2,
            "ocr": 98.9,
            "physical_property_reasoning": 75.9,
            "physical_relation": 77.3,
            "social_relation": 90.1,
            "spatial_relationship": 86.7,
            "structuralized_imagetext_understanding": 86.2,
            "Method": [
                "SenseNova-V6-Pro",
                "https://platform.sensenova.cn/technology/fusion/Pro/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "SenseTime",
            "Time": "2025/05/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SenseNova-V6-Pro",
            "key": 498
        },
        {
            "Overall": 72.6,
            "AR": 73.9,
            "CP": 78.1,
            "FP-C": 65.2,
            "FP-S": 76.6,
            "LR": 54.3,
            "RR": 74.0,
            "action_recognition": 88.0,
            "attribute_comparison": 54.7,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 66.7,
            "function_reasoning": 84.4,
            "future_prediction": 62.7,
            "identity_reasoning": 94.7,
            "image_emotion": 76.7,
            "image_quality": 53.2,
            "image_scene": 89.6,
            "image_style": 76.1,
            "image_topic": 97.8,
            "nature_relation": 68.5,
            "object_localization": 63.8,
            "ocr": 88.9,
            "physical_property_reasoning": 41.8,
            "physical_relation": 61.3,
            "social_relation": 90.1,
            "spatial_relationship": 40.0,
            "structuralized_imagetext_understanding": 48.6,
            "Method": [
                "QTuneVL1-2B",
                "https://huggingface.co/hanchaow/QTuneVL1-2B"
            ],
            "Parameters": "2.21B",
            "Language Model": "InternLM2.5-1.8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Reconova AI Lab",
            "Time": "2025/05/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "QTuneVL1-2B",
            "key": 499
        },
        {
            "Overall": 87.9,
            "AR": 92.7,
            "CP": 81.7,
            "FP-C": 91.0,
            "FP-S": 93.5,
            "LR": 83.7,
            "RR": 86.8,
            "action_recognition": 93.2,
            "attribute_comparison": 90.7,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 89.8,
            "function_reasoning": 96.7,
            "future_prediction": 86.7,
            "identity_reasoning": 98.7,
            "image_emotion": 80.0,
            "image_quality": 60.5,
            "image_scene": 90.3,
            "image_style": 82.6,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 92.4,
            "ocr": 98.9,
            "physical_property_reasoning": 82.3,
            "physical_relation": 77.3,
            "social_relation": 87.9,
            "spatial_relationship": 88.0,
            "structuralized_imagetext_understanding": 81.7,
            "Method": [
                "CongRong-v2.0",
                "http://115.120.28.181:20228/web/#/document-center"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "CloudWalk",
            "Time": "2025/05/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "CongRong-v2.0",
            "key": 500
        },
        {
            "Overall": 82.5,
            "AR": 82.4,
            "CP": 80.7,
            "FP-C": 81.3,
            "FP-S": 91.2,
            "LR": 75.0,
            "RR": 78.7,
            "action_recognition": 85.5,
            "attribute_comparison": 85.3,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 92.5,
            "function_reasoning": 93.3,
            "future_prediction": 77.3,
            "identity_reasoning": 96.1,
            "image_emotion": 78.9,
            "image_quality": 58.1,
            "image_scene": 89.6,
            "image_style": 82.6,
            "image_topic": 97.8,
            "nature_relation": 85.9,
            "object_localization": 85.7,
            "ocr": 96.7,
            "physical_property_reasoning": 57.0,
            "physical_relation": 58.7,
            "social_relation": 87.9,
            "spatial_relationship": 70.7,
            "structuralized_imagetext_understanding": 73.4,
            "Method": [
                "WeThink-Qwen2.5VL-7B",
                "https://huggingface.co/yangjie-cv/WeThink-Qwen2.5VL-7B"
            ],
            "Parameters": "8.29B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "QwenViT",
            "Org": "WeChat Vision",
            "Time": "2025/05/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "WeThink-Qwen2.5VL-7B",
            "key": 501
        },
        {
            "Overall": 81.2,
            "AR": 88.2,
            "CP": 79.4,
            "FP-C": 75.7,
            "FP-S": 88.4,
            "LR": 67.9,
            "RR": 81.4,
            "action_recognition": 88.9,
            "attribute_comparison": 74.7,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 87.1,
            "function_reasoning": 96.7,
            "future_prediction": 81.3,
            "identity_reasoning": 96.1,
            "image_emotion": 76.7,
            "image_quality": 58.1,
            "image_scene": 87.5,
            "image_style": 80.4,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 79.0,
            "ocr": 96.7,
            "physical_property_reasoning": 70.9,
            "physical_relation": 61.3,
            "social_relation": 85.7,
            "spatial_relationship": 56.0,
            "structuralized_imagetext_understanding": 58.7,
            "Method": [
                "valley2",
                "https://huggingface.co/bytedance-research/Valley-Eagle-7B"
            ],
            "Parameters": "8.88B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2025/05/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "valley2",
            "key": 502
        },
        {
            "Overall": 82.1,
            "AR": 88.6,
            "CP": 78.7,
            "FP-C": 76.4,
            "FP-S": 89.3,
            "LR": 76.1,
            "RR": 81.0,
            "action_recognition": 86.3,
            "attribute_comparison": 76.0,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 88.4,
            "function_reasoning": 95.6,
            "future_prediction": 82.7,
            "identity_reasoning": 96.1,
            "image_emotion": 77.8,
            "image_quality": 57.3,
            "image_scene": 86.8,
            "image_style": 78.3,
            "image_topic": 96.7,
            "nature_relation": 92.4,
            "object_localization": 79.0,
            "ocr": 97.8,
            "physical_property_reasoning": 73.4,
            "physical_relation": 61.3,
            "social_relation": 85.7,
            "spatial_relationship": 61.3,
            "structuralized_imagetext_understanding": 71.6,
            "Method": [
                "valley2_dpo",
                "https://huggingface.co/bytedance-research/Valley2-DPO"
            ],
            "Parameters": "8.88B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2025/05/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "valley2_dpo",
            "key": 503
        },
        {
            "Overall": 77.1,
            "AR": 86.1,
            "CP": 76.7,
            "FP-C": 73.8,
            "FP-S": 79.6,
            "LR": 63.0,
            "RR": 79.1,
            "action_recognition": 86.3,
            "attribute_comparison": 82.7,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 71.4,
            "function_reasoning": 93.3,
            "future_prediction": 76.0,
            "identity_reasoning": 97.4,
            "image_emotion": 76.7,
            "image_quality": 54.0,
            "image_scene": 86.1,
            "image_style": 70.7,
            "image_topic": 98.9,
            "nature_relation": 84.8,
            "object_localization": 67.6,
            "ocr": 92.2,
            "physical_property_reasoning": 67.1,
            "physical_relation": 65.3,
            "social_relation": 84.6,
            "spatial_relationship": 45.3,
            "structuralized_imagetext_understanding": 54.1,
            "Method": [
                "Flash-VL-2B-Dynamic-ISS",
                "https://huggingface.co/FlashVL/FlashVL-2B-Dynamic-ISS"
            ],
            "Parameters": "2.53B",
            "Language Model": "Qwen-2.5-1.5B-Instruct",
            "Vision Model": "SigLIP2-400M-512",
            "Org": "Meituan",
            "Time": "2025/05/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Flash-VL-2B-Dynamic-ISS",
            "key": 504
        },
        {
            "Overall": 89.0,
            "AR": 85.7,
            "CP": 84.8,
            "FP-C": 91.0,
            "FP-S": 95.8,
            "LR": 90.2,
            "RR": 86.8,
            "action_recognition": 92.3,
            "attribute_comparison": 94.7,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 98.0,
            "function_reasoning": 96.7,
            "future_prediction": 82.7,
            "identity_reasoning": 100.0,
            "image_emotion": 76.7,
            "image_quality": 72.6,
            "image_scene": 91.0,
            "image_style": 87.0,
            "image_topic": 97.8,
            "nature_relation": 95.7,
            "object_localization": 90.5,
            "ocr": 98.9,
            "physical_property_reasoning": 59.5,
            "physical_relation": 77.3,
            "social_relation": 85.7,
            "spatial_relationship": 85.3,
            "structuralized_imagetext_understanding": 95.4,
            "Method": [
                "Seed1.5-VL",
                "https://github.com/ByteDance-Seed/Seed1.5-VL"
            ],
            "Parameters": "",
            "Language Model": "Seed1.5-LLM",
            "Vision Model": "Seed-ViT",
            "Org": "ByteDance",
            "Time": "2025/05/30",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "Seed1.5-VL",
            "key": 505
        },
        {
            "Overall": 76.8,
            "AR": 81.2,
            "CP": 79.6,
            "FP-C": 68.5,
            "FP-S": 82.1,
            "LR": 67.4,
            "RR": 72.9,
            "action_recognition": 82.1,
            "attribute_comparison": 69.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 73.5,
            "function_reasoning": 87.8,
            "future_prediction": 69.3,
            "identity_reasoning": 92.1,
            "image_emotion": 77.8,
            "image_quality": 55.6,
            "image_scene": 91.0,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 78.3,
            "object_localization": 74.3,
            "ocr": 98.9,
            "physical_property_reasoning": 63.3,
            "physical_relation": 64.0,
            "social_relation": 74.7,
            "spatial_relationship": 46.7,
            "structuralized_imagetext_understanding": 66.1,
            "Method": [
                "Long-VITA-16K",
                "https://huggingface.co/VITA-MLLM/Long-VITA-16K"
            ],
            "Parameters": "14B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "InternViT-300M",
            "Org": "Tencent Youtu Lab & Nanjing University",
            "Time": "2025/06/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Long-VITA-16K",
            "key": 506
        },
        {
            "Overall": 65.3,
            "AR": 78.0,
            "CP": 70.6,
            "FP-C": 56.6,
            "FP-S": 67.3,
            "LR": 45.1,
            "RR": 62.4,
            "action_recognition": 77.8,
            "attribute_comparison": 58.7,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 68.7,
            "function_reasoning": 85.6,
            "future_prediction": 56.0,
            "identity_reasoning": 94.7,
            "image_emotion": 72.2,
            "image_quality": 32.3,
            "image_scene": 84.7,
            "image_style": 72.8,
            "image_topic": 96.7,
            "nature_relation": 71.7,
            "object_localization": 34.3,
            "ocr": 91.1,
            "physical_property_reasoning": 53.2,
            "physical_relation": 37.3,
            "social_relation": 73.6,
            "spatial_relationship": 21.3,
            "structuralized_imagetext_understanding": 37.6,
            "Method": [
                "HawkVL-2B",
                "https://huggingface.co/xjtupanda/HawkVL-2B"
            ],
            "Parameters": "2.44B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "QwenViT",
            "Org": " Reconova AI Lab & USTC",
            "Time": "2025/06/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "HawkVL-2B",
            "key": 507
        },
        {
            "Overall": 74.1,
            "AR": 81.2,
            "CP": 76.7,
            "FP-C": 67.4,
            "FP-S": 79.4,
            "LR": 61.4,
            "RR": 69.0,
            "action_recognition": 85.5,
            "attribute_comparison": 74.7,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 70.1,
            "function_reasoning": 86.7,
            "future_prediction": 66.7,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 50.8,
            "image_scene": 84.7,
            "image_style": 76.1,
            "image_topic": 96.7,
            "nature_relation": 63.0,
            "object_localization": 70.5,
            "ocr": 90.0,
            "physical_property_reasoning": 59.5,
            "physical_relation": 61.3,
            "social_relation": 81.3,
            "spatial_relationship": 32.0,
            "structuralized_imagetext_understanding": 57.8,
            "Method": [
                "granite-vision-3.1-2b-preview",
                "https://huggingface.co/ibm-granite/granite-vision-3.1-2b-preview"
            ],
            "Parameters": "2.98B",
            "Language Model": "granite-3.1-2b-instruct",
            "Vision Model": "SigLip",
            "Org": "IBM",
            "Time": "2025/06/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "granite_vision_3.1_2b_preview",
            "key": 508
        },
        {
            "Overall": 75.8,
            "AR": 81.2,
            "CP": 77.2,
            "FP-C": 69.3,
            "FP-S": 81.9,
            "LR": 63.0,
            "RR": 73.3,
            "action_recognition": 88.0,
            "attribute_comparison": 74.7,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 75.5,
            "function_reasoning": 88.9,
            "future_prediction": 73.3,
            "identity_reasoning": 96.1,
            "image_emotion": 81.1,
            "image_quality": 50.8,
            "image_scene": 84.7,
            "image_style": 77.2,
            "image_topic": 97.8,
            "nature_relation": 68.5,
            "object_localization": 72.4,
            "ocr": 90.0,
            "physical_property_reasoning": 58.2,
            "physical_relation": 62.7,
            "social_relation": 86.8,
            "spatial_relationship": 34.7,
            "structuralized_imagetext_understanding": 56.0,
            "Method": [
                "granite-vision-3.2-2b",
                "https://huggingface.co/ibm-granite/granite-vision-3.2-2b"
            ],
            "Parameters": "2.98B",
            "Language Model": "granite-3.1-2b-instruct",
            "Vision Model": "SigLip",
            "Org": "IBM",
            "Time": "2025/06/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "granite_vision_3.2_2b",
            "key": 509
        },
        {
            "Overall": 71.3,
            "AR": 76.7,
            "CP": 72.4,
            "FP-C": 67.8,
            "FP-S": 77.7,
            "LR": 56.0,
            "RR": 67.8,
            "action_recognition": 88.0,
            "attribute_comparison": 77.3,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 68.0,
            "function_reasoning": 83.3,
            "future_prediction": 61.3,
            "identity_reasoning": 98.7,
            "image_emotion": 70.0,
            "image_quality": 41.1,
            "image_scene": 84.0,
            "image_style": 71.7,
            "image_topic": 100.0,
            "nature_relation": 64.1,
            "object_localization": 67.6,
            "ocr": 93.3,
            "physical_property_reasoning": 48.1,
            "physical_relation": 58.7,
            "social_relation": 79.1,
            "spatial_relationship": 26.7,
            "structuralized_imagetext_understanding": 52.3,
            "Method": [
                "granite-vision-3.3-2b",
                "https://huggingface.co/ibm-granite/granite-vision-3.3-2b"
            ],
            "Parameters": "2.98B",
            "Language Model": "granite-3.1-2b-instruct",
            "Vision Model": "SigLIP2-400M",
            "Org": "IBM",
            "Time": "2025/06/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "granite_vision_3.3_2b",
            "key": 510
        },
        {
            "Overall": 81.5,
            "AR": 73.5,
            "CP": 82.0,
            "FP-C": 80.1,
            "FP-S": 88.6,
            "LR": 81.0,
            "RR": 77.5,
            "action_recognition": 80.3,
            "attribute_comparison": 90.7,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 89.8,
            "function_reasoning": 81.1,
            "future_prediction": 77.3,
            "identity_reasoning": 96.1,
            "image_emotion": 75.6,
            "image_quality": 68.5,
            "image_scene": 89.6,
            "image_style": 84.8,
            "image_topic": 92.2,
            "nature_relation": 85.9,
            "object_localization": 82.9,
            "ocr": 95.6,
            "physical_property_reasoning": 43.0,
            "physical_relation": 64.0,
            "social_relation": 80.2,
            "spatial_relationship": 69.3,
            "structuralized_imagetext_understanding": 83.5,
            "Method": [
                "MiMo-VL-7B",
                "https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-RL"
            ],
            "Parameters": "8.31B",
            "Language Model": "Mimo-7B",
            "Vision Model": "Qwen2.5-ViT",
            "Org": "Xiaomi",
            "Time": "2025/07/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MiMo-VL-7B-RL",
            "key": 511
        },
        {
            "Overall": 84.7,
            "AR": 88.6,
            "CP": 82.2,
            "FP-C": 80.9,
            "FP-S": 91.0,
            "LR": 84.2,
            "RR": 79.8,
            "action_recognition": 80.3,
            "attribute_comparison": 89.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 89.1,
            "function_reasoning": 95.6,
            "future_prediction": 78.7,
            "identity_reasoning": 96.1,
            "image_emotion": 76.7,
            "image_quality": 63.7,
            "image_scene": 92.4,
            "image_style": 80.4,
            "image_topic": 98.9,
            "nature_relation": 85.9,
            "object_localization": 90.5,
            "ocr": 96.7,
            "physical_property_reasoning": 73.4,
            "physical_relation": 62.7,
            "social_relation": 87.9,
            "spatial_relationship": 73.3,
            "structuralized_imagetext_understanding": 88.1,
            "Method": [
                "Qwen2.5-VL-32B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct"
            ],
            "Parameters": "33.5B",
            "Language Model": "Qwen2.5-32B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/07/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-32B-Instruct",
            "key": 512
        },
        {
            "Overall": 80.4,
            "AR": 81.6,
            "CP": 78.0,
            "FP-C": 79.0,
            "FP-S": 87.0,
            "LR": 77.7,
            "RR": 76.4,
            "action_recognition": 86.3,
            "attribute_comparison": 82.7,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 89.1,
            "function_reasoning": 94.4,
            "future_prediction": 76.0,
            "identity_reasoning": 98.7,
            "image_emotion": 72.2,
            "image_quality": 62.1,
            "image_scene": 86.1,
            "image_style": 79.3,
            "image_topic": 91.1,
            "nature_relation": 82.6,
            "object_localization": 76.2,
            "ocr": 95.6,
            "physical_property_reasoning": 50.6,
            "physical_relation": 60.0,
            "social_relation": 83.5,
            "spatial_relationship": 64.0,
            "structuralized_imagetext_understanding": 78.9,
            "Method": [
                "Kimi-VL-A3B-Thinking-2506",
                "https://huggingface.co/moonshotai/Kimi-VL-A3B-Thinking-2506"
            ],
            "Parameters": "16.4B",
            "Language Model": "Moonlight-16B-A3B",
            "Vision Model": "MoonViT",
            "Org": "moonshot.ai",
            "Time": "2025/07/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kimi-VL-A3B-Thinking-2506",
            "key": 513
        },
        {
            "Overall": 73.7,
            "AR": 70.6,
            "CP": 75.2,
            "FP-C": 70.0,
            "FP-S": 78.9,
            "LR": 73.9,
            "RR": 68.2,
            "action_recognition": 77.8,
            "attribute_comparison": 76.0,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 70.7,
            "function_reasoning": 75.6,
            "future_prediction": 68.0,
            "identity_reasoning": 93.4,
            "image_emotion": 72.2,
            "image_quality": 68.5,
            "image_scene": 78.5,
            "image_style": 71.7,
            "image_topic": 85.6,
            "nature_relation": 66.3,
            "object_localization": 71.4,
            "ocr": 90.0,
            "physical_property_reasoning": 43.0,
            "physical_relation": 62.7,
            "social_relation": 74.7,
            "spatial_relationship": 52.0,
            "structuralized_imagetext_understanding": 78.0,
            "Method": [
                "BlueLM-2.5-3B",
                "https://arxiv.org/pdf/2507.05934"
            ],
            "Parameters": "2.9B",
            "Language Model": "BlueLM-base-3B",
            "Vision Model": "Siglip2-So400M",
            "Org": "Vivo",
            "Time": "2025/07/16",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "BlueLM-2.5-3B",
            "key": 514
        },
        {
            "Overall": 78.3,
            "AR": 79.2,
            "CP": 81.1,
            "FP-C": 74.9,
            "FP-S": 82.8,
            "LR": 63.6,
            "RR": 77.9,
            "action_recognition": 88.0,
            "attribute_comparison": 78.7,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 76.2,
            "function_reasoning": 87.8,
            "future_prediction": 70.7,
            "identity_reasoning": 96.1,
            "image_emotion": 75.6,
            "image_quality": 61.3,
            "image_scene": 88.9,
            "image_style": 84.8,
            "image_topic": 97.8,
            "nature_relation": 75.0,
            "object_localization": 71.4,
            "ocr": 96.7,
            "physical_property_reasoning": 53.2,
            "physical_relation": 69.3,
            "social_relation": 87.9,
            "spatial_relationship": 50.7,
            "structuralized_imagetext_understanding": 58.7,
            "Method": [
                "Ovis-U1-3B",
                "https://huggingface.co/AIDC-AI/Ovis-U1-3B"
            ],
            "Parameters": "3.64B",
            "Language Model": "Qwen3-1.7B",
            "Vision Model": "aimv2-large-path14-448",
            "Org": "Ovis Team, Alibaba Group",
            "Time": "2025/07/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis-U1-3B",
            "key": 515
        },
        {
            "Overall": 74.9,
            "AR": 83.7,
            "CP": 78.9,
            "FP-C": 73.0,
            "FP-S": 74.7,
            "LR": 53.8,
            "RR": 75.2,
            "action_recognition": 88.0,
            "attribute_comparison": 77.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 67.3,
            "function_reasoning": 91.1,
            "future_prediction": 64.0,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 52.4,
            "image_scene": 88.9,
            "image_style": 79.3,
            "image_topic": 97.8,
            "nature_relation": 82.6,
            "object_localization": 62.9,
            "ocr": 86.7,
            "physical_property_reasoning": 62.0,
            "physical_relation": 52.0,
            "social_relation": 86.8,
            "spatial_relationship": 45.3,
            "structuralized_imagetext_understanding": 46.8,
            "Method": [
                "VARCO-VISION-2.0-1.7B",
                "https://huggingface.co/NCSOFT/VARCO-VISION-2.0-1.7B"
            ],
            "Parameters": "2.12B",
            "Language Model": "Qwen3-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "NCSOFT",
            "Time": "2025/08/04",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "varco-vision-2-1.7b",
            "key": 516
        },
        {
            "Overall": 84.4,
            "AR": 87.3,
            "CP": 81.5,
            "FP-C": 81.3,
            "FP-S": 90.3,
            "LR": 79.9,
            "RR": 84.5,
            "action_recognition": 87.2,
            "attribute_comparison": 90.7,
            "attribute_recognition": 97.8,
            "celebrity_recognition": 81.6,
            "function_reasoning": 93.3,
            "future_prediction": 84.0,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 60.5,
            "image_scene": 90.3,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 91.3,
            "object_localization": 88.6,
            "ocr": 98.9,
            "physical_property_reasoning": 70.9,
            "physical_relation": 70.7,
            "social_relation": 89.0,
            "spatial_relationship": 62.7,
            "structuralized_imagetext_understanding": 77.1,
            "Method": [
                "VARCO-VISION-2.0-14B",
                "https://huggingface.co/NCSOFT/VARCO-VISION-2.0-14B"
            ],
            "Parameters": "15.2B",
            "Language Model": "Qwen3-14B",
            "Vision Model": "SigLIP-400M",
            "Org": "NCSOFT",
            "Time": "2025/08/04",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "varco-vision-2-14b",
            "key": 517
        },
        {
            "Overall": 88.5,
            "AR": 92.2,
            "CP": 83.3,
            "FP-C": 91.8,
            "FP-S": 94.2,
            "LR": 85.9,
            "RR": 84.5,
            "action_recognition": 92.3,
            "attribute_comparison": 94.7,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 94.6,
            "function_reasoning": 95.6,
            "future_prediction": 89.3,
            "identity_reasoning": 98.7,
            "image_emotion": 82.2,
            "image_quality": 66.9,
            "image_scene": 86.1,
            "image_style": 88.0,
            "image_topic": 97.8,
            "nature_relation": 89.1,
            "object_localization": 87.6,
            "ocr": 98.9,
            "physical_property_reasoning": 82.3,
            "physical_relation": 69.3,
            "social_relation": 92.3,
            "spatial_relationship": 88.0,
            "structuralized_imagetext_understanding": 83.5,
            "Method": [
                "JT-VL-Chat-V3.0",
                "https://github.com/jiutiancv/JT-VL-Chat/tree/main"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "China Mobile",
            "Time": "2025/08/04",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "JTVL-V3",
            "key": 386
        },
        {
            "Overall": 78.6,
            "AR": 81.6,
            "CP": 79.3,
            "FP-C": 74.5,
            "FP-S": 83.3,
            "LR": 64.1,
            "RR": 81.0,
            "action_recognition": 90.6,
            "attribute_comparison": 81.3,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 77.6,
            "function_reasoning": 92.2,
            "future_prediction": 72.0,
            "identity_reasoning": 97.4,
            "image_emotion": 75.6,
            "image_quality": 56.5,
            "image_scene": 88.2,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 85.9,
            "object_localization": 73.3,
            "ocr": 95.6,
            "physical_property_reasoning": 54.4,
            "physical_relation": 61.3,
            "social_relation": 92.3,
            "spatial_relationship": 42.7,
            "structuralized_imagetext_understanding": 58.7,
            "Method": [
                "QTuneVL1.5-2B",
                "https://huggingface.co/hanchaow/QTuneVL1_5-2B"
            ],
            "Parameters": "2.09B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Reconova AI Lab & BDAA-Lab ",
            "Time": "2025/08/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "QTuneVL1_5-2B",
            "key": 518
        },
        {
            "Overall": 77.5,
            "AR": 82.0,
            "CP": 77.6,
            "FP-C": 70.0,
            "FP-S": 86.3,
            "LR": 66.8,
            "RR": 73.3,
            "action_recognition": 83.8,
            "attribute_comparison": 76.0,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 91.8,
            "function_reasoning": 93.3,
            "future_prediction": 69.3,
            "identity_reasoning": 96.1,
            "image_emotion": 77.8,
            "image_quality": 48.4,
            "image_scene": 91.0,
            "image_style": 76.1,
            "image_topic": 97.8,
            "nature_relation": 78.3,
            "object_localization": 71.4,
            "ocr": 95.6,
            "physical_property_reasoning": 55.7,
            "physical_relation": 49.3,
            "social_relation": 87.9,
            "spatial_relationship": 42.7,
            "structuralized_imagetext_understanding": 65.1,
            "Method": [
                "QTuneVL1.5-3B",
                "https://huggingface.co/hanchaow/QTuneVL1_5-3B"
            ],
            "Parameters": "3.75B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "QwenViT",
            "Org": "Reconova AI Lab & BDAA-Lab ",
            "Time": "2025/08/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "QTuneVL1_5-3B",
            "key": 519
        },
        {
            "Overall": 83.7,
            "AR": 85.7,
            "CP": 80.4,
            "FP-C": 85.0,
            "FP-S": 88.9,
            "LR": 80.4,
            "RR": 81.4,
            "action_recognition": 89.7,
            "attribute_comparison": 90.7,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 83.0,
            "function_reasoning": 92.2,
            "future_prediction": 70.7,
            "identity_reasoning": 94.7,
            "image_emotion": 80.0,
            "image_quality": 60.5,
            "image_scene": 88.2,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 91.3,
            "object_localization": 82.9,
            "ocr": 98.9,
            "physical_property_reasoning": 69.6,
            "physical_relation": 70.7,
            "social_relation": 80.2,
            "spatial_relationship": 72.0,
            "structuralized_imagetext_understanding": 87.2,
            "Method": [
                "R-4B",
                "https://huggingface.co/YannQi/R-4B"
            ],
            "Parameters": "4.82B",
            "Language Model": "Qwen3-4B",
            "Vision Model": "SigLip-400M",
            "Org": "",
            "Time": "2025/08/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "X-VL-4B",
            "key": 520
        },
        {
            "Overall": 86.8,
            "AR": 89.8,
            "CP": 86.9,
            "FP-C": 92.9,
            "FP-S": 78.7,
            "LR": 90.2,
            "RR": 88.8,
            "action_recognition": 95.7,
            "attribute_comparison": 88.0,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 51.0,
            "function_reasoning": 93.3,
            "future_prediction": 89.3,
            "identity_reasoning": 100.0,
            "image_emotion": 81.1,
            "image_quality": 74.2,
            "image_scene": 91.7,
            "image_style": 91.3,
            "image_topic": 97.8,
            "nature_relation": 96.7,
            "object_localization": 84.8,
            "ocr": 100.0,
            "physical_property_reasoning": 75.9,
            "physical_relation": 73.3,
            "social_relation": 93.4,
            "spatial_relationship": 93.3,
            "structuralized_imagetext_understanding": 90.8,
            "Method": [
                "GPT-5-20250807",
                "https://openai.com/index/introducing-gpt-5/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/08/14",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "gpt-5-2025-08-07",
            "key": 521
        },
        {
            "Overall": 78.9,
            "AR": 82.9,
            "CP": 79.4,
            "FP-C": 81.6,
            "FP-S": 74.2,
            "LR": 83.2,
            "RR": 75.6,
            "action_recognition": 81.2,
            "attribute_comparison": 86.7,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 51.7,
            "function_reasoning": 88.9,
            "future_prediction": 77.3,
            "identity_reasoning": 93.4,
            "image_emotion": 76.7,
            "image_quality": 60.5,
            "image_scene": 87.5,
            "image_style": 77.2,
            "image_topic": 97.8,
            "nature_relation": 85.9,
            "object_localization": 72.4,
            "ocr": 97.8,
            "physical_property_reasoning": 65.8,
            "physical_relation": 57.3,
            "social_relation": 80.2,
            "spatial_relationship": 77.3,
            "structuralized_imagetext_understanding": 87.2,
            "Method": [
                "GPT-5-nano-20250807",
                "https://openai.com/index/introducing-gpt-5/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/08/14",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "gpt-5-nano-2025-08-07",
            "key": 522
        },
        {
            "Overall": 86.2,
            "AR": 91.0,
            "CP": 86.3,
            "FP-C": 90.3,
            "FP-S": 80.5,
            "LR": 89.7,
            "RR": 84.5,
            "action_recognition": 89.7,
            "attribute_comparison": 89.3,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 57.1,
            "function_reasoning": 95.6,
            "future_prediction": 80.0,
            "identity_reasoning": 97.4,
            "image_emotion": 81.1,
            "image_quality": 80.6,
            "image_scene": 90.3,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 91.3,
            "object_localization": 87.6,
            "ocr": 97.8,
            "physical_property_reasoning": 79.7,
            "physical_relation": 72.0,
            "social_relation": 87.9,
            "spatial_relationship": 92.0,
            "structuralized_imagetext_understanding": 96.3,
            "Method": [
                "GPT-5-mini-20250807",
                "https://openai.com/index/introducing-gpt-5/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/08/14",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "gpt-5-mini-2025-08-07",
            "key": 523
        },
        {
            "Overall": 87.6,
            "AR": 88.6,
            "CP": 83.0,
            "FP-C": 88.0,
            "FP-S": 94.2,
            "LR": 83.7,
            "RR": 88.0,
            "action_recognition": 91.5,
            "attribute_comparison": 89.3,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 91.2,
            "function_reasoning": 95.6,
            "future_prediction": 80.0,
            "identity_reasoning": 97.4,
            "image_emotion": 85.6,
            "image_quality": 62.9,
            "image_scene": 89.6,
            "image_style": 82.6,
            "image_topic": 97.8,
            "nature_relation": 97.8,
            "object_localization": 93.3,
            "ocr": 97.8,
            "physical_property_reasoning": 72.2,
            "physical_relation": 76.0,
            "social_relation": 87.9,
            "spatial_relationship": 81.3,
            "structuralized_imagetext_understanding": 86.2,
            "Method": [
                "SenseNova-V6-5-Pro",
                "https://platform.sensenova.cn/technology/fusion/Pro/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "SenseTime",
            "Time": "2025/09/03",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "SenseNova-V6-5-Pro",
            "key": 524
        },
        {
            "Overall": 86.4,
            "AR": 86.1,
            "CP": 86.3,
            "FP-C": 84.3,
            "FP-S": 92.3,
            "LR": 81.0,
            "RR": 83.3,
            "action_recognition": 84.6,
            "attribute_comparison": 80.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 91.8,
            "function_reasoning": 94.4,
            "future_prediction": 74.7,
            "identity_reasoning": 98.7,
            "image_emotion": 75.6,
            "image_quality": 83.1,
            "image_scene": 89.6,
            "image_style": 84.8,
            "image_topic": 97.8,
            "nature_relation": 91.3,
            "object_localization": 86.7,
            "ocr": 98.9,
            "physical_property_reasoning": 64.6,
            "physical_relation": 73.3,
            "social_relation": 83.5,
            "spatial_relationship": 88.0,
            "structuralized_imagetext_understanding": 85.3,
            "Method": [
                "BlueLM-2.5-3B-0909",
                "https://developers.vivo.com/product/ai/bluelm"
            ],
            "Parameters": "3B",
            "Language Model": "BlueLM-base-3B",
            "Vision Model": "Siglip2-So400M",
            "Org": "Vivo",
            "Time": "2025/09/17",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "BlueLM-2.6-3B",
            "key": 525
        },
        {
            "Overall": 80.9,
            "AR": 81.2,
            "CP": 80.6,
            "FP-C": 77.9,
            "FP-S": 86.1,
            "LR": 71.7,
            "RR": 82.2,
            "action_recognition": 93.2,
            "attribute_comparison": 74.7,
            "attribute_recognition": 97.8,
            "celebrity_recognition": 76.2,
            "function_reasoning": 96.7,
            "future_prediction": 82.7,
            "identity_reasoning": 94.7,
            "image_emotion": 81.1,
            "image_quality": 58.9,
            "image_scene": 87.5,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 84.8,
            "object_localization": 81.0,
            "ocr": 96.7,
            "physical_property_reasoning": 50.6,
            "physical_relation": 70.7,
            "social_relation": 89.0,
            "spatial_relationship": 57.3,
            "structuralized_imagetext_understanding": 64.2,
            "Method": [
                "SAIL-VL2-2B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL2-2B"
            ],
            "Parameters": "2.73B",
            "Language Model": "Qwen3-1.7B",
            "Vision Model": "SAILViT-Huge",
            "Org": "Douyin",
            "Time": "2025/09/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL2-2B",
            "key": 526
        },
        {
            "Overall": 84.3,
            "AR": 88.6,
            "CP": 80.7,
            "FP-C": 83.9,
            "FP-S": 90.0,
            "LR": 78.8,
            "RR": 82.6,
            "action_recognition": 91.5,
            "attribute_comparison": 92.0,
            "attribute_recognition": 97.8,
            "celebrity_recognition": 81.6,
            "function_reasoning": 92.2,
            "future_prediction": 78.7,
            "identity_reasoning": 96.1,
            "image_emotion": 81.1,
            "image_quality": 62.9,
            "image_scene": 87.5,
            "image_style": 77.2,
            "image_topic": 97.8,
            "nature_relation": 89.1,
            "object_localization": 88.6,
            "ocr": 97.8,
            "physical_property_reasoning": 77.2,
            "physical_relation": 72.0,
            "social_relation": 84.6,
            "spatial_relationship": 64.0,
            "structuralized_imagetext_understanding": 78.9,
            "Method": [
                "SAIL-VL2-8B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL2-8B"
            ],
            "Parameters": "8.91B",
            "Language Model": "Qwen3-8B",
            "Vision Model": "SAILViT-Huge",
            "Org": "Douyin",
            "Time": "2025/09/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL2-8B",
            "key": 527
        },
        {
            "Overall": 87.3,
            "AR": 90.2,
            "CP": 84.4,
            "FP-C": 90.3,
            "FP-S": 93.0,
            "LR": 79.3,
            "RR": 83.3,
            "action_recognition": 94.0,
            "attribute_comparison": 96.0,
            "attribute_recognition": 97.8,
            "celebrity_recognition": 93.2,
            "function_reasoning": 92.2,
            "future_prediction": 86.7,
            "identity_reasoning": 100.0,
            "image_emotion": 83.3,
            "image_quality": 70.2,
            "image_scene": 86.1,
            "image_style": 90.2,
            "image_topic": 96.7,
            "nature_relation": 89.1,
            "object_localization": 86.7,
            "ocr": 95.6,
            "physical_property_reasoning": 78.5,
            "physical_relation": 72.0,
            "social_relation": 86.8,
            "spatial_relationship": 78.7,
            "structuralized_imagetext_understanding": 74.3,
            "Method": [
                "JT-VL-Chat-Mini",
                "https://github.com/jiutiancv/JT-VL-Chat/tree/main"
            ],
            "Parameters": "3.8B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "China Mobile",
            "Time": "2025/10/26",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "JTVL-Mini",
            "key": 528
        },
        {
            "Overall": 86.2,
            "AR": 91.0,
            "CP": 84.4,
            "FP-C": 88.0,
            "FP-S": 90.0,
            "LR": 73.9,
            "RR": 85.7,
            "action_recognition": 92.3,
            "attribute_comparison": 93.3,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 88.4,
            "function_reasoning": 93.3,
            "future_prediction": 84.0,
            "identity_reasoning": 98.7,
            "image_emotion": 84.4,
            "image_quality": 64.5,
            "image_scene": 89.6,
            "image_style": 90.2,
            "image_topic": 97.8,
            "nature_relation": 90.2,
            "object_localization": 83.8,
            "ocr": 95.6,
            "physical_property_reasoning": 81.0,
            "physical_relation": 72.0,
            "social_relation": 92.3,
            "spatial_relationship": 76.0,
            "structuralized_imagetext_understanding": 67.0,
            "Method": [
                "JT-VL-Chat-2B",
                "https://github.com/jiutiancv/JT-VL-Chat/tree/main"
            ],
            "Parameters": "2B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "China Mobile",
            "Time": "2025/11/10",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "JTVL-2B",
            "key": 529
        },
        {
            "Overall": 87.1,
            "AR": 88.6,
            "CP": 83.7,
            "FP-C": 85.0,
            "FP-S": 94.0,
            "LR": 82.6,
            "RR": 86.8,
            "action_recognition": 90.6,
            "attribute_comparison": 86.7,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 90.5,
            "function_reasoning": 94.4,
            "future_prediction": 84.0,
            "identity_reasoning": 96.1,
            "image_emotion": 82.2,
            "image_quality": 64.5,
            "image_scene": 91.7,
            "image_style": 84.8,
            "image_topic": 97.8,
            "nature_relation": 91.3,
            "object_localization": 93.3,
            "ocr": 97.8,
            "physical_property_reasoning": 74.7,
            "physical_relation": 76.0,
            "social_relation": 91.2,
            "spatial_relationship": 74.7,
            "structuralized_imagetext_understanding": 81.7,
            "Method": [
                "RBDashMM3-DPO-38B",
                "https://huggingface.co/RBDash-Team/RBDash-v2.0"
            ],
            "Parameters": "38B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "RBDash Team",
            "Time": "2025/11/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "rbdashmm3_DPO_38B_api",
            "key": 530
        },
        {
            "Overall": 83.6,
            "AR": 86.5,
            "CP": 79.8,
            "FP-C": 81.6,
            "FP-S": 91.2,
            "LR": 78.8,
            "RR": 81.4,
            "action_recognition": 88.0,
            "attribute_comparison": 82.7,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 88.4,
            "function_reasoning": 95.6,
            "future_prediction": 81.3,
            "identity_reasoning": 96.1,
            "image_emotion": 76.7,
            "image_quality": 61.3,
            "image_scene": 88.2,
            "image_style": 77.2,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 84.8,
            "ocr": 98.9,
            "physical_property_reasoning": 67.1,
            "physical_relation": 61.3,
            "social_relation": 85.7,
            "spatial_relationship": 70.7,
            "structuralized_imagetext_understanding": 77.1,
            "Method": [
                "Valley3",
                "https://huggingface.co/bytedance-research/Valley3"
            ],
            "Parameters": "9B",
            "Language Model": "Qwen3-8B",
            "Vision Model": "Qwen2-VL-ViT",
            "Org": "ByteDance",
            "Time": "2025/11/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "valley3",
            "key": 531
        },
        {
            "Overall": 79.8,
            "AR": 85.7,
            "CP": 79.4,
            "FP-C": 77.9,
            "FP-S": 86.3,
            "LR": 64.1,
            "RR": 77.1,
            "action_recognition": 87.2,
            "attribute_comparison": 88.0,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 79.6,
            "function_reasoning": 92.2,
            "future_prediction": 70.7,
            "identity_reasoning": 97.4,
            "image_emotion": 76.7,
            "image_quality": 56.5,
            "image_scene": 88.2,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 77.2,
            "object_localization": 80.0,
            "ocr": 94.4,
            "physical_property_reasoning": 67.1,
            "physical_relation": 66.7,
            "social_relation": 85.7,
            "spatial_relationship": 53.3,
            "structuralized_imagetext_understanding": 59.6,
            "Method": [
                "MiniCPM-V-4",
                "https://huggingface.co/openbmb/MiniCPM-V-4"
            ],
            "Parameters": "4.1B",
            "Language Model": "MiniCPM4-3B",
            "Vision Model": "SigLIP2-400M",
            "Org": "OpenBMB",
            "Time": "2025/11/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MiniCPM-V-4",
            "key": 532
        },
        {
            "Overall": 84.5,
            "AR": 85.7,
            "CP": 81.5,
            "FP-C": 85.0,
            "FP-S": 91.0,
            "LR": 82.1,
            "RR": 79.8,
            "action_recognition": 88.0,
            "attribute_comparison": 86.7,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 87.1,
            "function_reasoning": 93.3,
            "future_prediction": 77.3,
            "identity_reasoning": 96.1,
            "image_emotion": 78.9,
            "image_quality": 63.7,
            "image_scene": 88.2,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 89.1,
            "object_localization": 87.6,
            "ocr": 97.8,
            "physical_property_reasoning": 67.1,
            "physical_relation": 65.3,
            "social_relation": 82.4,
            "spatial_relationship": 78.7,
            "structuralized_imagetext_understanding": 85.3,
            "Method": [
                "MiniCPM-V-4_5",
                "https://huggingface.co/openbmb/MiniCPM-V-4_5"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen3-8B",
            "Vision Model": "SigLIP2-400M",
            "Org": "OpenBMB",
            "Time": "2025/11/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MiniCPM-V-4_5",
            "key": 533
        }
    ],
    "MMBench_TEST_CN_V11_Data": [
        {
            "Overall": 24.2,
            "AR": 33.1,
            "CP": 27.8,
            "FP-C": 19.5,
            "FP-S": 31.6,
            "LR": 11.4,
            "RR": 10.1,
            "action_recognition": 38.5,
            "attribute_comparison": 4.0,
            "attribute_recognition": 36.0,
            "celebrity_recognition": 42.9,
            "function_reasoning": 37.8,
            "future_prediction": 16.0,
            "identity_reasoning": 44.7,
            "image_emotion": 44.4,
            "image_quality": 0.0,
            "image_scene": 27.8,
            "image_style": 31.5,
            "image_topic": 45.6,
            "nature_relation": 3.3,
            "object_localization": 1.9,
            "ocr": 43.3,
            "physical_property_reasoning": 16.5,
            "physical_relation": 6.7,
            "social_relation": 19.8,
            "spatial_relationship": 5.3,
            "structuralized_imagetext_understanding": 8.3,
            "key": 23,
            "Method": [
                "Qwen-VL",
                "https://github.com/QwenLM/Qwen-VL"
            ],
            "Parameters": "9.6B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-G/16",
            "Org": "Alibaba",
            "Time": "2023/8/24",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 57.5,
            "AR": 74.7,
            "CP": 62.8,
            "FP-C": 41.6,
            "FP-S": 64.5,
            "LR": 35.9,
            "RR": 50.0,
            "action_recognition": 76.9,
            "attribute_comparison": 10.7,
            "attribute_recognition": 66.3,
            "celebrity_recognition": 86.4,
            "function_reasoning": 83.3,
            "future_prediction": 68.0,
            "identity_reasoning": 94.7,
            "image_emotion": 62.2,
            "image_quality": 15.3,
            "image_scene": 79.9,
            "image_style": 69.6,
            "image_topic": 94.4,
            "nature_relation": 52.2,
            "object_localization": 16.2,
            "ocr": 83.3,
            "physical_property_reasoning": 45.6,
            "physical_relation": 16.0,
            "social_relation": 75.8,
            "spatial_relationship": 17.3,
            "structuralized_imagetext_understanding": 13.8,
            "key": 24,
            "Method": [
                "Qwen-VL-Chat",
                "https://github.com/QwenLM/Qwen-VL"
            ],
            "Parameters": "9.6B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-G/16",
            "Org": "Alibaba",
            "Time": "2023/8/24",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 29.2,
            "AR": 50.2,
            "CP": 39.6,
            "FP-C": 12.4,
            "FP-S": 20.2,
            "LR": 12.5,
            "RR": 31.8,
            "action_recognition": 24.8,
            "attribute_comparison": 4.0,
            "attribute_recognition": 49.4,
            "celebrity_recognition": 16.3,
            "function_reasoning": 48.9,
            "future_prediction": 29.3,
            "identity_reasoning": 75.0,
            "image_emotion": 34.4,
            "image_quality": 13.7,
            "image_scene": 55.6,
            "image_style": 42.4,
            "image_topic": 52.2,
            "nature_relation": 32.6,
            "object_localization": 7.6,
            "ocr": 12.2,
            "physical_property_reasoning": 27.8,
            "physical_relation": 16.0,
            "social_relation": 44.0,
            "spatial_relationship": 1.3,
            "structuralized_imagetext_understanding": 0.9,
            "Method": [
                "PandaGPT-13B",
                "https://arxiv.org/abs/2305.16355"
            ],
            "Parameters": "14B",
            "Language Model": "Vicuna 13B",
            "Vision Model": "ImageBind ViT-H/14",
            "Org": "Tencent AI Lab",
            "Time": "2023/5/25",
            "key": 25,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 13.3,
            "AR": 19.2,
            "CP": 16.5,
            "FP-C": 9.0,
            "FP-S": 10.0,
            "LR": 11.4,
            "RR": 12.4,
            "action_recognition": 6.0,
            "attribute_comparison": 18.7,
            "attribute_recognition": 15.7,
            "celebrity_recognition": 17.0,
            "function_reasoning": 11.1,
            "future_prediction": 22.7,
            "identity_reasoning": 36.8,
            "image_emotion": 10.0,
            "image_quality": 11.3,
            "image_scene": 27.1,
            "image_style": 10.9,
            "image_topic": 18.9,
            "nature_relation": 14.1,
            "object_localization": 1.9,
            "ocr": 2.2,
            "physical_property_reasoning": 11.4,
            "physical_relation": 14.7,
            "social_relation": 8.8,
            "spatial_relationship": 4.0,
            "structuralized_imagetext_understanding": 3.7,
            "key": 1,
            "Method": [
                "OpenFlamingo v2",
                "https://github.com/mlfoundations/open_flamingo"
            ],
            "Parameters": "9B",
            "Language Model": "MPT 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "The University of Washington",
            "Time": "2023/6/28",
            "Verified": "No",
            "OpenSource": "Yes"
        },
        {
            "Overall": 58.6,
            "AR": 71.8,
            "CP": 67.4,
            "FP-C": 52.8,
            "FP-S": 57.8,
            "LR": 29.3,
            "RR": 56.2,
            "action_recognition": 83.8,
            "attribute_comparison": 34.7,
            "attribute_recognition": 68.5,
            "celebrity_recognition": 55.8,
            "function_reasoning": 80.0,
            "future_prediction": 56.0,
            "identity_reasoning": 93.4,
            "image_emotion": 75.6,
            "image_quality": 30.6,
            "image_scene": 83.3,
            "image_style": 59.8,
            "image_topic": 92.2,
            "nature_relation": 58.7,
            "object_localization": 33.3,
            "ocr": 78.9,
            "physical_property_reasoning": 41.8,
            "physical_relation": 36.0,
            "social_relation": 70.3,
            "spatial_relationship": 22.7,
            "structuralized_imagetext_understanding": 11.0,
            "Method": [
                "ShareGPT4V-7B",
                "https://sharegpt4v.github.io"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 184
        },
        {
            "Overall": 63.0,
            "AR": 75.1,
            "CP": 70.2,
            "FP-C": 56.2,
            "FP-S": 63.3,
            "LR": 37.5,
            "RR": 61.2,
            "action_recognition": 76.1,
            "attribute_comparison": 53.3,
            "attribute_recognition": 77.5,
            "celebrity_recognition": 58.5,
            "function_reasoning": 84.4,
            "future_prediction": 62.7,
            "identity_reasoning": 94.7,
            "image_emotion": 77.8,
            "image_quality": 36.3,
            "image_scene": 84.7,
            "image_style": 59.8,
            "image_topic": 96.7,
            "nature_relation": 54.3,
            "object_localization": 38.1,
            "ocr": 86.7,
            "physical_property_reasoning": 45.6,
            "physical_relation": 38.7,
            "social_relation": 86.8,
            "spatial_relationship": 28.0,
            "structuralized_imagetext_understanding": 20.2,
            "Method": [
                "ShareGPT4V-13B",
                "https://sharegpt4v.github.io"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 185
        },
        {
            "Overall": 67.9,
            "AR": 78.0,
            "CP": 72.0,
            "FP-C": 56.2,
            "FP-S": 73.5,
            "LR": 46.7,
            "RR": 67.8,
            "action_recognition": 78.6,
            "attribute_comparison": 50.7,
            "attribute_recognition": 78.7,
            "celebrity_recognition": 75.5,
            "function_reasoning": 87.8,
            "future_prediction": 77.3,
            "identity_reasoning": 96.1,
            "image_emotion": 73.3,
            "image_quality": 38.7,
            "image_scene": 86.8,
            "image_style": 69.6,
            "image_topic": 95.6,
            "nature_relation": 79.3,
            "object_localization": 53.3,
            "ocr": 88.9,
            "physical_property_reasoning": 49.4,
            "physical_relation": 34.7,
            "social_relation": 83.5,
            "spatial_relationship": 26.7,
            "structuralized_imagetext_understanding": 25.7,
            "Method": [
                "TransCore-M",
                "https://github.com/PCIResearch/TransCore-M"
            ],
            "Parameters": "13.4B",
            "Language Model": "PCITransGPT-13B",
            "Vision Model": "CLIP ViT/L-14",
            "Org": "PCI Research",
            "Time": "2024/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 236
        },
        {
            "Overall": 18.4,
            "AR": 30.6,
            "CP": 16.3,
            "FP-C": 9.7,
            "FP-S": 19.0,
            "LR": 10.3,
            "RR": 25.2,
            "action_recognition": 16.2,
            "attribute_comparison": 5.3,
            "attribute_recognition": 28.1,
            "celebrity_recognition": 15.6,
            "function_reasoning": 21.1,
            "future_prediction": 21.3,
            "identity_reasoning": 64.5,
            "image_emotion": 17.8,
            "image_quality": 0.0,
            "image_scene": 33.3,
            "image_style": 9.8,
            "image_topic": 16.7,
            "nature_relation": 13.0,
            "object_localization": 1.9,
            "ocr": 35.6,
            "physical_property_reasoning": 8.9,
            "physical_relation": 8.0,
            "social_relation": 51.6,
            "spatial_relationship": 4.0,
            "structuralized_imagetext_understanding": 2.8,
            "key": 7,
            "Method": [
                "InstructBLIP-7B",
                "https://arxiv.org/abs/2305.06500"
            ],
            "Parameters": "8B",
            "Language Model": "Vicuna 7B",
            "Vision Model": "EVA-G",
            "Org": "Salesforce Research",
            "Time": "2023/5/11",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 34.6,
            "AR": 44.1,
            "CP": 44.6,
            "FP-C": 22.5,
            "FP-S": 37.4,
            "LR": 16.3,
            "RR": 26.0,
            "action_recognition": 42.7,
            "attribute_comparison": 6.7,
            "attribute_recognition": 40.4,
            "celebrity_recognition": 40.1,
            "function_reasoning": 51.1,
            "future_prediction": 30.7,
            "identity_reasoning": 67.1,
            "image_emotion": 37.8,
            "image_quality": 8.1,
            "image_scene": 64.6,
            "image_style": 35.9,
            "image_topic": 78.9,
            "nature_relation": 18.5,
            "object_localization": 5.7,
            "ocr": 66.7,
            "physical_property_reasoning": 13.9,
            "physical_relation": 16.0,
            "social_relation": 41.8,
            "spatial_relationship": 6.7,
            "structuralized_imagetext_understanding": 6.4,
            "Method": [
                "VisualGLM",
                "https://github.com/THUDM/VisualGLM-6B"
            ],
            "Parameters": "8B",
            "Language Model": "ChatGLM 6B",
            "Vision Model": "EVA-CLIP",
            "Org": "Tsinghua University",
            "Time": "2023/5/17",
            "key": 41,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 58.0,
            "AR": 75.1,
            "CP": 64.4,
            "FP-C": 50.2,
            "FP-S": 57.1,
            "LR": 31.5,
            "RR": 56.6,
            "action_recognition": 76.9,
            "attribute_comparison": 34.7,
            "attribute_recognition": 64.0,
            "celebrity_recognition": 61.9,
            "function_reasoning": 78.9,
            "future_prediction": 58.7,
            "identity_reasoning": 100.0,
            "image_emotion": 73.3,
            "image_quality": 18.5,
            "image_scene": 81.9,
            "image_style": 64.1,
            "image_topic": 91.1,
            "nature_relation": 59.8,
            "object_localization": 23.8,
            "ocr": 81.1,
            "physical_property_reasoning": 46.8,
            "physical_relation": 22.7,
            "social_relation": 81.3,
            "spatial_relationship": 24.0,
            "structuralized_imagetext_understanding": 12.8,
            "Method": [
                "mPLUG-Owl2",
                "https://github.com/X-PLUG/mPLUG-Owl/tree/main/mPLUG-Owl2"
            ],
            "Parameters": "8.2B",
            "Language Model": "LLaMA2 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "DAMO Academy",
            "Time": "2023/11/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 32
        },
        {
            "Overall": 54.0,
            "AR": 67.8,
            "CP": 66.1,
            "FP-C": 47.6,
            "FP-S": 49.7,
            "LR": 26.1,
            "RR": 49.6,
            "action_recognition": 82.9,
            "attribute_comparison": 28.0,
            "attribute_recognition": 67.4,
            "celebrity_recognition": 48.3,
            "function_reasoning": 83.3,
            "future_prediction": 44.0,
            "identity_reasoning": 92.1,
            "image_emotion": 73.3,
            "image_quality": 24.2,
            "image_scene": 84.0,
            "image_style": 62.0,
            "image_topic": 92.2,
            "nature_relation": 52.2,
            "object_localization": 8.6,
            "ocr": 82.2,
            "physical_property_reasoning": 26.6,
            "physical_relation": 17.3,
            "social_relation": 73.6,
            "spatial_relationship": 12.0,
            "structuralized_imagetext_understanding": 13.8,
            "Method": [
                "CogVLM-17B-Chat",
                "https://huggingface.co/THUDM/cogvlm-chat-hf"
            ],
            "Parameters": "17B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "EVA2-CLIP-E",
            "Org": "Zhipu AI",
            "Time": "2024/01/03",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 75
        },
        {
            "Overall": 57.8,
            "AR": 74.3,
            "CP": 57.6,
            "FP-C": 50.9,
            "FP-S": 68.0,
            "LR": 25.5,
            "RR": 55.4,
            "action_recognition": 69.2,
            "attribute_comparison": 50.7,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 72.1,
            "function_reasoning": 78.9,
            "future_prediction": 48.0,
            "identity_reasoning": 94.7,
            "image_emotion": 52.2,
            "image_quality": 47.6,
            "image_scene": 66.0,
            "image_style": 25.0,
            "image_topic": 96.7,
            "nature_relation": 76.1,
            "object_localization": 42.9,
            "ocr": 78.9,
            "physical_property_reasoning": 49.4,
            "physical_relation": 30.7,
            "social_relation": 54.9,
            "spatial_relationship": 22.7,
            "structuralized_imagetext_understanding": 10.1,
            "Method": [
                "ShareCaptioner",
                "https://huggingface.co/Lin-Chen/ShareCaptioner/"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM-7B",
            "Vision Model": "EVA-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 245
        },
        {
            "Overall": 52.5,
            "AR": 72.7,
            "CP": 58.9,
            "FP-C": 35.2,
            "FP-S": 57.8,
            "LR": 29.3,
            "RR": 45.7,
            "action_recognition": 69.2,
            "attribute_comparison": 8.0,
            "attribute_recognition": 70.8,
            "celebrity_recognition": 76.9,
            "function_reasoning": 74.4,
            "future_prediction": 58.7,
            "identity_reasoning": 94.7,
            "image_emotion": 63.3,
            "image_quality": 8.1,
            "image_scene": 77.1,
            "image_style": 58.7,
            "image_topic": 95.6,
            "nature_relation": 48.9,
            "object_localization": 8.6,
            "ocr": 71.1,
            "physical_property_reasoning": 49.4,
            "physical_relation": 16.0,
            "social_relation": 67.0,
            "spatial_relationship": 9.3,
            "structuralized_imagetext_understanding": 9.2,
            "Method": [
                "Monkey",
                "https://github.com/Yuliang-Liu/Monkey"
            ],
            "Parameters": "9.8B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-BigHuge",
            "Org": "Huazhong University of Science and Technology",
            "Time": "2024/01/11",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 79
        },
        {
            "Overall": 65.1,
            "AR": 80.0,
            "CP": 71.5,
            "FP-C": 52.1,
            "FP-S": 68.9,
            "LR": 47.3,
            "RR": 57.4,
            "action_recognition": 83.8,
            "attribute_comparison": 28.0,
            "attribute_recognition": 75.3,
            "celebrity_recognition": 87.8,
            "function_reasoning": 86.7,
            "future_prediction": 78.7,
            "identity_reasoning": 97.4,
            "image_emotion": 77.8,
            "image_quality": 29.0,
            "image_scene": 87.5,
            "image_style": 72.8,
            "image_topic": 96.7,
            "nature_relation": 60.9,
            "object_localization": 23.8,
            "ocr": 84.4,
            "physical_property_reasoning": 55.7,
            "physical_relation": 26.7,
            "social_relation": 79.1,
            "spatial_relationship": 26.7,
            "structuralized_imagetext_understanding": 25.7,
            "Method": [
                "Monkey-Chat",
                "https://github.com/Yuliang-Liu/Monkey"
            ],
            "Parameters": "9.8B",
            "Language Model": "Qwen-7B",
            "Vision Model": "ViT-BigHuge",
            "Org": "Huazhong University of Science and Technology",
            "Time": "2024/01/16",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 97
        },
        {
            "Overall": 1.4,
            "AR": 4.1,
            "CP": 0.7,
            "FP-C": 0.7,
            "FP-S": 0.7,
            "LR": 0.5,
            "RR": 2.3,
            "action_recognition": 0.9,
            "attribute_comparison": 0.0,
            "attribute_recognition": 2.2,
            "celebrity_recognition": 0.7,
            "function_reasoning": 1.1,
            "future_prediction": 0.0,
            "identity_reasoning": 3.9,
            "image_emotion": 0.0,
            "image_quality": 1.6,
            "image_scene": 0.7,
            "image_style": 1.1,
            "image_topic": 0.0,
            "nature_relation": 5.4,
            "object_localization": 0.0,
            "ocr": 0.0,
            "physical_property_reasoning": 7.6,
            "physical_relation": 0.0,
            "social_relation": 1.1,
            "spatial_relationship": 1.3,
            "structuralized_imagetext_understanding": 0.9,
            "Method": [
                "MiniGPT-4-v2",
                "https://minigpt-v2.github.io"
            ],
            "Parameters": "8B",
            "Language Model": "LLaMA2 13B",
            "Vision Model": "EVA-G",
            "Org": "King Abdullah University of Science and Technology",
            "Time": "2023/10/27",
            "key": 31,
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 10.7,
            "AR": 24.5,
            "CP": 9.3,
            "FP-C": 5.2,
            "FP-S": 11.8,
            "LR": 4.9,
            "RR": 8.5,
            "action_recognition": 11.1,
            "attribute_comparison": 0.0,
            "attribute_recognition": 6.7,
            "celebrity_recognition": 8.8,
            "function_reasoning": 14.4,
            "future_prediction": 8.0,
            "identity_reasoning": 36.8,
            "image_emotion": 4.4,
            "image_quality": 3.2,
            "image_scene": 21.5,
            "image_style": 8.7,
            "image_topic": 3.3,
            "nature_relation": 15.2,
            "object_localization": 2.9,
            "ocr": 32.2,
            "physical_property_reasoning": 24.1,
            "physical_relation": 1.3,
            "social_relation": 7.7,
            "spatial_relationship": 1.3,
            "structuralized_imagetext_understanding": 2.8,
            "key": 3,
            "Method": [
                "MiniGPT-4-v1-7B",
                "https://arxiv.org/abs/2304.10592"
            ],
            "Parameters": "8B",
            "Language Model": "Vicuna 7B",
            "Vision Model": "EVA-G",
            "Org": "King Abdullah University of Science and Technology",
            "Time": "2023/4/20",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 44.3,
            "AR": 53.5,
            "CP": 53.9,
            "FP-C": 42.3,
            "FP-S": 38.1,
            "LR": 20.1,
            "RR": 45.3,
            "action_recognition": 76.1,
            "attribute_comparison": 17.3,
            "attribute_recognition": 36.0,
            "celebrity_recognition": 32.7,
            "function_reasoning": 57.8,
            "future_prediction": 41.3,
            "identity_reasoning": 84.2,
            "image_emotion": 60.0,
            "image_quality": 9.7,
            "image_scene": 78.5,
            "image_style": 34.8,
            "image_topic": 88.9,
            "nature_relation": 58.7,
            "object_localization": 14.3,
            "ocr": 76.7,
            "physical_property_reasoning": 19.0,
            "physical_relation": 10.7,
            "social_relation": 60.4,
            "spatial_relationship": 14.7,
            "structuralized_imagetext_understanding": 5.5,
            "Method": [
                "Emu2_chat",
                "https://github.com/baaivision/Emu/tree/main/Emu2"
            ],
            "Parameters": "37B",
            "Language Model": "LLaMA-33B",
            "Vision Model": "EVA-02-CLIP-E-plus",
            "Org": "Beijing Academy of Artificial Intelligence",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 86
        },
        {
            "Overall": 63.1,
            "AR": 75.1,
            "CP": 69.1,
            "FP-C": 52.1,
            "FP-S": 71.9,
            "LR": 36.4,
            "RR": 55.0,
            "action_recognition": 75.2,
            "attribute_comparison": 40.0,
            "attribute_recognition": 76.4,
            "celebrity_recognition": 80.3,
            "function_reasoning": 81.1,
            "future_prediction": 61.3,
            "identity_reasoning": 96.1,
            "image_emotion": 70.0,
            "image_quality": 26.6,
            "image_scene": 88.9,
            "image_style": 66.3,
            "image_topic": 97.8,
            "nature_relation": 50.0,
            "object_localization": 44.8,
            "ocr": 85.6,
            "physical_property_reasoning": 48.1,
            "physical_relation": 34.7,
            "social_relation": 76.9,
            "spatial_relationship": 28.0,
            "structuralized_imagetext_understanding": 19.3,
            "Method": [
                "Yi-VL-6B",
                "https://huggingface.co/01-ai/Yi-VL-6B"
            ],
            "Parameters": "6.6B",
            "Language Model": "Yi-6B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "01-AI",
            "Time": "2024/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 189
        },
        {
            "Overall": 66.8,
            "AR": 80.8,
            "CP": 70.0,
            "FP-C": 56.6,
            "FP-S": 75.6,
            "LR": 38.0,
            "RR": 62.8,
            "action_recognition": 76.1,
            "attribute_comparison": 46.7,
            "attribute_recognition": 82.0,
            "celebrity_recognition": 78.9,
            "function_reasoning": 90.0,
            "future_prediction": 64.0,
            "identity_reasoning": 96.1,
            "image_emotion": 68.9,
            "image_quality": 42.7,
            "image_scene": 77.8,
            "image_style": 69.6,
            "image_topic": 96.7,
            "nature_relation": 71.7,
            "object_localization": 51.4,
            "ocr": 92.2,
            "physical_property_reasoning": 55.7,
            "physical_relation": 38.7,
            "social_relation": 73.6,
            "spatial_relationship": 36.0,
            "structuralized_imagetext_understanding": 20.2,
            "Method": [
                "Yi-VL-34B",
                "https://huggingface.co/01-ai/Yi-VL-34B"
            ],
            "Parameters": "34.6B",
            "Language Model": "Yi-34B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "01-AI",
            "Time": "2024/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 190
        },
        {
            "Overall": 56.6,
            "AR": 75.5,
            "CP": 63.7,
            "FP-C": 53.9,
            "FP-S": 51.5,
            "LR": 29.9,
            "RR": 54.3,
            "action_recognition": 82.9,
            "attribute_comparison": 38.7,
            "attribute_recognition": 66.3,
            "celebrity_recognition": 56.5,
            "function_reasoning": 72.2,
            "future_prediction": 57.3,
            "identity_reasoning": 94.7,
            "image_emotion": 75.6,
            "image_quality": 14.5,
            "image_scene": 83.3,
            "image_style": 59.8,
            "image_topic": 92.2,
            "nature_relation": 62.0,
            "object_localization": 26.7,
            "ocr": 57.8,
            "physical_property_reasoning": 60.8,
            "physical_relation": 26.7,
            "social_relation": 69.2,
            "spatial_relationship": 24.0,
            "structuralized_imagetext_understanding": 11.0,
            "Method": [
                "MMAlaya",
                "https://huggingface.co/DataCanvas/MMAlaya"
            ],
            "Parameters": "7.8B",
            "Language Model": "Alaya-7B-Chat",
            "Vision Model": "EVA-G",
            "Org": "DataCanvas",
            "Time": "2024/01/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 134
        },
        {
            "Overall": 59.4,
            "AR": 72.7,
            "CP": 62.4,
            "FP-C": 53.2,
            "FP-S": 66.8,
            "LR": 29.9,
            "RR": 55.8,
            "action_recognition": 88.0,
            "attribute_comparison": 34.7,
            "attribute_recognition": 76.4,
            "celebrity_recognition": 62.6,
            "function_reasoning": 84.4,
            "future_prediction": 49.3,
            "identity_reasoning": 97.4,
            "image_emotion": 70.0,
            "image_quality": 13.7,
            "image_scene": 81.9,
            "image_style": 58.7,
            "image_topic": 94.4,
            "nature_relation": 53.3,
            "object_localization": 47.6,
            "ocr": 86.7,
            "physical_property_reasoning": 35.4,
            "physical_relation": 32.0,
            "social_relation": 78.0,
            "spatial_relationship": 17.3,
            "structuralized_imagetext_understanding": 16.5,
            "Method": [
                "OmniLMM-12B",
                "https://huggingface.co/openbmb/OmniLMM-12B"
            ],
            "Parameters": "12B",
            "Language Model": "Zephyr-7B-β",
            "Vision Model": "EVA-02-5B",
            "Org": "OpenBMB",
            "Time": "2024/02/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 145
        },
        {
            "Overall": 59.6,
            "AR": 69.0,
            "CP": 64.8,
            "FP-C": 52.8,
            "FP-S": 66.6,
            "LR": 33.2,
            "RR": 54.3,
            "action_recognition": 83.8,
            "attribute_comparison": 37.3,
            "attribute_recognition": 78.7,
            "celebrity_recognition": 73.5,
            "function_reasoning": 90.0,
            "future_prediction": 56.0,
            "identity_reasoning": 97.4,
            "image_emotion": 68.9,
            "image_quality": 13.7,
            "image_scene": 85.4,
            "image_style": 66.3,
            "image_topic": 96.7,
            "nature_relation": 58.7,
            "object_localization": 30.5,
            "ocr": 85.6,
            "physical_property_reasoning": 17.7,
            "physical_relation": 21.3,
            "social_relation": 76.9,
            "spatial_relationship": 20.0,
            "structuralized_imagetext_understanding": 17.4,
            "Method": [
                "MiniCPM-V",
                "https://huggingface.co/openbmb/MiniCPM-V"
            ],
            "Parameters": "3B",
            "Language Model": "MiniCPM-2.4B",
            "Vision Model": "SigLip-400M",
            "Org": "OpenBMB",
            "Time": "2024/02/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 146
        },
        {
            "Overall": 64.5,
            "AR": 78.8,
            "CP": 67.4,
            "FP-C": 56.6,
            "FP-S": 68.9,
            "LR": 40.8,
            "RR": 62.8,
            "action_recognition": 87.2,
            "attribute_comparison": 42.7,
            "attribute_recognition": 83.1,
            "celebrity_recognition": 77.6,
            "function_reasoning": 90.0,
            "future_prediction": 64.0,
            "identity_reasoning": 94.7,
            "image_emotion": 75.6,
            "image_quality": 15.3,
            "image_scene": 86.8,
            "image_style": 71.7,
            "image_topic": 95.6,
            "nature_relation": 70.7,
            "object_localization": 29.5,
            "ocr": 86.7,
            "physical_property_reasoning": 50.6,
            "physical_relation": 38.7,
            "social_relation": 74.7,
            "spatial_relationship": 22.7,
            "structuralized_imagetext_understanding": 24.8,
            "Method": [
                "MiniCPM-V-2",
                "https://huggingface.co/openbmb/MiniCPM-V-2"
            ],
            "Parameters": "2.8B",
            "Vision Model": "SigLip-400M",
            "Language Model": "MiniCPM-2.4B",
            "Org": "OpenBMB",
            "Time": "2024/04/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 231
        },
        {
            "Overall": 61.9,
            "AR": 80.0,
            "CP": 70.9,
            "FP-C": 53.2,
            "FP-S": 64.0,
            "LR": 31.5,
            "RR": 53.1,
            "action_recognition": 85.5,
            "attribute_comparison": 37.3,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 59.2,
            "function_reasoning": 84.4,
            "future_prediction": 60.0,
            "identity_reasoning": 96.1,
            "image_emotion": 82.2,
            "image_quality": 29.0,
            "image_scene": 88.2,
            "image_style": 64.1,
            "image_topic": 96.7,
            "nature_relation": 45.7,
            "object_localization": 44.8,
            "ocr": 78.9,
            "physical_property_reasoning": 59.5,
            "physical_relation": 34.7,
            "social_relation": 75.8,
            "spatial_relationship": 18.7,
            "structuralized_imagetext_understanding": 11.9,
            "Method": [
                "DeepSeek-VL-1.3B",
                "https://github.com/deepseek-ai/DeepSeek-VL"
            ],
            "Parameters": "2.0B",
            "Language Model": "DeekSeek-1B",
            "Vision Model": "SAM-B\nSigLIP-L",
            "Org": "DeepSeek",
            "Time": "2024/03/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 201
        },
        {
            "Overall": 69.7,
            "AR": 79.2,
            "CP": 74.8,
            "FP-C": 62.2,
            "FP-S": 73.8,
            "LR": 45.1,
            "RR": 68.6,
            "action_recognition": 86.3,
            "attribute_comparison": 60.0,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 74.8,
            "function_reasoning": 88.9,
            "future_prediction": 69.3,
            "identity_reasoning": 98.7,
            "image_emotion": 82.2,
            "image_quality": 38.7,
            "image_scene": 86.8,
            "image_style": 76.1,
            "image_topic": 96.7,
            "nature_relation": 72.8,
            "object_localization": 46.7,
            "ocr": 90.0,
            "physical_property_reasoning": 49.4,
            "physical_relation": 40.0,
            "social_relation": 87.9,
            "spatial_relationship": 26.7,
            "structuralized_imagetext_understanding": 28.4,
            "Method": [
                "DeepSeek-VL-7B",
                "https://github.com/deepseek-ai/DeepSeek-VL"
            ],
            "Parameters": "7.3B",
            "Language Model": "DeekSeek-7B",
            "Vision Model": "SAM-B\nSigLIP-L",
            "Org": "DeepSeek",
            "Time": "2024/03/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 202
        },
        {
            "Overall": 60.5,
            "AR": 73.1,
            "CP": 67.6,
            "FP-C": 46.8,
            "FP-S": 66.6,
            "LR": 31.0,
            "RR": 58.9,
            "action_recognition": 82.1,
            "attribute_comparison": 13.3,
            "attribute_recognition": 76.4,
            "celebrity_recognition": 67.3,
            "function_reasoning": 83.3,
            "future_prediction": 45.3,
            "identity_reasoning": 98.7,
            "image_emotion": 82.2,
            "image_quality": 9.7,
            "image_scene": 86.8,
            "image_style": 72.8,
            "image_topic": 96.7,
            "nature_relation": 65.2,
            "object_localization": 51.4,
            "ocr": 73.3,
            "physical_property_reasoning": 36.7,
            "physical_relation": 38.7,
            "social_relation": 69.2,
            "spatial_relationship": 25.3,
            "structuralized_imagetext_understanding": 21.1,
            "Method": [
                "XVERSE-V-13B",
                "https://github.com/xverse-ai/XVERSE-V-13B"
            ],
            "Parameters": "13B",
            "Language Model": "XVERSE-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "XVERSE",
            "Time": "2024/05/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 256
        },
        {
            "Overall": 73.9,
            "AR": 84.9,
            "CP": 73.9,
            "FP-C": 67.8,
            "FP-S": 82.1,
            "LR": 48.9,
            "RR": 73.6,
            "action_recognition": 78.6,
            "attribute_comparison": 57.3,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 78.2,
            "function_reasoning": 86.7,
            "future_prediction": 80.0,
            "identity_reasoning": 97.4,
            "image_emotion": 81.1,
            "image_quality": 40.3,
            "image_scene": 86.1,
            "image_style": 70.7,
            "image_topic": 96.7,
            "nature_relation": 84.8,
            "object_localization": 76.2,
            "ocr": 91.1,
            "physical_property_reasoning": 70.9,
            "physical_relation": 60.0,
            "social_relation": 73.6,
            "spatial_relationship": 61.3,
            "structuralized_imagetext_understanding": 27.5,
            "Method": [
                "360VL-70B",
                "https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5"
            ],
            "Parameters": "70B",
            "Language Model": "Llama-3-70B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "QiHoo360",
            "Time": "2024/05/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 264
        },
        {
            "Overall": 70.1,
            "AR": 80.0,
            "CP": 74.1,
            "FP-C": 58.4,
            "FP-S": 78.9,
            "LR": 52.2,
            "RR": 62.8,
            "action_recognition": 80.3,
            "attribute_comparison": 54.7,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 78.2,
            "function_reasoning": 91.1,
            "future_prediction": 65.3,
            "identity_reasoning": 97.4,
            "image_emotion": 72.2,
            "image_quality": 41.9,
            "image_scene": 85.4,
            "image_style": 77.2,
            "image_topic": 98.9,
            "nature_relation": 67.4,
            "object_localization": 60.0,
            "ocr": 90.0,
            "physical_property_reasoning": 50.6,
            "physical_relation": 36.0,
            "social_relation": 80.2,
            "spatial_relationship": 28.0,
            "structuralized_imagetext_understanding": 43.1,
            "Method": [
                "MiniCPM-Llama3-V2.5",
                "https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLip-400M",
            "Org": "OpenBMB",
            "Time": "2024/05/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 265
        },
        {
            "Overall": 59.8,
            "AR": 71.8,
            "CP": 68.7,
            "FP-C": 50.9,
            "FP-S": 56.1,
            "LR": 46.7,
            "RR": 54.7,
            "action_recognition": 74.4,
            "attribute_comparison": 37.3,
            "attribute_recognition": 62.9,
            "celebrity_recognition": 44.9,
            "function_reasoning": 73.3,
            "future_prediction": 52.0,
            "identity_reasoning": 92.1,
            "image_emotion": 73.3,
            "image_quality": 39.5,
            "image_scene": 81.9,
            "image_style": 56.5,
            "image_topic": 95.6,
            "nature_relation": 50.0,
            "object_localization": 41.9,
            "ocr": 84.4,
            "physical_property_reasoning": 50.6,
            "physical_relation": 40.0,
            "social_relation": 71.4,
            "spatial_relationship": 28.0,
            "structuralized_imagetext_understanding": 43.1,
            "Method": [
                "Phi-3-Vision",
                "https://huggingface.co/microsoft/Phi-3-vision-128k-instruct"
            ],
            "Parameters": "4.2B",
            "Language Model": "Phi-3",
            "Vision Model": "CLIP ViT/L-14",
            "Org": "Microsoft",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 268
        },
        {
            "Overall": 68.6,
            "AR": 75.1,
            "CP": 70.9,
            "FP-C": 64.8,
            "FP-S": 72.2,
            "LR": 50.5,
            "RR": 68.6,
            "action_recognition": 89.7,
            "attribute_comparison": 56.0,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 79.6,
            "function_reasoning": 84.4,
            "future_prediction": 65.3,
            "identity_reasoning": 97.4,
            "image_emotion": 72.2,
            "image_quality": 38.7,
            "image_scene": 80.6,
            "image_style": 72.8,
            "image_topic": 96.7,
            "nature_relation": 81.5,
            "object_localization": 37.1,
            "ocr": 87.8,
            "physical_property_reasoning": 43.0,
            "physical_relation": 34.7,
            "social_relation": 83.5,
            "spatial_relationship": 34.7,
            "structuralized_imagetext_understanding": 40.4,
            "Method": [
                "CogVLM2-19B-Chat",
                "https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B"
            ],
            "Parameters": "19B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "EVA2-CLIP-E",
            "Org": "Zhipu AI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 269
        },
        {
            "Overall": 73.6,
            "AR": 79.6,
            "CP": 79.1,
            "FP-C": 66.3,
            "FP-S": 77.7,
            "LR": 57.6,
            "RR": 68.2,
            "action_recognition": 82.1,
            "attribute_comparison": 65.3,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 76.2,
            "function_reasoning": 90.0,
            "future_prediction": 69.3,
            "identity_reasoning": 94.7,
            "image_emotion": 77.8,
            "image_quality": 52.4,
            "image_scene": 89.6,
            "image_style": 82.6,
            "image_topic": 96.7,
            "nature_relation": 68.5,
            "object_localization": 69.5,
            "ocr": 81.1,
            "physical_property_reasoning": 53.2,
            "physical_relation": 46.7,
            "social_relation": 85.7,
            "spatial_relationship": 42.7,
            "structuralized_imagetext_understanding": 49.5,
            "Method": [
                "WeMM",
                "https://github.com/scenarios/WeMM/tree/main"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "SigLip-400M",
            "Org": "WechatCV",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 273
        },
        {
            "Overall": 19.5,
            "AR": 35.5,
            "CP": 22.2,
            "FP-C": 7.1,
            "FP-S": 17.6,
            "LR": 6.0,
            "RR": 24.4,
            "action_recognition": 9.4,
            "attribute_comparison": 10.7,
            "attribute_recognition": 23.6,
            "celebrity_recognition": 13.6,
            "function_reasoning": 34.4,
            "future_prediction": 13.3,
            "identity_reasoning": 60.5,
            "image_emotion": 41.1,
            "image_quality": 5.6,
            "image_scene": 31.2,
            "image_style": 30.4,
            "image_topic": 3.3,
            "nature_relation": 17.4,
            "object_localization": 3.8,
            "ocr": 34.4,
            "physical_property_reasoning": 12.7,
            "physical_relation": 9.3,
            "social_relation": 44.0,
            "spatial_relationship": 0.0,
            "structuralized_imagetext_understanding": 0.9,
            "key": 18,
            "Method": [
                "IDEFICS-9B-Instruct",
                "https://huggingface.co/HuggingFaceM4/idefics-9b-instruct"
            ],
            "Language Model": "LLaMA 7B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "Hugging Face",
            "Time": "2023/7/25",
            "Parameters": "9B",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 44.4,
            "AR": 59.6,
            "CP": 54.8,
            "FP-C": 42.3,
            "FP-S": 37.1,
            "LR": 17.4,
            "RR": 41.9,
            "action_recognition": 75.2,
            "attribute_comparison": 20.0,
            "attribute_recognition": 34.8,
            "celebrity_recognition": 38.8,
            "function_reasoning": 74.4,
            "future_prediction": 38.7,
            "identity_reasoning": 89.5,
            "image_emotion": 63.3,
            "image_quality": 6.5,
            "image_scene": 75.7,
            "image_style": 46.7,
            "image_topic": 87.8,
            "nature_relation": 41.3,
            "object_localization": 10.5,
            "ocr": 67.8,
            "physical_property_reasoning": 13.9,
            "physical_relation": 10.7,
            "social_relation": 68.1,
            "spatial_relationship": 13.3,
            "structuralized_imagetext_understanding": 2.8,
            "key": 19,
            "Method": [
                "IDEFICS-80B-Instruct",
                "https://huggingface.co/HuggingFaceM4/idefics-80b-instruct"
            ],
            "Language Model": "LLaMA65B",
            "Vision Model": "CLIP ViT-H/14",
            "Org": "Hugging Face",
            "Time": "2023/7/25",
            "Parameters": "80B",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 65.1,
            "AR": 82.0,
            "CP": 70.0,
            "FP-C": 59.9,
            "FP-S": 67.5,
            "LR": 42.9,
            "RR": 55.8,
            "action_recognition": 85.5,
            "attribute_comparison": 58.7,
            "attribute_recognition": 77.5,
            "celebrity_recognition": 69.4,
            "function_reasoning": 87.8,
            "future_prediction": 60.0,
            "identity_reasoning": 94.7,
            "image_emotion": 77.8,
            "image_quality": 35.5,
            "image_scene": 84.0,
            "image_style": 60.9,
            "image_topic": 96.7,
            "nature_relation": 57.6,
            "object_localization": 39.0,
            "ocr": 87.8,
            "physical_property_reasoning": 63.3,
            "physical_relation": 26.7,
            "social_relation": 78.0,
            "spatial_relationship": 21.3,
            "structuralized_imagetext_understanding": 31.2,
            "Method": [
                "IDEFICS2-8B",
                "https://huggingface.co/HuggingFaceM4/idefics2-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Mistral-7B",
            "Vision Model": "SigLip-400M",
            "Org": "Hugging Face",
            "Time": "2024/04/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 248
        },
        {
            "Overall": 45.5,
            "AR": 56.3,
            "CP": 48.5,
            "FP-C": 37.1,
            "FP-S": 43.6,
            "LR": 23.9,
            "RR": 56.2,
            "action_recognition": 60.7,
            "attribute_comparison": 20.0,
            "attribute_recognition": 50.6,
            "celebrity_recognition": 62.6,
            "function_reasoning": 62.2,
            "future_prediction": 48.0,
            "identity_reasoning": 67.1,
            "image_emotion": 36.7,
            "image_quality": 24.2,
            "image_scene": 61.8,
            "image_style": 56.5,
            "image_topic": 64.4,
            "nature_relation": 60.9,
            "object_localization": 33.3,
            "ocr": 17.8,
            "physical_property_reasoning": 39.2,
            "physical_relation": 24.0,
            "social_relation": 78.0,
            "spatial_relationship": 17.3,
            "structuralized_imagetext_understanding": 7.3,
            "key": 22,
            "Method": [
                "InternLM-XComposer",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM-7B",
            "Vision Model": "EVA-G",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/9/26",
            "Verified": "Yes",
            "OpenSource": "Yes"
        },
        {
            "Overall": 77.1,
            "AR": 88.2,
            "CP": 80.4,
            "FP-C": 71.2,
            "FP-S": 82.8,
            "LR": 55.4,
            "RR": 72.1,
            "action_recognition": 82.9,
            "attribute_comparison": 77.3,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 80.3,
            "function_reasoning": 90.0,
            "future_prediction": 65.3,
            "identity_reasoning": 97.4,
            "image_emotion": 81.1,
            "image_quality": 61.3,
            "image_scene": 91.0,
            "image_style": 71.7,
            "image_topic": 97.8,
            "nature_relation": 78.3,
            "object_localization": 76.2,
            "ocr": 87.8,
            "physical_property_reasoning": 77.2,
            "physical_relation": 53.3,
            "social_relation": 81.3,
            "spatial_relationship": 46.7,
            "structuralized_imagetext_understanding": 48.6,
            "Method": [
                "InternLM-XComposer2",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 132
        },
        {
            "Overall": 66.8,
            "AR": 76.3,
            "CP": 73.0,
            "FP-C": 60.3,
            "FP-S": 65.4,
            "LR": 45.1,
            "RR": 69.0,
            "action_recognition": 82.9,
            "attribute_comparison": 56.0,
            "attribute_recognition": 73.0,
            "celebrity_recognition": 63.3,
            "function_reasoning": 78.9,
            "future_prediction": 61.3,
            "identity_reasoning": 92.1,
            "image_emotion": 77.8,
            "image_quality": 46.0,
            "image_scene": 84.7,
            "image_style": 60.9,
            "image_topic": 98.9,
            "nature_relation": 71.7,
            "object_localization": 46.7,
            "ocr": 83.3,
            "physical_property_reasoning": 58.2,
            "physical_relation": 60.0,
            "social_relation": 73.6,
            "spatial_relationship": 29.3,
            "structuralized_imagetext_understanding": 33.9,
            "Method": [
                "InternLM-XComposer2-1.8B",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 275
        },
        {
            "Overall": 76.1,
            "AR": 85.7,
            "CP": 78.0,
            "FP-C": 65.2,
            "FP-S": 81.4,
            "LR": 65.8,
            "RR": 72.5,
            "action_recognition": 79.5,
            "attribute_comparison": 68.0,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 78.9,
            "function_reasoning": 87.8,
            "future_prediction": 76.0,
            "identity_reasoning": 97.4,
            "image_emotion": 77.8,
            "image_quality": 58.1,
            "image_scene": 88.9,
            "image_style": 69.6,
            "image_topic": 96.7,
            "nature_relation": 76.1,
            "object_localization": 74.3,
            "ocr": 88.9,
            "physical_property_reasoning": 72.2,
            "physical_relation": 56.0,
            "social_relation": 82.4,
            "spatial_relationship": 40.0,
            "structuralized_imagetext_understanding": 58.7,
            "Method": [
                "InternLM-XComposer2-4KHD",
                "https://github.com/InternLM/InternLM-XComposer"
            ],
            "Parameters": "7B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/06/09",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 276
        },
        {
            "Overall": 79.1,
            "AR": 86.1,
            "CP": 79.4,
            "FP-C": 75.3,
            "FP-S": 84.5,
            "LR": 65.8,
            "RR": 76.4,
            "action_recognition": 92.3,
            "attribute_comparison": 77.3,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 83.0,
            "function_reasoning": 90.0,
            "future_prediction": 80.0,
            "identity_reasoning": 98.7,
            "image_emotion": 80.0,
            "image_quality": 58.9,
            "image_scene": 85.4,
            "image_style": 79.3,
            "image_topic": 97.8,
            "nature_relation": 79.3,
            "object_localization": 73.3,
            "ocr": 91.1,
            "physical_property_reasoning": 69.6,
            "physical_relation": 65.3,
            "social_relation": 82.4,
            "spatial_relationship": 46.7,
            "structuralized_imagetext_understanding": 56.0,
            "Method": [
                "InternVL-Chat-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/04/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 241
        },
        {
            "Overall": 35.8,
            "AR": 50.6,
            "CP": 48.0,
            "FP-C": 25.1,
            "FP-S": 37.4,
            "LR": 8.7,
            "RR": 24.4,
            "action_recognition": 41.9,
            "attribute_comparison": 9.3,
            "attribute_recognition": 40.4,
            "celebrity_recognition": 38.8,
            "function_reasoning": 41.1,
            "future_prediction": 20.0,
            "identity_reasoning": 76.3,
            "image_emotion": 50.0,
            "image_quality": 15.3,
            "image_scene": 62.5,
            "image_style": 37.0,
            "image_topic": 78.9,
            "nature_relation": 16.3,
            "object_localization": 13.3,
            "ocr": 60.0,
            "physical_property_reasoning": 36.7,
            "physical_relation": 13.3,
            "social_relation": 41.8,
            "spatial_relationship": 14.7,
            "structuralized_imagetext_understanding": 0.9,
            "Method": [
                "LLaVA-v1-7B",
                "https://arxiv.org/abs/2304.08485"
            ],
            "Parameters": "7.2B",
            "Language Model": "LLaMA 7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin-Madison",
            "Time": "2023/4/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 187
        },
        {
            "Overall": 64.1,
            "AR": 75.5,
            "CP": 70.7,
            "FP-C": 55.8,
            "FP-S": 63.8,
            "LR": 40.2,
            "RR": 65.5,
            "action_recognition": 85.5,
            "attribute_comparison": 37.3,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 63.9,
            "function_reasoning": 83.3,
            "future_prediction": 68.0,
            "identity_reasoning": 96.1,
            "image_emotion": 81.1,
            "image_quality": 31.5,
            "image_scene": 86.1,
            "image_style": 64.1,
            "image_topic": 96.7,
            "nature_relation": 79.3,
            "object_localization": 30.5,
            "ocr": 86.7,
            "physical_property_reasoning": 46.8,
            "physical_relation": 33.3,
            "social_relation": 78.0,
            "spatial_relationship": 28.0,
            "structuralized_imagetext_understanding": 21.1,
            "Method": [
                "LLaVA-InternLM-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "7.6B",
            "Language Model": "InternLM-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 70
        },
        {
            "Overall": 59.5,
            "AR": 73.9,
            "CP": 68.3,
            "FP-C": 58.1,
            "FP-S": 56.6,
            "LR": 32.1,
            "RR": 53.5,
            "action_recognition": 81.2,
            "attribute_comparison": 54.7,
            "attribute_recognition": 60.7,
            "celebrity_recognition": 54.4,
            "function_reasoning": 81.1,
            "future_prediction": 62.7,
            "identity_reasoning": 94.7,
            "image_emotion": 80.0,
            "image_quality": 34.7,
            "image_scene": 82.6,
            "image_style": 56.5,
            "image_topic": 92.2,
            "nature_relation": 51.1,
            "object_localization": 39.0,
            "ocr": 76.7,
            "physical_property_reasoning": 45.6,
            "physical_relation": 34.7,
            "social_relation": 71.4,
            "spatial_relationship": 25.3,
            "structuralized_imagetext_understanding": 11.0,
            "Method": [
                "LLaVA-v1.5-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 71
        },
        {
            "Overall": 62.5,
            "AR": 74.7,
            "CP": 69.4,
            "FP-C": 55.8,
            "FP-S": 62.9,
            "LR": 38.6,
            "RR": 60.1,
            "action_recognition": 81.2,
            "attribute_comparison": 49.3,
            "attribute_recognition": 78.7,
            "celebrity_recognition": 57.1,
            "function_reasoning": 78.9,
            "future_prediction": 64.0,
            "identity_reasoning": 92.1,
            "image_emotion": 75.6,
            "image_quality": 34.7,
            "image_scene": 82.6,
            "image_style": 64.1,
            "image_topic": 95.6,
            "nature_relation": 59.8,
            "object_localization": 41.0,
            "ocr": 82.2,
            "physical_property_reasoning": 53.2,
            "physical_relation": 37.3,
            "social_relation": 79.1,
            "spatial_relationship": 22.7,
            "structuralized_imagetext_understanding": 21.1,
            "Method": [
                "LLaVA-v1.5-13B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2023/12/28",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 72
        },
        {
            "Overall": 60.2,
            "AR": 73.1,
            "CP": 67.0,
            "FP-C": 61.0,
            "FP-S": 59.2,
            "LR": 40.2,
            "RR": 48.4,
            "action_recognition": 76.9,
            "attribute_comparison": 60.0,
            "attribute_recognition": 67.4,
            "celebrity_recognition": 51.7,
            "function_reasoning": 74.4,
            "future_prediction": 62.7,
            "identity_reasoning": 92.1,
            "image_emotion": 71.1,
            "image_quality": 35.5,
            "image_scene": 78.5,
            "image_style": 59.8,
            "image_topic": 95.6,
            "nature_relation": 43.5,
            "object_localization": 44.8,
            "ocr": 80.0,
            "physical_property_reasoning": 53.2,
            "physical_relation": 30.7,
            "social_relation": 68.1,
            "spatial_relationship": 37.3,
            "structuralized_imagetext_understanding": 24.8,
            "Method": [
                "LLaVA-LLaMA-3-8B",
                "https://huggingface.co/xtuner/llava-llama-3-8b-v1_1"
            ],
            "Parameters": "8B",
            "Language Model": "LLaMA-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/05/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 254
        },
        {
            "Overall": 70.0,
            "AR": 78.8,
            "CP": 75.0,
            "FP-C": 63.3,
            "FP-S": 74.2,
            "LR": 44.0,
            "RR": 69.8,
            "action_recognition": 82.1,
            "attribute_comparison": 64.0,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 75.5,
            "function_reasoning": 87.8,
            "future_prediction": 69.3,
            "identity_reasoning": 97.4,
            "image_emotion": 77.8,
            "image_quality": 44.4,
            "image_scene": 90.3,
            "image_style": 67.4,
            "image_topic": 97.8,
            "nature_relation": 78.3,
            "object_localization": 54.3,
            "ocr": 85.6,
            "physical_property_reasoning": 50.6,
            "physical_relation": 44.0,
            "social_relation": 82.4,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 26.6,
            "Method": [
                "LLaVA-InternLM2-7B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "8.1B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 91
        },
        {
            "Overall": 70.5,
            "AR": 75.1,
            "CP": 76.1,
            "FP-C": 67.4,
            "FP-S": 73.5,
            "LR": 46.2,
            "RR": 69.8,
            "action_recognition": 82.9,
            "attribute_comparison": 65.3,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 69.4,
            "function_reasoning": 83.3,
            "future_prediction": 77.3,
            "identity_reasoning": 93.4,
            "image_emotion": 82.2,
            "image_quality": 45.2,
            "image_scene": 90.3,
            "image_style": 68.5,
            "image_topic": 97.8,
            "nature_relation": 80.4,
            "object_localization": 61.0,
            "ocr": 84.4,
            "physical_property_reasoning": 48.1,
            "physical_relation": 44.0,
            "social_relation": 80.2,
            "spatial_relationship": 45.3,
            "structuralized_imagetext_understanding": 24.8,
            "Method": [
                "LLaVA-InternLM2-20B (QLoRA)",
                "https://github.com/InternLM/xtuner/blob/main/xtuner/configs/llava/README.md"
            ],
            "Parameters": "20.2B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/01/17",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 92
        },
        {
            "Overall": 59.4,
            "AR": 74.7,
            "CP": 69.6,
            "FP-C": 53.2,
            "FP-S": 57.8,
            "LR": 28.8,
            "RR": 54.3,
            "action_recognition": 83.8,
            "attribute_comparison": 44.0,
            "attribute_recognition": 68.5,
            "celebrity_recognition": 51.0,
            "function_reasoning": 81.1,
            "future_prediction": 53.3,
            "identity_reasoning": 94.7,
            "image_emotion": 82.2,
            "image_quality": 36.3,
            "image_scene": 81.2,
            "image_style": 62.0,
            "image_topic": 92.2,
            "nature_relation": 57.6,
            "object_localization": 37.1,
            "ocr": 82.2,
            "physical_property_reasoning": 48.1,
            "physical_relation": 29.3,
            "social_relation": 71.4,
            "spatial_relationship": 14.7,
            "structuralized_imagetext_understanding": 11.9,
            "Method": [
                "LLaVA-Next-Vicuna-7B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "7.1B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 210
        },
        {
            "Overall": 59.8,
            "AR": 73.1,
            "CP": 67.6,
            "FP-C": 53.9,
            "FP-S": 58.2,
            "LR": 34.2,
            "RR": 57.8,
            "action_recognition": 79.5,
            "attribute_comparison": 48.0,
            "attribute_recognition": 75.3,
            "celebrity_recognition": 43.5,
            "function_reasoning": 76.7,
            "future_prediction": 57.3,
            "identity_reasoning": 93.4,
            "image_emotion": 76.7,
            "image_quality": 34.7,
            "image_scene": 82.6,
            "image_style": 54.3,
            "image_topic": 93.3,
            "nature_relation": 57.6,
            "object_localization": 45.7,
            "ocr": 80.0,
            "physical_property_reasoning": 49.4,
            "physical_relation": 36.0,
            "social_relation": 75.8,
            "spatial_relationship": 20.0,
            "structuralized_imagetext_understanding": 18.3,
            "Method": [
                "LLaVA-Next-Mistral-7B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "7.6B",
            "Language Model": "Mistral-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 211
        },
        {
            "Overall": 65.7,
            "AR": 75.5,
            "CP": 72.4,
            "FP-C": 59.6,
            "FP-S": 64.5,
            "LR": 41.8,
            "RR": 67.8,
            "action_recognition": 82.1,
            "attribute_comparison": 54.7,
            "attribute_recognition": 75.3,
            "celebrity_recognition": 57.1,
            "function_reasoning": 83.3,
            "future_prediction": 66.7,
            "identity_reasoning": 94.7,
            "image_emotion": 78.9,
            "image_quality": 39.5,
            "image_scene": 85.4,
            "image_style": 65.2,
            "image_topic": 97.8,
            "nature_relation": 69.6,
            "object_localization": 45.7,
            "ocr": 87.8,
            "physical_property_reasoning": 48.1,
            "physical_relation": 44.0,
            "social_relation": 85.7,
            "spatial_relationship": 29.3,
            "structuralized_imagetext_understanding": 24.8,
            "Method": [
                "LLaVA-Next-Vicuna-13B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 212
        },
        {
            "Overall": 77.1,
            "AR": 86.1,
            "CP": 78.1,
            "FP-C": 70.8,
            "FP-S": 83.1,
            "LR": 62.5,
            "RR": 73.6,
            "action_recognition": 81.2,
            "attribute_comparison": 60.0,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 81.0,
            "function_reasoning": 91.1,
            "future_prediction": 74.7,
            "identity_reasoning": 98.7,
            "image_emotion": 84.4,
            "image_quality": 48.4,
            "image_scene": 88.2,
            "image_style": 76.1,
            "image_topic": 98.9,
            "nature_relation": 76.1,
            "object_localization": 74.3,
            "ocr": 93.3,
            "physical_property_reasoning": 68.4,
            "physical_relation": 53.3,
            "social_relation": 87.9,
            "spatial_relationship": 65.3,
            "structuralized_imagetext_understanding": 54.1,
            "Method": [
                "LLaVA-Next-Yi-34B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "34.8B",
            "Language Model": "Yi-34B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2024/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 213
        },
        {
            "Overall": 62.8,
            "AR": 77.6,
            "CP": 70.0,
            "FP-C": 52.4,
            "FP-S": 61.7,
            "LR": 36.4,
            "RR": 64.7,
            "action_recognition": 76.9,
            "attribute_comparison": 41.3,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 59.2,
            "function_reasoning": 85.6,
            "future_prediction": 65.3,
            "identity_reasoning": 93.4,
            "image_emotion": 78.9,
            "image_quality": 33.9,
            "image_scene": 86.1,
            "image_style": 63.0,
            "image_topic": 92.2,
            "nature_relation": 66.3,
            "object_localization": 31.4,
            "ocr": 72.2,
            "physical_property_reasoning": 53.2,
            "physical_relation": 42.7,
            "social_relation": 81.3,
            "spatial_relationship": 25.3,
            "structuralized_imagetext_understanding": 16.5,
            "Method": [
                "PaliGemma-3B-mix-448",
                "https://github.com/google-research/big_vision/blob/main/big_vision/configs/proj/paligemma/README.md"
            ],
            "Parameters": "3B",
            "Language Model": "Gemma-2B",
            "Vision Model": "SigLip-400M",
            "Org": "Google",
            "Time": "2024/05/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 261
        },
        {
            "Overall": 72.2,
            "AR": 83.7,
            "CP": 75.2,
            "FP-C": 70.0,
            "FP-S": 69.4,
            "LR": 62.5,
            "RR": 68.6,
            "action_recognition": 83.8,
            "attribute_comparison": 54.7,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 57.1,
            "function_reasoning": 93.3,
            "future_prediction": 66.7,
            "identity_reasoning": 94.7,
            "image_emotion": 81.1,
            "image_quality": 46.8,
            "image_scene": 82.6,
            "image_style": 75.0,
            "image_topic": 96.7,
            "nature_relation": 90.2,
            "object_localization": 51.4,
            "ocr": 93.3,
            "physical_property_reasoning": 62.0,
            "physical_relation": 41.3,
            "social_relation": 69.2,
            "spatial_relationship": 64.0,
            "structuralized_imagetext_understanding": 59.6,
            "Method": [
                "GPT-4v (1106, detail-low)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2023/12/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 242
        },
        {
            "Overall": 65.5,
            "AR": 79.6,
            "CP": 68.7,
            "FP-C": 56.9,
            "FP-S": 65.0,
            "LR": 59.2,
            "RR": 59.3,
            "action_recognition": 72.6,
            "attribute_comparison": 46.7,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 59.2,
            "function_reasoning": 88.9,
            "future_prediction": 65.3,
            "identity_reasoning": 96.1,
            "image_emotion": 57.8,
            "image_quality": 37.9,
            "image_scene": 81.2,
            "image_style": 76.1,
            "image_topic": 94.4,
            "nature_relation": 69.6,
            "object_localization": 36.2,
            "ocr": 93.3,
            "physical_property_reasoning": 53.2,
            "physical_relation": 37.3,
            "social_relation": 67.0,
            "spatial_relationship": 42.7,
            "structuralized_imagetext_understanding": 55.0,
            "Method": [
                "GPT-4v (1106, detail-high)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/04/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 243
        },
        {
            "Overall": 78.2,
            "AR": 86.9,
            "CP": 77.2,
            "FP-C": 72.3,
            "FP-S": 84.2,
            "LR": 70.7,
            "RR": 73.3,
            "action_recognition": 84.6,
            "attribute_comparison": 58.7,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 93.9,
            "function_reasoning": 94.4,
            "future_prediction": 78.7,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 50.8,
            "image_scene": 84.0,
            "image_style": 81.5,
            "image_topic": 96.7,
            "nature_relation": 91.3,
            "object_localization": 55.2,
            "ocr": 97.8,
            "physical_property_reasoning": 68.4,
            "physical_relation": 46.7,
            "social_relation": 76.9,
            "spatial_relationship": 66.7,
            "structuralized_imagetext_understanding": 65.1,
            "Method": [
                "GPT-4v (0409, detail-low)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 244
        },
        {
            "Overall": 79.5,
            "AR": 86.5,
            "CP": 78.3,
            "FP-C": 73.0,
            "FP-S": 86.1,
            "LR": 73.4,
            "RR": 75.2,
            "action_recognition": 87.2,
            "attribute_comparison": 57.3,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 94.6,
            "function_reasoning": 93.3,
            "future_prediction": 78.7,
            "identity_reasoning": 96.1,
            "image_emotion": 82.2,
            "image_quality": 50.8,
            "image_scene": 86.1,
            "image_style": 81.5,
            "image_topic": 96.7,
            "nature_relation": 90.2,
            "object_localization": 61.0,
            "ocr": 97.8,
            "physical_property_reasoning": 69.6,
            "physical_relation": 45.3,
            "social_relation": 84.6,
            "spatial_relationship": 66.7,
            "structuralized_imagetext_understanding": 69.7,
            "Method": [
                "GPT-4v (0409, detail-high)",
                "https://openai.com/research/gpt-4v-system-card"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 246
        },
        {
            "Overall": 82.5,
            "AR": 89.4,
            "CP": 81.5,
            "FP-C": 85.8,
            "FP-S": 82.1,
            "LR": 76.6,
            "RR": 79.5,
            "action_recognition": 93.2,
            "attribute_comparison": 82.7,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 64.6,
            "function_reasoning": 93.3,
            "future_prediction": 81.3,
            "identity_reasoning": 98.7,
            "image_emotion": 84.4,
            "image_quality": 59.7,
            "image_scene": 86.8,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 83.8,
            "ocr": 100.0,
            "physical_property_reasoning": 75.9,
            "physical_relation": 52.0,
            "social_relation": 87.9,
            "spatial_relationship": 77.3,
            "structuralized_imagetext_understanding": 73.4,
            "Method": [
                "GPT-4o (0513, detail-low)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 260
        },
        {
            "Overall": 81.5,
            "AR": 86.5,
            "CP": 81.5,
            "FP-C": 85.0,
            "FP-S": 79.1,
            "LR": 77.2,
            "RR": 79.8,
            "action_recognition": 94.0,
            "attribute_comparison": 81.3,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 57.8,
            "function_reasoning": 94.4,
            "future_prediction": 82.7,
            "identity_reasoning": 97.4,
            "image_emotion": 85.6,
            "image_quality": 58.9,
            "image_scene": 88.2,
            "image_style": 80.4,
            "image_topic": 98.9,
            "nature_relation": 94.6,
            "object_localization": 82.9,
            "ocr": 97.8,
            "physical_property_reasoning": 67.1,
            "physical_relation": 53.3,
            "social_relation": 86.8,
            "spatial_relationship": 74.7,
            "structuralized_imagetext_understanding": 73.4,
            "Method": [
                "GPT-4o (0513, detail-high)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 270
        },
        {
            "Overall": 69.2,
            "AR": 80.4,
            "CP": 68.1,
            "FP-C": 64.0,
            "FP-S": 77.3,
            "LR": 45.7,
            "RR": 69.8,
            "action_recognition": 87.2,
            "attribute_comparison": 46.7,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 85.7,
            "function_reasoning": 91.1,
            "future_prediction": 54.7,
            "identity_reasoning": 97.4,
            "image_emotion": 75.6,
            "image_quality": 33.1,
            "image_scene": 78.5,
            "image_style": 69.6,
            "image_topic": 91.1,
            "nature_relation": 90.2,
            "object_localization": 46.7,
            "ocr": 88.9,
            "physical_property_reasoning": 51.9,
            "physical_relation": 26.7,
            "social_relation": 84.6,
            "spatial_relationship": 45.3,
            "structuralized_imagetext_understanding": 39.4,
            "Method": [
                "Gemini-1.0-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2023/12/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 101
        },
        {
            "Overall": 68.2,
            "AR": 75.9,
            "CP": 69.8,
            "FP-C": 61.8,
            "FP-S": 78.2,
            "LR": 48.9,
            "RR": 60.9,
            "action_recognition": 90.6,
            "attribute_comparison": 41.3,
            "attribute_recognition": 77.5,
            "celebrity_recognition": 86.4,
            "function_reasoning": 85.6,
            "future_prediction": 53.3,
            "identity_reasoning": 94.7,
            "image_emotion": 81.1,
            "image_quality": 29.0,
            "image_scene": 81.2,
            "image_style": 68.5,
            "image_topic": 97.8,
            "nature_relation": 80.4,
            "object_localization": 58.1,
            "ocr": 88.9,
            "physical_property_reasoning": 46.8,
            "physical_relation": 21.3,
            "social_relation": 73.6,
            "spatial_relationship": 37.3,
            "structuralized_imagetext_understanding": 45.9,
            "Method": [
                "Qwen-VL-Plus",
                "https://github.com/QwenLM/Qwen-VL?tab=readme-ov-file#qwen-vl-plus"
            ],
            "Parameters": "",
            "Language Model": "QwenLM",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/01/10",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "key": 77
        },
        {
            "Overall": 73.7,
            "AR": 79.2,
            "CP": 74.8,
            "FP-C": 69.3,
            "FP-S": 81.9,
            "LR": 56.0,
            "RR": 69.8,
            "action_recognition": 88.0,
            "attribute_comparison": 57.3,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 91.2,
            "function_reasoning": 93.3,
            "future_prediction": 66.7,
            "identity_reasoning": 92.1,
            "image_emotion": 78.9,
            "image_quality": 45.2,
            "image_scene": 86.8,
            "image_style": 69.6,
            "image_topic": 97.8,
            "nature_relation": 85.9,
            "object_localization": 59.0,
            "ocr": 91.1,
            "physical_property_reasoning": 50.6,
            "physical_relation": 41.3,
            "social_relation": 76.9,
            "spatial_relationship": 52.0,
            "structuralized_imagetext_understanding": 48.6,
            "Method": [
                "Qwen-VL-Max",
                "https://huggingface.co/spaces/Qwen/Qwen-VL-Max"
            ],
            "Parameters": "",
            "Language Model": "QwenLM",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 136
        },
        {
            "Overall": 56.2,
            "AR": 74.3,
            "CP": 64.4,
            "FP-C": 38.6,
            "FP-S": 54.8,
            "LR": 50.5,
            "RR": 46.5,
            "action_recognition": 55.6,
            "attribute_comparison": 28.0,
            "attribute_recognition": 73.0,
            "celebrity_recognition": 43.5,
            "function_reasoning": 87.8,
            "future_prediction": 57.3,
            "identity_reasoning": 86.8,
            "image_emotion": 58.9,
            "image_quality": 25.8,
            "image_scene": 84.0,
            "image_style": 63.0,
            "image_topic": 93.3,
            "nature_relation": 53.3,
            "object_localization": 25.7,
            "ocr": 88.9,
            "physical_property_reasoning": 46.8,
            "physical_relation": 17.3,
            "social_relation": 63.7,
            "spatial_relationship": 22.7,
            "structuralized_imagetext_understanding": 45.9,
            "Method": [
                "Claude3-Haiku",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 217
        },
        {
            "Overall": 63.5,
            "AR": 75.5,
            "CP": 68.1,
            "FP-C": 55.1,
            "FP-S": 65.4,
            "LR": 54.3,
            "RR": 54.7,
            "action_recognition": 63.2,
            "attribute_comparison": 57.3,
            "attribute_recognition": 78.7,
            "celebrity_recognition": 59.9,
            "function_reasoning": 92.2,
            "future_prediction": 62.7,
            "identity_reasoning": 90.8,
            "image_emotion": 64.4,
            "image_quality": 33.9,
            "image_scene": 79.2,
            "image_style": 75.0,
            "image_topic": 94.4,
            "nature_relation": 58.7,
            "object_localization": 40.0,
            "ocr": 91.1,
            "physical_property_reasoning": 41.8,
            "physical_relation": 29.3,
            "social_relation": 71.4,
            "spatial_relationship": 40.0,
            "structuralized_imagetext_understanding": 48.6,
            "Method": [
                "Claude3-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 218
        },
        {
            "Overall": 58.1,
            "AR": 76.3,
            "CP": 66.5,
            "FP-C": 45.3,
            "FP-S": 55.0,
            "LR": 50.5,
            "RR": 47.3,
            "action_recognition": 57.3,
            "attribute_comparison": 36.0,
            "attribute_recognition": 78.7,
            "celebrity_recognition": 39.5,
            "function_reasoning": 80.0,
            "future_prediction": 54.7,
            "identity_reasoning": 92.1,
            "image_emotion": 55.6,
            "image_quality": 29.0,
            "image_scene": 83.3,
            "image_style": 76.1,
            "image_topic": 92.2,
            "nature_relation": 42.4,
            "object_localization": 28.6,
            "ocr": 87.8,
            "physical_property_reasoning": 57.0,
            "physical_relation": 25.3,
            "social_relation": 70.3,
            "spatial_relationship": 36.0,
            "structuralized_imagetext_understanding": 47.7,
            "Method": [
                "Claude3-Opus",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/03/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 219
        },
        {
            "Overall": 71.4,
            "AR": 79.6,
            "CP": 74.1,
            "FP-C": 65.5,
            "FP-S": 74.0,
            "LR": 56.5,
            "RR": 70.2,
            "action_recognition": 81.2,
            "attribute_comparison": 56.0,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 70.1,
            "function_reasoning": 90.0,
            "future_prediction": 64.0,
            "identity_reasoning": 97.4,
            "image_emotion": 81.1,
            "image_quality": 41.1,
            "image_scene": 83.3,
            "image_style": 72.8,
            "image_topic": 98.9,
            "nature_relation": 82.6,
            "object_localization": 55.2,
            "ocr": 92.2,
            "physical_property_reasoning": 50.6,
            "physical_relation": 44.0,
            "social_relation": 79.1,
            "spatial_relationship": 50.7,
            "structuralized_imagetext_understanding": 51.4,
            "Method": [
                "RekaFlash",
                "https://www.reka.ai"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Reka AI",
            "Time": "2024/05/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 262
        },
        {
            "Overall": 56.6,
            "AR": 69.0,
            "CP": 65.4,
            "FP-C": 46.1,
            "FP-S": 56.6,
            "LR": 24.5,
            "RR": 60.5,
            "action_recognition": 77.8,
            "attribute_comparison": 17.3,
            "attribute_recognition": 78.7,
            "celebrity_recognition": 54.4,
            "function_reasoning": 80.0,
            "future_prediction": 46.7,
            "identity_reasoning": 94.7,
            "image_emotion": 73.3,
            "image_quality": 17.7,
            "image_scene": 84.7,
            "image_style": 64.1,
            "image_topic": 93.3,
            "nature_relation": 63.0,
            "object_localization": 16.2,
            "ocr": 85.6,
            "physical_property_reasoning": 31.6,
            "physical_relation": 32.0,
            "social_relation": 81.3,
            "spatial_relationship": 25.3,
            "structuralized_imagetext_understanding": 9.2,
            "Method": [
                "RekaEdge",
                "https://www.reka.ai"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Reka AI",
            "Time": "2024/05/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 271
        },
        {
            "Overall": 78.0,
            "AR": 81.6,
            "CP": 79.6,
            "FP-C": 74.5,
            "FP-S": 82.8,
            "LR": 64.7,
            "RR": 76.0,
            "action_recognition": 92.3,
            "attribute_comparison": 72.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 93.9,
            "function_reasoning": 88.9,
            "future_prediction": 73.3,
            "identity_reasoning": 100.0,
            "image_emotion": 87.8,
            "image_quality": 49.2,
            "image_scene": 90.3,
            "image_style": 79.3,
            "image_topic": 96.7,
            "nature_relation": 79.3,
            "object_localization": 52.4,
            "ocr": 90.0,
            "physical_property_reasoning": 55.7,
            "physical_relation": 60.0,
            "social_relation": 85.7,
            "spatial_relationship": 49.3,
            "structuralized_imagetext_understanding": 58.7,
            "Method": [
                "GLM-4v",
                "https://open.bigmodel.cn/dev/api#glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2024/05/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 263
        },
        {
            "Overall": 63.0,
            "AR": 74.7,
            "CP": 70.4,
            "FP-C": 54.3,
            "FP-S": 65.7,
            "LR": 38.0,
            "RR": 58.9,
            "action_recognition": 81.2,
            "attribute_comparison": 41.3,
            "attribute_recognition": 78.7,
            "celebrity_recognition": 63.9,
            "function_reasoning": 80.0,
            "future_prediction": 57.3,
            "identity_reasoning": 92.1,
            "image_emotion": 74.4,
            "image_quality": 32.3,
            "image_scene": 86.1,
            "image_style": 66.3,
            "image_topic": 97.8,
            "nature_relation": 60.9,
            "object_localization": 41.0,
            "ocr": 84.4,
            "physical_property_reasoning": 51.9,
            "physical_relation": 33.3,
            "social_relation": 78.0,
            "spatial_relationship": 25.3,
            "structuralized_imagetext_understanding": 24.8,
            "Method": [
                "Mini-InternVL-Chat-2B-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 277
        },
        {
            "Overall": 66.8,
            "AR": 75.9,
            "CP": 71.5,
            "FP-C": 62.5,
            "FP-S": 67.5,
            "LR": 47.8,
            "RR": 65.1,
            "action_recognition": 78.6,
            "attribute_comparison": 66.7,
            "attribute_recognition": 83.1,
            "celebrity_recognition": 50.3,
            "function_reasoning": 81.1,
            "future_prediction": 60.0,
            "identity_reasoning": 94.7,
            "image_emotion": 75.6,
            "image_quality": 40.3,
            "image_scene": 84.0,
            "image_style": 65.2,
            "image_topic": 96.7,
            "nature_relation": 60.9,
            "object_localization": 61.0,
            "ocr": 87.8,
            "physical_property_reasoning": 51.9,
            "physical_relation": 41.3,
            "social_relation": 89.0,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 39.4,
            "Method": [
                "Mini-InternVL-Chat-4B-V1.5",
                "https://github.com/OpenGVLab/InternVL"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & Sensetime & Tsinghua University",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 278
        },
        {
            "Overall": 73.2,
            "AR": 74.7,
            "CP": 75.2,
            "FP-C": 68.9,
            "FP-S": 81.0,
            "LR": 58.7,
            "RR": 69.4,
            "action_recognition": 81.2,
            "attribute_comparison": 68.0,
            "attribute_recognition": 77.5,
            "celebrity_recognition": 87.1,
            "function_reasoning": 81.1,
            "future_prediction": 61.3,
            "identity_reasoning": 81.6,
            "image_emotion": 83.3,
            "image_quality": 42.7,
            "image_scene": 82.6,
            "image_style": 77.2,
            "image_topic": 97.8,
            "nature_relation": 83.7,
            "object_localization": 69.5,
            "ocr": 87.8,
            "physical_property_reasoning": 60.8,
            "physical_relation": 44.0,
            "social_relation": 75.8,
            "spatial_relationship": 50.7,
            "structuralized_imagetext_understanding": 56.9,
            "Method": [
                "Gemini-1.5-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/06/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 279
        },
        {
            "Overall": 67.1,
            "AR": 72.7,
            "CP": 65.2,
            "FP-C": 67.4,
            "FP-S": 77.5,
            "LR": 58.7,
            "RR": 54.3,
            "action_recognition": 86.3,
            "attribute_comparison": 61.3,
            "attribute_recognition": 78.7,
            "celebrity_recognition": 85.0,
            "function_reasoning": 83.3,
            "future_prediction": 65.3,
            "identity_reasoning": 86.8,
            "image_emotion": 63.3,
            "image_quality": 48.4,
            "image_scene": 69.4,
            "image_style": 64.1,
            "image_topic": 84.4,
            "nature_relation": 50.0,
            "object_localization": 61.0,
            "ocr": 83.3,
            "physical_property_reasoning": 46.8,
            "physical_relation": 49.3,
            "social_relation": 62.6,
            "spatial_relationship": 44.0,
            "structuralized_imagetext_understanding": 54.1,
            "Method": [
                "GLM-4v-9B",
                "https://huggingface.co/THUDM/glm-4v-9b"
            ],
            "Parameters": "9B",
            "Language Model": "GLM-4-9B",
            "Vision Model": "EVA-02-5B",
            "Org": "Zhipu AI",
            "Time": "2024/06/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 281
        },
        {
            "Overall": 79.3,
            "AR": 86.5,
            "CP": 79.8,
            "FP-C": 75.7,
            "FP-S": 81.7,
            "LR": 75.5,
            "RR": 74.0,
            "action_recognition": 78.6,
            "attribute_comparison": 76.0,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 74.8,
            "function_reasoning": 94.4,
            "future_prediction": 69.3,
            "identity_reasoning": 97.4,
            "image_emotion": 73.3,
            "image_quality": 58.9,
            "image_scene": 88.2,
            "image_style": 82.6,
            "image_topic": 98.9,
            "nature_relation": 88.0,
            "object_localization": 78.1,
            "ocr": 94.4,
            "physical_property_reasoning": 67.1,
            "physical_relation": 50.7,
            "social_relation": 79.1,
            "spatial_relationship": 70.7,
            "structuralized_imagetext_understanding": 79.8,
            "Method": [
                "Claude3.5-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/06/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 284
        },
        {
            "Overall": 80.4,
            "AR": 84.9,
            "CP": 80.4,
            "FP-C": 76.0,
            "FP-S": 86.8,
            "LR": 69.0,
            "RR": 77.9,
            "action_recognition": 92.3,
            "attribute_comparison": 77.3,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 83.0,
            "function_reasoning": 88.9,
            "future_prediction": 85.3,
            "identity_reasoning": 96.1,
            "image_emotion": 82.2,
            "image_quality": 60.5,
            "image_scene": 86.8,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 83.7,
            "object_localization": 78.1,
            "ocr": 95.6,
            "physical_property_reasoning": 69.6,
            "physical_relation": 66.7,
            "social_relation": 81.3,
            "spatial_relationship": 49.3,
            "structuralized_imagetext_understanding": 57.8,
            "Method": [
                "CongRong",
                "https://mllm.cloudwalk.com/web/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "CloudWalk",
            "Time": "2024/06/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 285
        },
        {
            "Overall": 73.6,
            "AR": 83.3,
            "CP": 78.0,
            "FP-C": 64.4,
            "FP-S": 78.2,
            "LR": 53.8,
            "RR": 71.3,
            "action_recognition": 85.5,
            "attribute_comparison": 60.0,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 77.6,
            "function_reasoning": 92.2,
            "future_prediction": 77.3,
            "identity_reasoning": 100.0,
            "image_emotion": 84.4,
            "image_quality": 50.8,
            "image_scene": 86.8,
            "image_style": 76.1,
            "image_topic": 96.7,
            "nature_relation": 82.6,
            "object_localization": 61.0,
            "ocr": 91.1,
            "physical_property_reasoning": 57.0,
            "physical_relation": 42.7,
            "social_relation": 83.5,
            "spatial_relationship": 36.0,
            "structuralized_imagetext_understanding": 37.6,
            "Method": [
                "Bumblebee-7B-v1.6",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Monolith Foundation",
            "Time": "2024/06/27",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 286
        },
        {
            "Overall": 67.8,
            "AR": 83.3,
            "CP": 72.0,
            "FP-C": 62.5,
            "FP-S": 71.5,
            "LR": 41.3,
            "RR": 62.4,
            "action_recognition": 86.3,
            "attribute_comparison": 58.7,
            "attribute_recognition": 83.1,
            "celebrity_recognition": 72.8,
            "function_reasoning": 90.0,
            "future_prediction": 62.7,
            "identity_reasoning": 97.4,
            "image_emotion": 73.3,
            "image_quality": 46.8,
            "image_scene": 83.3,
            "image_style": 64.1,
            "image_topic": 95.6,
            "nature_relation": 62.0,
            "object_localization": 50.5,
            "ocr": 82.2,
            "physical_property_reasoning": 62.0,
            "physical_relation": 34.7,
            "social_relation": 85.7,
            "spatial_relationship": 29.3,
            "structuralized_imagetext_understanding": 26.6,
            "Method": [
                "Llama-3-MixSense",
                "https://huggingface.co/Zero-Vision/Llama-3-MixSense"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "ZeroVision",
            "Time": "2024/07/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 288
        },
        {
            "Overall": 85.7,
            "AR": 91.4,
            "CP": 82.6,
            "FP-C": 84.6,
            "FP-S": 91.2,
            "LR": 80.4,
            "RR": 82.6,
            "action_recognition": 94.0,
            "attribute_comparison": 80.0,
            "attribute_recognition": 97.8,
            "celebrity_recognition": 90.5,
            "function_reasoning": 94.4,
            "future_prediction": 84.0,
            "identity_reasoning": 98.7,
            "image_emotion": 84.4,
            "image_quality": 58.9,
            "image_scene": 90.3,
            "image_style": 84.8,
            "image_topic": 98.9,
            "nature_relation": 89.1,
            "object_localization": 81.9,
            "ocr": 96.7,
            "physical_property_reasoning": 81.0,
            "physical_relation": 70.7,
            "social_relation": 85.7,
            "spatial_relationship": 74.7,
            "structuralized_imagetext_understanding": 78.0,
            "Method": [
                "InternVL-2.0-Pro",
                "https://huggingface.co/spaces/OpenGVLab/InternVL/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/08",
            "Verified": "Yes",
            "OpenSource": "No",
            "key": 290
        },
        {
            "Overall": 57.7,
            "AR": 74.7,
            "CP": 67.2,
            "FP-C": 44.9,
            "FP-S": 59.4,
            "LR": 28.3,
            "RR": 53.1,
            "action_recognition": 83.8,
            "attribute_comparison": 12.0,
            "attribute_recognition": 70.8,
            "celebrity_recognition": 57.1,
            "function_reasoning": 80.0,
            "future_prediction": 48.0,
            "identity_reasoning": 89.5,
            "image_emotion": 67.8,
            "image_quality": 27.4,
            "image_scene": 83.3,
            "image_style": 67.4,
            "image_topic": 95.6,
            "nature_relation": 50.0,
            "object_localization": 39.0,
            "ocr": 75.6,
            "physical_property_reasoning": 54.4,
            "physical_relation": 32.0,
            "social_relation": 73.6,
            "spatial_relationship": 17.3,
            "structuralized_imagetext_understanding": 14.7,
            "Method": [
                "InternVL2-1B",
                "https://huggingface.co/OpenGVLab/InternVL2-1B"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 292
        },
        {
            "Overall": 68.9,
            "AR": 79.6,
            "CP": 75.6,
            "FP-C": 59.9,
            "FP-S": 70.8,
            "LR": 50.5,
            "RR": 64.0,
            "action_recognition": 84.6,
            "attribute_comparison": 54.7,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 64.6,
            "function_reasoning": 83.3,
            "future_prediction": 66.7,
            "identity_reasoning": 97.4,
            "image_emotion": 77.8,
            "image_quality": 44.4,
            "image_scene": 89.6,
            "image_style": 71.7,
            "image_topic": 97.8,
            "nature_relation": 67.4,
            "object_localization": 50.5,
            "ocr": 90.0,
            "physical_property_reasoning": 58.2,
            "physical_relation": 34.7,
            "social_relation": 84.6,
            "spatial_relationship": 26.7,
            "structuralized_imagetext_understanding": 39.4,
            "Method": [
                "InternVL2-2B",
                "https://huggingface.co/OpenGVLab/InternVL2-2B"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 293
        },
        {
            "Overall": 71.4,
            "AR": 79.6,
            "CP": 78.9,
            "FP-C": 67.0,
            "FP-S": 70.3,
            "LR": 54.3,
            "RR": 66.3,
            "action_recognition": 86.3,
            "attribute_comparison": 65.3,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 57.8,
            "function_reasoning": 82.2,
            "future_prediction": 60.0,
            "identity_reasoning": 93.4,
            "image_emotion": 76.7,
            "image_quality": 55.6,
            "image_scene": 91.0,
            "image_style": 75.0,
            "image_topic": 97.8,
            "nature_relation": 72.8,
            "object_localization": 59.0,
            "ocr": 87.8,
            "physical_property_reasoning": 63.3,
            "physical_relation": 40.0,
            "social_relation": 81.3,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 50.5,
            "Method": [
                "InternVL2-4B",
                "https://huggingface.co/OpenGVLab/InternVL2-4B"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 294
        },
        {
            "Overall": 79.3,
            "AR": 83.3,
            "CP": 81.9,
            "FP-C": 74.5,
            "FP-S": 84.2,
            "LR": 66.3,
            "RR": 76.4,
            "action_recognition": 88.0,
            "attribute_comparison": 74.7,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 81.0,
            "function_reasoning": 91.1,
            "future_prediction": 74.7,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 61.3,
            "image_scene": 92.4,
            "image_style": 80.4,
            "image_topic": 96.7,
            "nature_relation": 79.3,
            "object_localization": 73.3,
            "ocr": 95.6,
            "physical_property_reasoning": 60.8,
            "physical_relation": 56.0,
            "social_relation": 90.1,
            "spatial_relationship": 53.3,
            "structuralized_imagetext_understanding": 60.6,
            "Method": [
                "InternVL2-8B",
                "https://huggingface.co/OpenGVLab/InternVL2-8B"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 295
        },
        {
            "Overall": 80.9,
            "AR": 84.1,
            "CP": 82.2,
            "FP-C": 76.4,
            "FP-S": 86.8,
            "LR": 69.0,
            "RR": 78.7,
            "action_recognition": 93.2,
            "attribute_comparison": 74.7,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 83.7,
            "function_reasoning": 88.9,
            "future_prediction": 81.3,
            "identity_reasoning": 100.0,
            "image_emotion": 84.4,
            "image_quality": 64.5,
            "image_scene": 86.8,
            "image_style": 82.6,
            "image_topic": 96.7,
            "nature_relation": 83.7,
            "object_localization": 79.0,
            "ocr": 93.3,
            "physical_property_reasoning": 63.3,
            "physical_relation": 65.3,
            "social_relation": 84.6,
            "spatial_relationship": 52.0,
            "structuralized_imagetext_understanding": 60.6,
            "Method": [
                "InternVL2-26B",
                "https://huggingface.co/OpenGVLab/InternVL2-26B"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 296
        },
        {
            "Overall": 84.9,
            "AR": 90.6,
            "CP": 82.0,
            "FP-C": 81.3,
            "FP-S": 91.6,
            "LR": 76.6,
            "RR": 84.1,
            "action_recognition": 92.3,
            "attribute_comparison": 76.0,
            "attribute_recognition": 97.8,
            "celebrity_recognition": 90.5,
            "function_reasoning": 94.4,
            "future_prediction": 84.0,
            "identity_reasoning": 97.4,
            "image_emotion": 87.8,
            "image_quality": 57.3,
            "image_scene": 89.6,
            "image_style": 81.5,
            "image_topic": 98.9,
            "nature_relation": 92.4,
            "object_localization": 83.8,
            "ocr": 96.7,
            "physical_property_reasoning": 79.7,
            "physical_relation": 72.0,
            "social_relation": 85.7,
            "spatial_relationship": 69.3,
            "structuralized_imagetext_understanding": 71.6,
            "Method": [
                "InternVL2-40B",
                "https://huggingface.co/OpenGVLab/InternVL2-40B"
            ],
            "Parameters": "40B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 297
        },
        {
            "Overall": 64.9,
            "AR": 74.3,
            "CP": 71.3,
            "FP-C": 61.4,
            "FP-S": 62.4,
            "LR": 47.3,
            "RR": 62.8,
            "action_recognition": 83.8,
            "attribute_comparison": 57.3,
            "attribute_recognition": 71.9,
            "celebrity_recognition": 41.5,
            "function_reasoning": 87.8,
            "future_prediction": 60.0,
            "identity_reasoning": 93.4,
            "image_emotion": 72.2,
            "image_quality": 47.6,
            "image_scene": 83.3,
            "image_style": 58.7,
            "image_topic": 96.7,
            "nature_relation": 64.1,
            "object_localization": 61.0,
            "ocr": 88.9,
            "physical_property_reasoning": 40.5,
            "physical_relation": 41.3,
            "social_relation": 79.1,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 38.5,
            "Method": [
                "Cambrian-8B",
                "https://huggingface.co/nyu-visionx/cambrian-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "NYU",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 298
        },
        {
            "Overall": 78.8,
            "AR": 87.3,
            "CP": 78.9,
            "FP-C": 73.8,
            "FP-S": 84.2,
            "LR": 67.4,
            "RR": 74.4,
            "action_recognition": 86.3,
            "attribute_comparison": 78.7,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 82.3,
            "function_reasoning": 93.3,
            "future_prediction": 81.3,
            "identity_reasoning": 98.7,
            "image_emotion": 80.0,
            "image_quality": 55.6,
            "image_scene": 90.3,
            "image_style": 72.8,
            "image_topic": 97.8,
            "nature_relation": 82.6,
            "object_localization": 73.3,
            "ocr": 88.9,
            "physical_property_reasoning": 69.6,
            "physical_relation": 50.7,
            "social_relation": 85.7,
            "spatial_relationship": 49.3,
            "structuralized_imagetext_understanding": 57.8,
            "Method": [
                "InternLM-XComposer2.5",
                "https://huggingface.co/internlm/internlm-xcomposer2d5-7b"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Shanghai AI Laboratory",
            "Time": "2024/07/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 299
        },
        {
            "Overall": 76.5,
            "AR": 84.9,
            "CP": 79.6,
            "FP-C": 68.5,
            "FP-S": 79.8,
            "LR": 62.0,
            "RR": 75.2,
            "action_recognition": 85.5,
            "attribute_comparison": 72.0,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 75.5,
            "function_reasoning": 91.1,
            "future_prediction": 81.3,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 52.4,
            "image_scene": 89.6,
            "image_style": 81.5,
            "image_topic": 96.7,
            "nature_relation": 81.5,
            "object_localization": 66.7,
            "ocr": 94.4,
            "physical_property_reasoning": 65.8,
            "physical_relation": 53.3,
            "social_relation": 86.8,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 48.6,
            "Method": [
                "Bumblebee-7B-v2.0",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Monolith Foundation",
            "Time": "2024/07/11",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 300
        },
        {
            "Overall": 74.6,
            "AR": 87.3,
            "CP": 76.5,
            "FP-C": 67.4,
            "FP-S": 76.8,
            "LR": 51.6,
            "RR": 79.1,
            "action_recognition": 84.6,
            "attribute_comparison": 70.7,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 72.8,
            "function_reasoning": 93.3,
            "future_prediction": 74.7,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 55.6,
            "image_scene": 84.7,
            "image_style": 69.6,
            "image_topic": 96.7,
            "nature_relation": 90.2,
            "object_localization": 64.8,
            "ocr": 86.7,
            "physical_property_reasoning": 70.9,
            "physical_relation": 52.0,
            "social_relation": 90.1,
            "spatial_relationship": 37.3,
            "structuralized_imagetext_understanding": 35.8,
            "Method": [
                "XinYuan-VL",
                "https://cece.com"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "Cylingo Group",
            "Time": "2024/07/18",
            "Verified": "No",
            "OpenSource": "No",
            "key": 301
        },
        {
            "Overall": 77.3,
            "AR": 84.5,
            "CP": 78.7,
            "FP-C": 74.9,
            "FP-S": 81.7,
            "LR": 62.5,
            "RR": 73.3,
            "action_recognition": 85.5,
            "attribute_comparison": 77.3,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 78.2,
            "function_reasoning": 95.6,
            "future_prediction": 76.0,
            "identity_reasoning": 98.7,
            "image_emotion": 83.3,
            "image_quality": 52.4,
            "image_scene": 88.2,
            "image_style": 75.0,
            "image_topic": 98.9,
            "nature_relation": 83.7,
            "object_localization": 71.4,
            "ocr": 93.3,
            "physical_property_reasoning": 58.2,
            "physical_relation": 46.7,
            "social_relation": 84.6,
            "spatial_relationship": 56.0,
            "structuralized_imagetext_understanding": 53.2,
            "Method": [
                "Cambrian-34B",
                "https://huggingface.co/nyu-visionx/cambrian-34b"
            ],
            "Parameters": "34B",
            "Language Model": "Nous-Hermes-2-Yi-34B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "NYU",
            "Time": "2024/07/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 302
        },
        {
            "Overall": 71.7,
            "AR": 81.2,
            "CP": 76.5,
            "FP-C": 64.0,
            "FP-S": 75.9,
            "LR": 48.9,
            "RR": 69.8,
            "action_recognition": 86.3,
            "attribute_comparison": 61.3,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 75.5,
            "function_reasoning": 88.9,
            "future_prediction": 81.3,
            "identity_reasoning": 98.7,
            "image_emotion": 82.2,
            "image_quality": 47.6,
            "image_scene": 87.5,
            "image_style": 72.8,
            "image_topic": 96.7,
            "nature_relation": 75.0,
            "object_localization": 57.1,
            "ocr": 88.9,
            "physical_property_reasoning": 55.7,
            "physical_relation": 38.7,
            "social_relation": 90.1,
            "spatial_relationship": 32.0,
            "structuralized_imagetext_understanding": 26.6,
            "Method": [
                "Bunny-Llama3-8B",
                "https://huggingface.co/BAAI/Bunny-v1_1-Llama-3-8B-V"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "BAAI",
            "Time": "2024/07/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 303
        },
        {
            "Overall": 85.5,
            "AR": 91.4,
            "CP": 83.0,
            "FP-C": 84.3,
            "FP-S": 90.5,
            "LR": 75.5,
            "RR": 84.9,
            "action_recognition": 94.9,
            "attribute_comparison": 80.0,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 87.1,
            "function_reasoning": 94.4,
            "future_prediction": 81.3,
            "identity_reasoning": 100.0,
            "image_emotion": 86.7,
            "image_quality": 58.1,
            "image_scene": 91.7,
            "image_style": 83.7,
            "image_topic": 98.9,
            "nature_relation": 90.2,
            "object_localization": 86.7,
            "ocr": 94.4,
            "physical_property_reasoning": 79.7,
            "physical_relation": 74.7,
            "social_relation": 87.9,
            "spatial_relationship": 72.0,
            "structuralized_imagetext_understanding": 71.6,
            "Method": [
                "InternVL2-Llama3-76B",
                "https://huggingface.co/OpenGVLab/InternVL2-Llama3-76B"
            ],
            "Parameters": "76B",
            "Language Model": "Llama-3-70B-Instruct",
            "Vision Model": "InternViT-6B",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/07/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 304
        },
        {
            "Overall": 75.0,
            "AR": 84.1,
            "CP": 73.0,
            "FP-C": 71.2,
            "FP-S": 78.2,
            "LR": 72.3,
            "RR": 70.9,
            "action_recognition": 92.3,
            "attribute_comparison": 49.3,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 65.3,
            "function_reasoning": 91.1,
            "future_prediction": 82.7,
            "identity_reasoning": 96.1,
            "image_emotion": 82.2,
            "image_quality": 28.2,
            "image_scene": 85.4,
            "image_style": 81.5,
            "image_topic": 96.7,
            "nature_relation": 88.0,
            "object_localization": 67.6,
            "ocr": 100.0,
            "physical_property_reasoning": 64.6,
            "physical_relation": 34.7,
            "social_relation": 83.5,
            "spatial_relationship": 60.0,
            "structuralized_imagetext_understanding": 65.1,
            "Method": [
                "GPT-4o-mini (0718, detail-high)",
                "https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/07/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 305
        },
        {
            "Overall": 75.1,
            "AR": 82.9,
            "CP": 77.2,
            "FP-C": 72.3,
            "FP-S": 78.7,
            "LR": 61.4,
            "RR": 70.2,
            "action_recognition": 85.5,
            "attribute_comparison": 77.3,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 74.8,
            "function_reasoning": 91.1,
            "future_prediction": 70.7,
            "identity_reasoning": 97.4,
            "image_emotion": 76.7,
            "image_quality": 54.0,
            "image_scene": 89.6,
            "image_style": 70.7,
            "image_topic": 96.7,
            "nature_relation": 73.9,
            "object_localization": 61.0,
            "ocr": 93.3,
            "physical_property_reasoning": 59.5,
            "physical_relation": 49.3,
            "social_relation": 83.5,
            "spatial_relationship": 46.7,
            "structuralized_imagetext_understanding": 55.0,
            "Method": [
                "Ovis1.5-Llama3-8B",
                "https://huggingface.co/AIDC-AI/Ovis1.5-Llama3-8B"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 306
        },
        {
            "Overall": 19.6,
            "AR": 33.1,
            "CP": 27.0,
            "FP-C": 14.6,
            "FP-S": 11.1,
            "LR": 7.1,
            "RR": 19.8,
            "action_recognition": 29.9,
            "attribute_comparison": 4.0,
            "attribute_recognition": 25.8,
            "celebrity_recognition": 12.9,
            "function_reasoning": 34.4,
            "future_prediction": 16.0,
            "identity_reasoning": 40.8,
            "image_emotion": 14.4,
            "image_quality": 2.4,
            "image_scene": 42.4,
            "image_style": 26.1,
            "image_topic": 50.0,
            "nature_relation": 19.6,
            "object_localization": 1.0,
            "ocr": 5.6,
            "physical_property_reasoning": 24.1,
            "physical_relation": 6.7,
            "social_relation": 30.8,
            "spatial_relationship": 1.3,
            "structuralized_imagetext_understanding": 0.9,
            "Method": [
                "Chameleon-7B",
                "https://huggingface.co/facebook/chameleon-7b"
            ],
            "Parameters": "7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 309
        },
        {
            "Overall": 27.8,
            "AR": 54.3,
            "CP": 40.4,
            "FP-C": 14.2,
            "FP-S": 20.4,
            "LR": 3.3,
            "RR": 20.5,
            "action_recognition": 26.5,
            "attribute_comparison": 4.0,
            "attribute_recognition": 32.6,
            "celebrity_recognition": 23.8,
            "function_reasoning": 53.3,
            "future_prediction": 4.0,
            "identity_reasoning": 75.0,
            "image_emotion": 33.3,
            "image_quality": 0.0,
            "image_scene": 55.6,
            "image_style": 48.9,
            "image_topic": 70.0,
            "nature_relation": 20.7,
            "object_localization": 4.8,
            "ocr": 21.1,
            "physical_property_reasoning": 35.4,
            "physical_relation": 5.3,
            "social_relation": 33.0,
            "spatial_relationship": 5.3,
            "structuralized_imagetext_understanding": 2.8,
            "Method": [
                "Chameleon-30B",
                "https://huggingface.co/facebook/chameleon-30b"
            ],
            "Parameters": "30B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 310
        },
        {
            "Overall": 63.6,
            "AR": 70.2,
            "CP": 71.3,
            "FP-C": 62.9,
            "FP-S": 63.3,
            "LR": 38.6,
            "RR": 60.1,
            "action_recognition": 87.2,
            "attribute_comparison": 62.7,
            "attribute_recognition": 76.4,
            "celebrity_recognition": 47.6,
            "function_reasoning": 82.2,
            "future_prediction": 41.3,
            "identity_reasoning": 96.1,
            "image_emotion": 75.6,
            "image_quality": 44.4,
            "image_scene": 85.4,
            "image_style": 57.6,
            "image_topic": 95.6,
            "nature_relation": 62.0,
            "object_localization": 51.4,
            "ocr": 90.0,
            "physical_property_reasoning": 31.6,
            "physical_relation": 36.0,
            "social_relation": 78.0,
            "spatial_relationship": 25.3,
            "structuralized_imagetext_understanding": 36.7,
            "Method": [
                "Cambrian-13B",
                "https://huggingface.co/nyu-visionx/cambrian-13b"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "NYU",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 311
        },
        {
            "Overall": 76.1,
            "AR": 86.1,
            "CP": 77.6,
            "FP-C": 68.5,
            "FP-S": 81.4,
            "LR": 58.7,
            "RR": 74.4,
            "action_recognition": 85.5,
            "attribute_comparison": 69.3,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 76.2,
            "function_reasoning": 91.1,
            "future_prediction": 72.0,
            "identity_reasoning": 96.1,
            "image_emotion": 82.2,
            "image_quality": 50.0,
            "image_scene": 84.0,
            "image_style": 79.3,
            "image_topic": 98.9,
            "nature_relation": 90.2,
            "object_localization": 70.5,
            "ocr": 93.3,
            "physical_property_reasoning": 70.9,
            "physical_relation": 45.3,
            "social_relation": 82.4,
            "spatial_relationship": 41.3,
            "structuralized_imagetext_understanding": 49.5,
            "Method": [
                "Yi-Vision",
                "https://platform.lingyiwanwu.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "01-AI",
            "Time": "2024/08/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 312
        },
        {
            "Overall": 76.2,
            "AR": 81.2,
            "CP": 78.1,
            "FP-C": 70.8,
            "FP-S": 80.5,
            "LR": 62.5,
            "RR": 75.2,
            "action_recognition": 82.1,
            "attribute_comparison": 69.3,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 73.5,
            "function_reasoning": 88.9,
            "future_prediction": 74.7,
            "identity_reasoning": 97.4,
            "image_emotion": 81.1,
            "image_quality": 56.5,
            "image_scene": 86.1,
            "image_style": 73.9,
            "image_topic": 96.7,
            "nature_relation": 78.3,
            "object_localization": 68.6,
            "ocr": 92.2,
            "physical_property_reasoning": 57.0,
            "physical_relation": 61.3,
            "social_relation": 83.5,
            "spatial_relationship": 54.7,
            "structuralized_imagetext_understanding": 54.1,
            "Method": [
                "Ovis1.5-Gemma2-9B",
                "https://huggingface.co/AIDC-AI/Ovis1.5-Gemma2-9B"
            ],
            "Parameters": "11.4B",
            "Language Model": "Gemma2-9B-It",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/08/04",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 313
        },
        {
            "Overall": 67.5,
            "AR": 80.0,
            "CP": 74.1,
            "FP-C": 65.5,
            "FP-S": 68.2,
            "LR": 45.1,
            "RR": 58.9,
            "action_recognition": 85.5,
            "attribute_comparison": 60.0,
            "attribute_recognition": 74.2,
            "celebrity_recognition": 65.3,
            "function_reasoning": 83.3,
            "future_prediction": 69.3,
            "identity_reasoning": 93.4,
            "image_emotion": 78.9,
            "image_quality": 43.5,
            "image_scene": 86.8,
            "image_style": 68.5,
            "image_topic": 96.7,
            "nature_relation": 52.2,
            "object_localization": 53.3,
            "ocr": 84.4,
            "physical_property_reasoning": 63.3,
            "physical_relation": 42.7,
            "social_relation": 79.1,
            "spatial_relationship": 40.0,
            "structuralized_imagetext_understanding": 28.4,
            "Method": [
                "LLaVA-Next-Llama3",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "ByteDance",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 307
        },
        {
            "Overall": 70.9,
            "AR": 84.5,
            "CP": 75.6,
            "FP-C": 69.3,
            "FP-S": 72.4,
            "LR": 45.1,
            "RR": 65.9,
            "action_recognition": 88.9,
            "attribute_comparison": 73.3,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 74.1,
            "function_reasoning": 86.7,
            "future_prediction": 64.0,
            "identity_reasoning": 97.4,
            "image_emotion": 77.8,
            "image_quality": 50.0,
            "image_scene": 88.2,
            "image_style": 67.4,
            "image_topic": 96.7,
            "nature_relation": 81.5,
            "object_localization": 44.8,
            "ocr": 90.0,
            "physical_property_reasoning": 69.6,
            "physical_relation": 33.3,
            "social_relation": 76.9,
            "spatial_relationship": 34.7,
            "structuralized_imagetext_understanding": 32.1,
            "Method": [
                "LLaVA-Next-Interleave-7B-DPO",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen1.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/07/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 308
        },
        {
            "Overall": 69.4,
            "AR": 80.8,
            "CP": 72.6,
            "FP-C": 66.7,
            "FP-S": 71.7,
            "LR": 47.3,
            "RR": 66.3,
            "action_recognition": 88.9,
            "attribute_comparison": 69.3,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 78.2,
            "function_reasoning": 85.6,
            "future_prediction": 68.0,
            "identity_reasoning": 94.7,
            "image_emotion": 68.9,
            "image_quality": 42.7,
            "image_scene": 84.7,
            "image_style": 73.9,
            "image_topic": 96.7,
            "nature_relation": 76.1,
            "object_localization": 36.2,
            "ocr": 87.8,
            "physical_property_reasoning": 62.0,
            "physical_relation": 36.0,
            "social_relation": 81.3,
            "spatial_relationship": 29.3,
            "structuralized_imagetext_understanding": 33.0,
            "Method": [
                "LLaVA-Next-Interleave-7B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen1.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 314
        },
        {
            "Overall": 77.1,
            "AR": 85.3,
            "CP": 78.0,
            "FP-C": 71.2,
            "FP-S": 84.2,
            "LR": 56.0,
            "RR": 77.1,
            "action_recognition": 88.9,
            "attribute_comparison": 64.0,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 86.4,
            "function_reasoning": 93.3,
            "future_prediction": 76.0,
            "identity_reasoning": 98.7,
            "image_emotion": 83.3,
            "image_quality": 48.4,
            "image_scene": 89.6,
            "image_style": 75.0,
            "image_topic": 97.8,
            "nature_relation": 94.6,
            "object_localization": 67.6,
            "ocr": 94.4,
            "physical_property_reasoning": 63.3,
            "physical_relation": 50.7,
            "social_relation": 81.3,
            "spatial_relationship": 50.7,
            "structuralized_imagetext_understanding": 42.2,
            "Method": [
                "LLaVA-Next-Qwen-32B",
                "https://llava-vl.github.io/blog/2024-01-30-llava-next/"
            ],
            "Parameters": "33B",
            "Language Model": "Qwen1.5-32B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 315
        },
        {
            "Overall": 61.5,
            "AR": 76.3,
            "CP": 69.4,
            "FP-C": 53.9,
            "FP-S": 61.7,
            "LR": 38.0,
            "RR": 55.0,
            "action_recognition": 86.3,
            "attribute_comparison": 38.7,
            "attribute_recognition": 71.9,
            "celebrity_recognition": 70.1,
            "function_reasoning": 83.3,
            "future_prediction": 62.7,
            "identity_reasoning": 93.4,
            "image_emotion": 75.6,
            "image_quality": 24.2,
            "image_scene": 86.1,
            "image_style": 69.6,
            "image_topic": 98.9,
            "nature_relation": 53.3,
            "object_localization": 31.4,
            "ocr": 73.3,
            "physical_property_reasoning": 51.9,
            "physical_relation": 22.7,
            "social_relation": 83.5,
            "spatial_relationship": 18.7,
            "structuralized_imagetext_understanding": 21.1,
            "Method": [
                "Mantis-8B-clip-llama3",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-clip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 316
        },
        {
            "Overall": 63.1,
            "AR": 79.2,
            "CP": 71.7,
            "FP-C": 54.7,
            "FP-S": 66.1,
            "LR": 39.7,
            "RR": 50.0,
            "action_recognition": 88.9,
            "attribute_comparison": 33.3,
            "attribute_recognition": 77.5,
            "celebrity_recognition": 68.7,
            "function_reasoning": 88.9,
            "future_prediction": 72.0,
            "identity_reasoning": 97.4,
            "image_emotion": 77.8,
            "image_quality": 28.2,
            "image_scene": 87.5,
            "image_style": 75.0,
            "image_topic": 96.7,
            "nature_relation": 43.5,
            "object_localization": 36.2,
            "ocr": 85.6,
            "physical_property_reasoning": 50.6,
            "physical_relation": 24.0,
            "social_relation": 78.0,
            "spatial_relationship": 22.7,
            "structuralized_imagetext_understanding": 17.4,
            "Method": [
                "Mantis-8B-siglip-llama3",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-siglip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 317
        },
        {
            "Overall": 65.8,
            "AR": 75.1,
            "CP": 71.7,
            "FP-C": 64.0,
            "FP-S": 69.1,
            "LR": 44.0,
            "RR": 56.6,
            "action_recognition": 87.2,
            "attribute_comparison": 60.0,
            "attribute_recognition": 77.5,
            "celebrity_recognition": 65.3,
            "function_reasoning": 85.6,
            "future_prediction": 65.3,
            "identity_reasoning": 92.1,
            "image_emotion": 80.0,
            "image_quality": 33.9,
            "image_scene": 84.0,
            "image_style": 70.7,
            "image_topic": 96.7,
            "nature_relation": 47.8,
            "object_localization": 50.5,
            "ocr": 88.9,
            "physical_property_reasoning": 46.8,
            "physical_relation": 36.0,
            "social_relation": 82.4,
            "spatial_relationship": 32.0,
            "structuralized_imagetext_understanding": 29.4,
            "Method": [
                "Mantis-8B-Idefics2",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-Idefics2"
            ],
            "Parameters": "8B",
            "Language Model": "Mistral-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "TIGER Lab",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 318
        },
        {
            "Overall": 76.9,
            "AR": 83.7,
            "CP": 77.8,
            "FP-C": 70.0,
            "FP-S": 84.7,
            "LR": 59.8,
            "RR": 75.2,
            "action_recognition": 83.8,
            "attribute_comparison": 73.3,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 85.0,
            "function_reasoning": 87.8,
            "future_prediction": 72.0,
            "identity_reasoning": 97.4,
            "image_emotion": 77.8,
            "image_quality": 55.6,
            "image_scene": 85.4,
            "image_style": 76.1,
            "image_topic": 97.8,
            "nature_relation": 84.8,
            "object_localization": 69.5,
            "ocr": 94.4,
            "physical_property_reasoning": 65.8,
            "physical_relation": 57.3,
            "social_relation": 80.2,
            "spatial_relationship": 45.3,
            "structuralized_imagetext_understanding": 51.4,
            "Method": [
                "MiniCPM-V-2.6",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-siglip-llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "OpenBMB",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 319
        },
        {
            "Overall": 79.2,
            "AR": 88.6,
            "CP": 80.2,
            "FP-C": 81.6,
            "FP-S": 74.7,
            "LR": 73.9,
            "RR": 77.1,
            "action_recognition": 94.9,
            "attribute_comparison": 77.3,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 56.5,
            "function_reasoning": 92.2,
            "future_prediction": 81.3,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 59.7,
            "image_scene": 88.2,
            "image_style": 80.4,
            "image_topic": 96.7,
            "nature_relation": 94.6,
            "object_localization": 68.6,
            "ocr": 96.7,
            "physical_property_reasoning": 75.9,
            "physical_relation": 48.0,
            "social_relation": 83.5,
            "spatial_relationship": 65.3,
            "structuralized_imagetext_understanding": 68.8,
            "Method": [
                "GPT-4o (0806, detail-high)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/08/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 320
        },
        {
            "Overall": 70.1,
            "AR": 82.9,
            "CP": 74.4,
            "FP-C": 68.2,
            "FP-S": 69.4,
            "LR": 45.7,
            "RR": 69.4,
            "action_recognition": 83.8,
            "attribute_comparison": 73.3,
            "attribute_recognition": 78.7,
            "celebrity_recognition": 61.2,
            "function_reasoning": 87.8,
            "future_prediction": 65.3,
            "identity_reasoning": 94.7,
            "image_emotion": 77.8,
            "image_quality": 50.0,
            "image_scene": 85.4,
            "image_style": 66.3,
            "image_topic": 95.6,
            "nature_relation": 68.5,
            "object_localization": 62.9,
            "ocr": 81.1,
            "physical_property_reasoning": 65.8,
            "physical_relation": 48.0,
            "social_relation": 87.9,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 32.1,
            "Method": [
                "Llama-3-MixSense-v1.1",
                "https://huggingface.co/Zero-Vision/Llama-3-MixSenseV1_1"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "Florence-2-Large-FT",
            "Org": "ZeroVision",
            "Time": "2024/08/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 321
        },
        {
            "Overall": 79.5,
            "AR": 85.3,
            "CP": 78.1,
            "FP-C": 74.2,
            "FP-S": 87.2,
            "LR": 63.6,
            "RR": 80.6,
            "action_recognition": 88.0,
            "attribute_comparison": 80.0,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 85.0,
            "function_reasoning": 94.4,
            "future_prediction": 81.3,
            "identity_reasoning": 98.7,
            "image_emotion": 83.3,
            "image_quality": 53.2,
            "image_scene": 85.4,
            "image_style": 76.1,
            "image_topic": 97.8,
            "nature_relation": 89.1,
            "object_localization": 77.1,
            "ocr": 95.6,
            "physical_property_reasoning": 62.0,
            "physical_relation": 58.7,
            "social_relation": 90.1,
            "spatial_relationship": 46.7,
            "structuralized_imagetext_understanding": 51.4,
            "Method": [
                "OmChat-v2.0-13B",
                "https://huggingface.co/omlab/omchat-v2.0-13B-single-beta_hf"
            ],
            "Parameters": "13B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "InternViT-6B",
            "Org": "Om AI",
            "Time": "2024/08/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 323
        },
        {
            "Overall": 69.2,
            "AR": 82.0,
            "CP": 71.1,
            "FP-C": 64.0,
            "FP-S": 74.9,
            "LR": 41.8,
            "RR": 68.6,
            "action_recognition": 83.8,
            "attribute_comparison": 68.0,
            "attribute_recognition": 78.7,
            "celebrity_recognition": 72.1,
            "function_reasoning": 86.7,
            "future_prediction": 69.3,
            "identity_reasoning": 96.1,
            "image_emotion": 68.9,
            "image_quality": 36.3,
            "image_scene": 87.5,
            "image_style": 69.6,
            "image_topic": 96.7,
            "nature_relation": 73.9,
            "object_localization": 61.9,
            "ocr": 91.1,
            "physical_property_reasoning": 63.3,
            "physical_relation": 48.0,
            "social_relation": 80.2,
            "spatial_relationship": 29.3,
            "structuralized_imagetext_understanding": 22.9,
            "Method": [
                "Parrot-7B",
                "https://huggingface.co/AIDC-AI/Parrot-7B"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Alibaba",
            "Time": "2024/08/22",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 324
        },
        {
            "Overall": 54.5,
            "AR": 77.6,
            "CP": 63.1,
            "FP-C": 49.4,
            "FP-S": 48.5,
            "LR": 24.5,
            "RR": 51.6,
            "action_recognition": 84.6,
            "attribute_comparison": 16.0,
            "attribute_recognition": 69.7,
            "celebrity_recognition": 34.7,
            "function_reasoning": 84.4,
            "future_prediction": 50.7,
            "identity_reasoning": 93.4,
            "image_emotion": 80.0,
            "image_quality": 20.2,
            "image_scene": 81.9,
            "image_style": 44.6,
            "image_topic": 94.4,
            "nature_relation": 50.0,
            "object_localization": 25.7,
            "ocr": 76.7,
            "physical_property_reasoning": 54.4,
            "physical_relation": 24.0,
            "social_relation": 75.8,
            "spatial_relationship": 28.0,
            "structuralized_imagetext_understanding": 6.4,
            "Method": [
                "VILA1.5-3B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-3b"
            ],
            "Parameters": "3B",
            "Language Model": "Sheared-LLaMA-2.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 325
        },
        {
            "Overall": 57.9,
            "AR": 69.8,
            "CP": 66.1,
            "FP-C": 57.7,
            "FP-S": 57.8,
            "LR": 27.2,
            "RR": 51.9,
            "action_recognition": 82.9,
            "attribute_comparison": 52.0,
            "attribute_recognition": 67.4,
            "celebrity_recognition": 58.5,
            "function_reasoning": 78.9,
            "future_prediction": 49.3,
            "identity_reasoning": 89.5,
            "image_emotion": 75.6,
            "image_quality": 23.4,
            "image_scene": 82.6,
            "image_style": 58.7,
            "image_topic": 96.7,
            "nature_relation": 56.5,
            "object_localization": 29.5,
            "ocr": 80.0,
            "physical_property_reasoning": 40.5,
            "physical_relation": 24.0,
            "social_relation": 70.3,
            "spatial_relationship": 24.0,
            "structuralized_imagetext_understanding": 11.9,
            "Method": [
                "Llama-3-VILA1.5-8B",
                "https://huggingface.co/Efficient-Large-Model/Llama-3-VILA1.5-8b"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 326
        },
        {
            "Overall": 65.2,
            "AR": 73.9,
            "CP": 72.8,
            "FP-C": 63.3,
            "FP-S": 63.3,
            "LR": 42.4,
            "RR": 62.4,
            "action_recognition": 82.9,
            "attribute_comparison": 61.3,
            "attribute_recognition": 82.0,
            "celebrity_recognition": 56.5,
            "function_reasoning": 84.4,
            "future_prediction": 65.3,
            "identity_reasoning": 97.4,
            "image_emotion": 81.1,
            "image_quality": 40.3,
            "image_scene": 84.0,
            "image_style": 66.3,
            "image_topic": 97.8,
            "nature_relation": 72.8,
            "object_localization": 37.1,
            "ocr": 86.7,
            "physical_property_reasoning": 39.2,
            "physical_relation": 32.0,
            "social_relation": 76.9,
            "spatial_relationship": 34.7,
            "structuralized_imagetext_understanding": 26.6,
            "Method": [
                "VILA1.5-13B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-13b"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "SigLIP-400M",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 327
        },
        {
            "Overall": 79.4,
            "AR": 86.1,
            "CP": 77.6,
            "FP-C": 79.0,
            "FP-S": 86.8,
            "LR": 62.0,
            "RR": 77.5,
            "action_recognition": 93.2,
            "attribute_comparison": 72.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 86.4,
            "function_reasoning": 94.4,
            "future_prediction": 85.3,
            "identity_reasoning": 97.4,
            "image_emotion": 77.8,
            "image_quality": 54.8,
            "image_scene": 86.1,
            "image_style": 75.0,
            "image_topic": 97.8,
            "nature_relation": 90.2,
            "object_localization": 74.3,
            "ocr": 95.6,
            "physical_property_reasoning": 65.8,
            "physical_relation": 53.3,
            "social_relation": 84.6,
            "spatial_relationship": 64.0,
            "structuralized_imagetext_understanding": 45.9,
            "Method": [
                "VILA1.5-40B",
                "https://huggingface.co/Efficient-Large-Model/VILA1.5-40b"
            ],
            "Parameters": "40B",
            "Language Model": "Yi-34B",
            "Vision Model": "InternViT-6B",
            "Org": "NVIDIA",
            "Time": "2024/08/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 328
        },
        {
            "Overall": 79.7,
            "AR": 85.3,
            "CP": 80.4,
            "FP-C": 76.8,
            "FP-S": 84.9,
            "LR": 66.8,
            "RR": 76.7,
            "action_recognition": 92.3,
            "attribute_comparison": 80.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 83.0,
            "function_reasoning": 88.9,
            "future_prediction": 81.3,
            "identity_reasoning": 98.7,
            "image_emotion": 78.9,
            "image_quality": 62.1,
            "image_scene": 87.5,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 79.3,
            "object_localization": 75.2,
            "ocr": 91.1,
            "physical_property_reasoning": 68.4,
            "physical_relation": 66.7,
            "social_relation": 82.4,
            "spatial_relationship": 49.3,
            "structuralized_imagetext_understanding": 56.9,
            "Org": "DataCanvas",
            "Time": "2024/08/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "MMAlaya2",
                "https://huggingface.co/DataCanvas/MMAlaya2"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2-20B",
            "Vision Model": "InternViT-6B",
            "key": 329
        },
        {
            "Overall": 71.9,
            "AR": 82.4,
            "CP": 74.8,
            "FP-C": 66.3,
            "FP-S": 74.0,
            "LR": 58.2,
            "RR": 68.2,
            "action_recognition": 85.5,
            "attribute_comparison": 64.0,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 71.4,
            "function_reasoning": 90.0,
            "future_prediction": 69.3,
            "identity_reasoning": 97.4,
            "image_emotion": 83.3,
            "image_quality": 41.1,
            "image_scene": 86.1,
            "image_style": 71.7,
            "image_topic": 97.8,
            "nature_relation": 76.1,
            "object_localization": 55.2,
            "ocr": 88.9,
            "physical_property_reasoning": 59.5,
            "physical_relation": 41.3,
            "social_relation": 82.4,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 50.5,
            "Org": "HuggingFace",
            "Time": "2024/08/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "Idefics3-8B-Llama3",
                "https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "SigLIP-400M",
            "key": 330
        },
        {
            "Overall": 62.8,
            "AR": 74.7,
            "CP": 70.0,
            "FP-C": 58.8,
            "FP-S": 56.6,
            "LR": 47.3,
            "RR": 61.6,
            "action_recognition": 76.9,
            "attribute_comparison": 57.3,
            "attribute_recognition": 68.5,
            "celebrity_recognition": 49.0,
            "function_reasoning": 81.1,
            "future_prediction": 57.3,
            "identity_reasoning": 92.1,
            "image_emotion": 78.9,
            "image_quality": 42.7,
            "image_scene": 82.6,
            "image_style": 55.4,
            "image_topic": 93.3,
            "nature_relation": 63.0,
            "object_localization": 32.4,
            "ocr": 85.6,
            "physical_property_reasoning": 50.6,
            "physical_relation": 33.3,
            "social_relation": 83.5,
            "spatial_relationship": 32.0,
            "structuralized_imagetext_understanding": 40.4,
            "Org": "Microsoft",
            "Time": "2024/08/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "Method": [
                "Phi-3.5-Vision",
                "https://huggingface.co/microsoft/Phi-3.5-vision-instruct"
            ],
            "Parameters": "4B",
            "Language Model": "Phi-3.5",
            "Vision Model": "CLIP ViT-L/14",
            "key": 331
        },
        {
            "Overall": 77.2,
            "AR": 80.4,
            "CP": 79.1,
            "FP-C": 71.5,
            "FP-S": 78.0,
            "LR": 66.3,
            "RR": 82.6,
            "action_recognition": 84.6,
            "attribute_comparison": 72.0,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 72.8,
            "function_reasoning": 86.7,
            "future_prediction": 80.0,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 58.9,
            "image_scene": 86.8,
            "image_style": 73.9,
            "image_topic": 96.7,
            "nature_relation": 93.5,
            "object_localization": 67.6,
            "ocr": 90.0,
            "physical_property_reasoning": 57.0,
            "physical_relation": 62.7,
            "social_relation": 87.9,
            "spatial_relationship": 50.7,
            "structuralized_imagetext_understanding": 56.9,
            "Org": "Monolith Foundation",
            "Time": "2024/08/30",
            "Verified": "No",
            "OpenSource": "Yes",
            "Method": [
                "Mirage-12B-v2.0",
                "https://huggingface.co/MonolithFoundation/Mirage-12B"
            ],
            "Parameters": "12B",
            "Language Model": "Mistral-12B",
            "Vision Model": "SigLIP-400M",
            "key": 332
        },
        {
            "Overall": 43.9,
            "AR": 64.1,
            "CP": 50.9,
            "FP-C": 44.9,
            "FP-S": 38.3,
            "LR": 23.4,
            "RR": 32.9,
            "action_recognition": 72.6,
            "attribute_comparison": 29.3,
            "attribute_recognition": 29.2,
            "celebrity_recognition": 34.0,
            "function_reasoning": 65.6,
            "future_prediction": 41.3,
            "identity_reasoning": 86.8,
            "image_emotion": 60.0,
            "image_quality": 5.6,
            "image_scene": 68.1,
            "image_style": 37.0,
            "image_topic": 91.1,
            "nature_relation": 30.4,
            "object_localization": 17.1,
            "ocr": 78.9,
            "physical_property_reasoning": 40.5,
            "physical_relation": 17.3,
            "social_relation": 48.4,
            "spatial_relationship": 17.3,
            "structuralized_imagetext_understanding": 11.0,
            "Method": [
                "LLaVA-v1.5-7B",
                "https://arxiv.org/abs/2310.03744"
            ],
            "Parameters": "7.2B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2023/10/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 186
        },
        {
            "Overall": 55.5,
            "AR": 68.6,
            "CP": 64.4,
            "FP-C": 52.4,
            "FP-S": 52.7,
            "LR": 30.4,
            "RR": 50.0,
            "action_recognition": 75.2,
            "attribute_comparison": 50.7,
            "attribute_recognition": 55.1,
            "celebrity_recognition": 46.9,
            "function_reasoning": 78.9,
            "future_prediction": 52.0,
            "identity_reasoning": 90.8,
            "image_emotion": 65.6,
            "image_quality": 32.3,
            "image_scene": 79.2,
            "image_style": 52.2,
            "image_topic": 96.7,
            "nature_relation": 40.2,
            "object_localization": 36.2,
            "ocr": 78.9,
            "physical_property_reasoning": 35.4,
            "physical_relation": 30.7,
            "social_relation": 75.8,
            "spatial_relationship": 18.7,
            "structuralized_imagetext_understanding": 15.6,
            "Method": [
                "LLaVA-v1.5-13B",
                "https://arxiv.org/abs/2310.03744"
            ],
            "Parameters": "13.4B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "University of Wisconsin–Madison",
            "Time": "2023/10/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 188
        },
        {
            "Overall": 64.2,
            "AR": 72.7,
            "CP": 71.1,
            "FP-C": 63.3,
            "FP-S": 63.6,
            "LR": 34.2,
            "RR": 64.7,
            "action_recognition": 83.8,
            "attribute_comparison": 69.3,
            "attribute_recognition": 73.0,
            "celebrity_recognition": 46.9,
            "function_reasoning": 84.4,
            "future_prediction": 48.0,
            "identity_reasoning": 92.1,
            "image_emotion": 74.4,
            "image_quality": 45.2,
            "image_scene": 85.4,
            "image_style": 59.8,
            "image_topic": 92.2,
            "nature_relation": 73.9,
            "object_localization": 58.1,
            "ocr": 87.8,
            "physical_property_reasoning": 40.5,
            "physical_relation": 36.0,
            "social_relation": 79.1,
            "spatial_relationship": 25.3,
            "structuralized_imagetext_understanding": 24.8,
            "Method": [
                "XGen-MM-Instruct-Interleave-v1.5",
                "https://huggingface.co/Salesforce/xgen-mm-phi3-mini-instruct-interleave-r-v1.5"
            ],
            "Parameters": "4.4B",
            "Language Model": "Phi-3",
            "Vision Model": "SigLIP-400M",
            "Org": "Salesforce",
            "Time": "2024/09/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 333
        },
        {
            "Overall": 65.5,
            "AR": 78.8,
            "CP": 72.0,
            "FP-C": 59.9,
            "FP-S": 62.9,
            "LR": 39.1,
            "RR": 67.8,
            "action_recognition": 82.1,
            "attribute_comparison": 64.0,
            "attribute_recognition": 74.2,
            "celebrity_recognition": 50.3,
            "function_reasoning": 87.8,
            "future_prediction": 54.7,
            "identity_reasoning": 92.1,
            "image_emotion": 75.6,
            "image_quality": 44.4,
            "image_scene": 84.7,
            "image_style": 63.0,
            "image_topic": 95.6,
            "nature_relation": 75.0,
            "object_localization": 54.3,
            "ocr": 82.2,
            "physical_property_reasoning": 55.7,
            "physical_relation": 38.7,
            "social_relation": 84.6,
            "spatial_relationship": 21.3,
            "structuralized_imagetext_understanding": 28.4,
            "Method": [
                "XGen-MM-Instruct-DPO-v1.5",
                "https://huggingface.co/Salesforce/xgen-mm-phi3-mini-instruct-dpo-r-v1.5"
            ],
            "Parameters": "4.4B",
            "Language Model": "Phi-3",
            "Vision Model": "SigLIP-400M",
            "Org": "Salesforce",
            "Time": "2024/09/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 334
        },
        {
            "Overall": 80.3,
            "AR": 84.1,
            "CP": 82.0,
            "FP-C": 76.4,
            "FP-S": 86.1,
            "LR": 64.1,
            "RR": 79.1,
            "action_recognition": 90.6,
            "attribute_comparison": 74.7,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 89.1,
            "function_reasoning": 88.9,
            "future_prediction": 74.7,
            "identity_reasoning": 98.7,
            "image_emotion": 86.7,
            "image_quality": 60.5,
            "image_scene": 88.2,
            "image_style": 82.6,
            "image_topic": 96.7,
            "nature_relation": 87.0,
            "object_localization": 68.6,
            "ocr": 97.8,
            "physical_property_reasoning": 64.6,
            "physical_relation": 57.3,
            "social_relation": 89.0,
            "spatial_relationship": 56.0,
            "structuralized_imagetext_understanding": 56.9,
            "Method": [
                "Qwen2-VL-7B",
                "https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/09/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 336
        },
        {
            "Overall": 71.2,
            "AR": 79.6,
            "CP": 73.3,
            "FP-C": 63.3,
            "FP-S": 78.0,
            "LR": 52.7,
            "RR": 69.0,
            "action_recognition": 88.9,
            "attribute_comparison": 56.0,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 84.4,
            "function_reasoning": 90.0,
            "future_prediction": 70.7,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 39.5,
            "image_scene": 87.5,
            "image_style": 67.4,
            "image_topic": 97.8,
            "nature_relation": 75.0,
            "object_localization": 52.4,
            "ocr": 91.1,
            "physical_property_reasoning": 50.6,
            "physical_relation": 42.7,
            "social_relation": 84.6,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 40.4,
            "Method": [
                "Qwen2-VL-2B",
                "https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct"
            ],
            "Parameters": "2B",
            "Language Model": "Qwen2-1.5B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/09/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 337
        },
        {
            "Overall": 31.8,
            "AR": 41.6,
            "CP": 43.9,
            "FP-C": 26.6,
            "FP-S": 23.7,
            "LR": 19.6,
            "RR": 24.8,
            "action_recognition": 44.4,
            "attribute_comparison": 20.0,
            "attribute_recognition": 56.2,
            "celebrity_recognition": 12.9,
            "function_reasoning": 40.0,
            "future_prediction": 40.0,
            "identity_reasoning": 56.6,
            "image_emotion": 46.7,
            "image_quality": 8.1,
            "image_scene": 60.4,
            "image_style": 25.0,
            "image_topic": 83.3,
            "nature_relation": 21.7,
            "object_localization": 11.4,
            "ocr": 23.3,
            "physical_property_reasoning": 29.1,
            "physical_relation": 12.0,
            "social_relation": 38.5,
            "spatial_relationship": 5.3,
            "structuralized_imagetext_understanding": 5.5,
            "Method": [
                "Mantis-8B-Fuyu",
                "https://huggingface.co/TIGER-Lab/Mantis-8B-Fuyu"
            ],
            "Parameters": "8B",
            "Language Model": "Fuyu-8B",
            "Vision Model": "",
            "Org": "TIGER Lab",
            "Time": "2024/09/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 339
        },
        {
            "Overall": 54.3,
            "AR": 68.6,
            "CP": 64.3,
            "FP-C": 47.6,
            "FP-S": 50.1,
            "LR": 26.6,
            "RR": 53.9,
            "action_recognition": 80.3,
            "attribute_comparison": 26.7,
            "attribute_recognition": 64.0,
            "celebrity_recognition": 50.3,
            "function_reasoning": 78.9,
            "future_prediction": 52.0,
            "identity_reasoning": 92.1,
            "image_emotion": 76.7,
            "image_quality": 20.2,
            "image_scene": 81.2,
            "image_style": 57.6,
            "image_topic": 92.2,
            "nature_relation": 63.0,
            "object_localization": 23.8,
            "ocr": 66.7,
            "physical_property_reasoning": 34.2,
            "physical_relation": 26.7,
            "social_relation": 67.0,
            "spatial_relationship": 17.3,
            "structuralized_imagetext_understanding": 9.2,
            "Method": [
                "Slime-7B",
                "https://huggingface.co/yifanzhang114/SliME-vicuna-7B"
            ],
            "Parameters": "7B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 340
        },
        {
            "Overall": 63.7,
            "AR": 72.7,
            "CP": 73.9,
            "FP-C": 57.7,
            "FP-S": 63.1,
            "LR": 35.9,
            "RR": 61.2,
            "action_recognition": 83.8,
            "attribute_comparison": 45.3,
            "attribute_recognition": 70.8,
            "celebrity_recognition": 63.9,
            "function_reasoning": 85.6,
            "future_prediction": 72.0,
            "identity_reasoning": 97.4,
            "image_emotion": 81.1,
            "image_quality": 41.9,
            "image_scene": 88.2,
            "image_style": 65.2,
            "image_topic": 96.7,
            "nature_relation": 66.3,
            "object_localization": 49.5,
            "ocr": 70.0,
            "physical_property_reasoning": 34.2,
            "physical_relation": 40.0,
            "social_relation": 73.6,
            "spatial_relationship": 29.3,
            "structuralized_imagetext_understanding": 11.0,
            "Method": [
                "Slime-8B",
                "https://huggingface.co/yifanzhang114/SliME-Llama3-8B"
            ],
            "Parameters": "8B",
            "Language Model": "Llama-3-8B-Instruct",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 341
        },
        {
            "Overall": 56.8,
            "AR": 67.8,
            "CP": 69.4,
            "FP-C": 47.6,
            "FP-S": 52.0,
            "LR": 27.2,
            "RR": 58.5,
            "action_recognition": 80.3,
            "attribute_comparison": 22.7,
            "attribute_recognition": 65.2,
            "celebrity_recognition": 51.7,
            "function_reasoning": 77.8,
            "future_prediction": 49.3,
            "identity_reasoning": 93.4,
            "image_emotion": 81.1,
            "image_quality": 33.9,
            "image_scene": 80.6,
            "image_style": 62.0,
            "image_topic": 96.7,
            "nature_relation": 67.4,
            "object_localization": 26.7,
            "ocr": 68.9,
            "physical_property_reasoning": 31.6,
            "physical_relation": 29.3,
            "social_relation": 73.6,
            "spatial_relationship": 21.3,
            "structuralized_imagetext_understanding": 11.9,
            "Method": [
                "Slime-13B",
                "https://huggingface.co/yifanzhang114/SliME-vicuna-13B"
            ],
            "Parameters": "13B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Institute of Automation",
            "Time": "2024/09/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 342
        },
        {
            "Overall": 70.1,
            "AR": 82.0,
            "CP": 70.2,
            "FP-C": 64.0,
            "FP-S": 75.9,
            "LR": 60.3,
            "RR": 62.4,
            "action_recognition": 72.6,
            "attribute_comparison": 66.7,
            "attribute_recognition": 83.1,
            "celebrity_recognition": 73.5,
            "function_reasoning": 92.2,
            "future_prediction": 65.3,
            "identity_reasoning": 93.4,
            "image_emotion": 67.8,
            "image_quality": 40.3,
            "image_scene": 80.6,
            "image_style": 69.6,
            "image_topic": 97.8,
            "nature_relation": 65.2,
            "object_localization": 61.0,
            "ocr": 90.0,
            "physical_property_reasoning": 59.5,
            "physical_relation": 42.7,
            "social_relation": 75.8,
            "spatial_relationship": 48.0,
            "structuralized_imagetext_understanding": 56.9,
            "Method": [
                "Pixtral-12B",
                "https://huggingface.co/mistralai/Pixtral-12B-2409"
            ],
            "Parameters": "13B",
            "Language Model": "Nemo-12B",
            "Vision Model": "ViT-400M",
            "Org": "Mistral AI",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 343
        },
        {
            "Overall": 76.7,
            "AR": 83.3,
            "CP": 78.5,
            "FP-C": 73.8,
            "FP-S": 82.8,
            "LR": 63.6,
            "RR": 69.0,
            "action_recognition": 82.9,
            "attribute_comparison": 66.7,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 85.7,
            "function_reasoning": 87.8,
            "future_prediction": 70.7,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 53.2,
            "image_scene": 86.1,
            "image_style": 81.5,
            "image_topic": 96.7,
            "nature_relation": 87.0,
            "object_localization": 67.6,
            "ocr": 87.8,
            "physical_property_reasoning": 64.6,
            "physical_relation": 45.3,
            "social_relation": 70.3,
            "spatial_relationship": 66.7,
            "structuralized_imagetext_understanding": 58.7,
            "Method": [
                "Gemini-1.5-Flash",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 344
        },
        {
            "Overall": 53.9,
            "AR": 73.5,
            "CP": 61.1,
            "FP-C": 48.3,
            "FP-S": 50.8,
            "LR": 28.3,
            "RR": 49.2,
            "action_recognition": 82.9,
            "attribute_comparison": 22.7,
            "attribute_recognition": 65.2,
            "celebrity_recognition": 47.6,
            "function_reasoning": 76.7,
            "future_prediction": 56.0,
            "identity_reasoning": 92.1,
            "image_emotion": 76.7,
            "image_quality": 8.9,
            "image_scene": 81.2,
            "image_style": 47.8,
            "image_topic": 98.9,
            "nature_relation": 48.9,
            "object_localization": 15.2,
            "ocr": 83.3,
            "physical_property_reasoning": 51.9,
            "physical_relation": 34.7,
            "social_relation": 61.5,
            "spatial_relationship": 20.0,
            "structuralized_imagetext_understanding": 9.2,
            "Method": [
                "LLaVA-OneVision-0.5B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-0.5b-ov"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 345
        },
        {
            "Overall": 80.9,
            "AR": 86.5,
            "CP": 82.4,
            "FP-C": 75.7,
            "FP-S": 84.7,
            "LR": 66.3,
            "RR": 81.8,
            "action_recognition": 89.7,
            "attribute_comparison": 76.0,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 81.0,
            "function_reasoning": 94.4,
            "future_prediction": 78.7,
            "identity_reasoning": 98.7,
            "image_emotion": 90.0,
            "image_quality": 58.9,
            "image_scene": 90.3,
            "image_style": 79.3,
            "image_topic": 97.8,
            "nature_relation": 91.3,
            "object_localization": 76.2,
            "ocr": 91.1,
            "physical_property_reasoning": 65.8,
            "physical_relation": 65.3,
            "social_relation": 85.7,
            "spatial_relationship": 53.3,
            "structuralized_imagetext_understanding": 57.8,
            "Method": [
                "LLaVA-OneVision-7B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-7b-ov"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 346
        },
        {
            "Overall": 47.6,
            "AR": 70.2,
            "CP": 58.3,
            "FP-C": 38.2,
            "FP-S": 44.1,
            "LR": 21.2,
            "RR": 38.4,
            "action_recognition": 77.8,
            "attribute_comparison": 4.0,
            "attribute_recognition": 58.4,
            "celebrity_recognition": 42.2,
            "function_reasoning": 73.3,
            "future_prediction": 49.3,
            "identity_reasoning": 89.5,
            "image_emotion": 73.3,
            "image_quality": 3.2,
            "image_scene": 81.2,
            "image_style": 45.7,
            "image_topic": 95.6,
            "nature_relation": 37.0,
            "object_localization": 8.6,
            "ocr": 74.4,
            "physical_property_reasoning": 48.1,
            "physical_relation": 14.7,
            "social_relation": 59.3,
            "spatial_relationship": 10.7,
            "structuralized_imagetext_understanding": 1.8,
            "Method": [
                "LLaVA-OneVision-0.5B (SI)",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-0.5b-si"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 347
        },
        {
            "Overall": 75.8,
            "AR": 84.9,
            "CP": 77.6,
            "FP-C": 68.5,
            "FP-S": 78.4,
            "LR": 57.6,
            "RR": 79.5,
            "action_recognition": 88.0,
            "attribute_comparison": 68.0,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 76.2,
            "function_reasoning": 94.4,
            "future_prediction": 80.0,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 52.4,
            "image_scene": 88.2,
            "image_style": 70.7,
            "image_topic": 97.8,
            "nature_relation": 89.1,
            "object_localization": 62.9,
            "ocr": 93.3,
            "physical_property_reasoning": 62.0,
            "physical_relation": 53.3,
            "social_relation": 91.2,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 42.2,
            "Method": [
                "LLaVA-OneVision-7B (SI)",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-7b-si"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 348
        },
        {
            "Overall": 68.7,
            "AR": 80.8,
            "CP": 71.1,
            "FP-C": 66.7,
            "FP-S": 62.9,
            "LR": 63.0,
            "RR": 68.2,
            "action_recognition": 82.9,
            "attribute_comparison": 68.0,
            "attribute_recognition": 61.8,
            "celebrity_recognition": 61.2,
            "function_reasoning": 83.3,
            "future_prediction": 73.3,
            "identity_reasoning": 93.4,
            "image_emotion": 73.3,
            "image_quality": 56.5,
            "image_scene": 72.2,
            "image_style": 67.4,
            "image_topic": 91.1,
            "nature_relation": 85.9,
            "object_localization": 48.6,
            "ocr": 83.3,
            "physical_property_reasoning": 65.8,
            "physical_relation": 53.3,
            "social_relation": 62.6,
            "spatial_relationship": 40.0,
            "structuralized_imagetext_understanding": 56.0,
            "Method": [
                "Qwen-VL-Plus-0809",
                "https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-qianwen-vl-plus-api"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Alibaba",
            "Time": "2024/09/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 349
        },
        {
            "Overall": 81.9,
            "AR": 90.2,
            "CP": 80.4,
            "FP-C": 81.3,
            "FP-S": 84.7,
            "LR": 66.3,
            "RR": 84.1,
            "action_recognition": 88.9,
            "attribute_comparison": 78.7,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 83.0,
            "function_reasoning": 95.6,
            "future_prediction": 82.7,
            "identity_reasoning": 100.0,
            "image_emotion": 82.2,
            "image_quality": 59.7,
            "image_scene": 86.1,
            "image_style": 80.4,
            "image_topic": 97.8,
            "nature_relation": 95.7,
            "object_localization": 72.4,
            "ocr": 94.4,
            "physical_property_reasoning": 74.7,
            "physical_relation": 64.0,
            "social_relation": 89.0,
            "spatial_relationship": 72.0,
            "structuralized_imagetext_understanding": 55.0,
            "Method": [
                "LLaVA-OneVision-72B (SI)",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-72b-si"
            ],
            "Parameters": "73B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 350
        },
        {
            "Overall": 83.9,
            "AR": 91.0,
            "CP": 83.0,
            "FP-C": 83.5,
            "FP-S": 87.7,
            "LR": 70.7,
            "RR": 82.9,
            "action_recognition": 89.7,
            "attribute_comparison": 88.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 85.7,
            "function_reasoning": 94.4,
            "future_prediction": 86.7,
            "identity_reasoning": 100.0,
            "image_emotion": 84.4,
            "image_quality": 66.9,
            "image_scene": 88.2,
            "image_style": 79.3,
            "image_topic": 98.9,
            "nature_relation": 88.0,
            "object_localization": 80.0,
            "ocr": 94.4,
            "physical_property_reasoning": 78.5,
            "physical_relation": 66.7,
            "social_relation": 91.2,
            "spatial_relationship": 69.3,
            "structuralized_imagetext_understanding": 59.6,
            "Method": [
                "LLaVA-OneVision-72B",
                "https://huggingface.co/lmms-lab/llava-onevision-qwen2-72b-ov"
            ],
            "Parameters": "73B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/09/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 351
        },
        {
            "Overall": 79.5,
            "AR": 84.5,
            "CP": 78.9,
            "FP-C": 75.3,
            "FP-S": 84.9,
            "LR": 69.0,
            "RR": 78.7,
            "action_recognition": 84.6,
            "attribute_comparison": 76.0,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 79.6,
            "function_reasoning": 94.4,
            "future_prediction": 78.7,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 57.3,
            "image_scene": 83.3,
            "image_style": 79.3,
            "image_topic": 97.8,
            "nature_relation": 92.4,
            "object_localization": 77.1,
            "ocr": 95.6,
            "physical_property_reasoning": 60.8,
            "physical_relation": 57.3,
            "social_relation": 82.4,
            "spatial_relationship": 60.0,
            "structuralized_imagetext_understanding": 62.4,
            "Method": [
                "Ovis1.6-Gemma2-9B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B"
            ],
            "Parameters": "10.2B",
            "Language Model": "Gemma2-9B-It",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/09/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 352
        },
        {
            "Overall": 60.5,
            "AR": 74.3,
            "CP": 68.5,
            "FP-C": 54.3,
            "FP-S": 59.6,
            "LR": 33.2,
            "RR": 58.1,
            "action_recognition": 83.8,
            "attribute_comparison": 37.3,
            "attribute_recognition": 73.0,
            "celebrity_recognition": 51.0,
            "function_reasoning": 83.3,
            "future_prediction": 54.7,
            "identity_reasoning": 94.7,
            "image_emotion": 73.3,
            "image_quality": 34.7,
            "image_scene": 80.6,
            "image_style": 65.2,
            "image_topic": 94.4,
            "nature_relation": 62.0,
            "object_localization": 39.0,
            "ocr": 84.4,
            "physical_property_reasoning": 44.3,
            "physical_relation": 34.7,
            "social_relation": 73.6,
            "spatial_relationship": 25.3,
            "structuralized_imagetext_understanding": 18.3,
            "Method": [
                "Eagle-X5-7B",
                "https://huggingface.co/NVEagle/Eagle-X5-7B"
            ],
            "Parameters": "9B",
            "Language Model": "Vicuna-v1.5-7B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 353
        },
        {
            "Overall": 65.2,
            "AR": 76.7,
            "CP": 71.5,
            "FP-C": 58.1,
            "FP-S": 65.9,
            "LR": 40.2,
            "RR": 65.5,
            "action_recognition": 82.9,
            "attribute_comparison": 54.7,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 55.1,
            "function_reasoning": 81.1,
            "future_prediction": 64.0,
            "identity_reasoning": 94.7,
            "image_emotion": 72.2,
            "image_quality": 37.9,
            "image_scene": 84.7,
            "image_style": 69.6,
            "image_topic": 97.8,
            "nature_relation": 68.5,
            "object_localization": 51.4,
            "ocr": 86.7,
            "physical_property_reasoning": 54.4,
            "physical_relation": 48.0,
            "social_relation": 76.9,
            "spatial_relationship": 22.7,
            "structuralized_imagetext_understanding": 23.9,
            "Method": [
                "Eagle-X5-13B",
                "https://huggingface.co/NVEagle/Eagle-X5-13B"
            ],
            "Parameters": "15B",
            "Language Model": "Vicuna-v1.5-13B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 354
        },
        {
            "Overall": 18.6,
            "AR": 21.6,
            "CP": 20.6,
            "FP-C": 11.2,
            "FP-S": 22.3,
            "LR": 13.6,
            "RR": 17.1,
            "action_recognition": 14.5,
            "attribute_comparison": 10.7,
            "attribute_recognition": 13.5,
            "celebrity_recognition": 12.9,
            "function_reasoning": 16.7,
            "future_prediction": 18.7,
            "identity_reasoning": 35.5,
            "image_emotion": 25.6,
            "image_quality": 5.6,
            "image_scene": 27.1,
            "image_style": 21.7,
            "image_topic": 24.4,
            "nature_relation": 25.0,
            "object_localization": 5.7,
            "ocr": 65.6,
            "physical_property_reasoning": 13.9,
            "physical_relation": 5.3,
            "social_relation": 18.7,
            "spatial_relationship": 6.7,
            "structuralized_imagetext_understanding": 10.1,
            "Method": [
                "Moondream1",
                "https://huggingface.co/vikhyatk/moondream1"
            ],
            "Parameters": "1.9B",
            "Language Model": "SigLIP-400M",
            "Vision Model": "Phi-1.5",
            "Org": "Moondream",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 355
        },
        {
            "Overall": 68.3,
            "AR": 82.0,
            "CP": 74.4,
            "FP-C": 61.4,
            "FP-S": 68.4,
            "LR": 49.5,
            "RR": 62.4,
            "action_recognition": 87.2,
            "attribute_comparison": 49.3,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 60.5,
            "function_reasoning": 86.7,
            "future_prediction": 70.7,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 38.7,
            "image_scene": 88.2,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 63.0,
            "object_localization": 44.8,
            "ocr": 92.2,
            "physical_property_reasoning": 62.0,
            "physical_relation": 37.3,
            "social_relation": 82.4,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 34.9,
            "Method": [
                "MiniMonkey",
                "https://huggingface.co/mx262/MiniMonkey"
            ],
            "Parameters": "2.2B",
            "Language Model": "InternLM2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "HUST",
            "Time": "2024/09/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 357
        },
        {
            "Overall": 74.2,
            "AR": 79.6,
            "CP": 77.8,
            "FP-C": 64.8,
            "FP-S": 80.7,
            "LR": 57.1,
            "RR": 72.9,
            "action_recognition": 88.0,
            "attribute_comparison": 57.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 86.4,
            "function_reasoning": 88.9,
            "future_prediction": 77.3,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 50.8,
            "image_scene": 87.5,
            "image_style": 76.1,
            "image_topic": 98.9,
            "nature_relation": 76.1,
            "object_localization": 56.2,
            "ocr": 92.2,
            "physical_property_reasoning": 51.9,
            "physical_relation": 56.0,
            "social_relation": 83.5,
            "spatial_relationship": 36.0,
            "structuralized_imagetext_understanding": 43.1,
            "Method": [
                "XinYuan-VL-2B-Instruct",
                "https://huggingface.co/Cylingo/Xinyuan-VL-2B"
            ],
            "Parameters": "2B",
            "Language Model": "Qwen2-1.5B",
            "Vision Model": "QwenViT",
            "Org": "Cylingo",
            "Time": "2024/09/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 359
        },
        {
            "Overall": 64.2,
            "AR": 75.9,
            "CP": 67.6,
            "FP-C": 55.1,
            "FP-S": 70.8,
            "LR": 41.8,
            "RR": 60.5,
            "action_recognition": 76.9,
            "attribute_comparison": 45.3,
            "attribute_recognition": 74.2,
            "celebrity_recognition": 70.7,
            "function_reasoning": 87.8,
            "future_prediction": 61.3,
            "identity_reasoning": 92.1,
            "image_emotion": 71.1,
            "image_quality": 33.1,
            "image_scene": 82.6,
            "image_style": 57.6,
            "image_topic": 97.8,
            "nature_relation": 66.3,
            "object_localization": 52.4,
            "ocr": 88.9,
            "physical_property_reasoning": 46.8,
            "physical_relation": 33.3,
            "social_relation": 76.9,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 28.4,
            "Method": [
                "Llama-3.2-11B-Vision-Instruct",
                "https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct"
            ],
            "Parameters": "11B",
            "Language Model": "Llama-3.1-8B",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/10/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 360
        },
        {
            "Overall": 83.5,
            "AR": 87.3,
            "CP": 81.9,
            "FP-C": 81.3,
            "FP-S": 90.3,
            "LR": 73.4,
            "RR": 81.8,
            "action_recognition": 87.2,
            "attribute_comparison": 78.7,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 95.2,
            "function_reasoning": 93.3,
            "future_prediction": 85.3,
            "identity_reasoning": 98.7,
            "image_emotion": 78.9,
            "image_quality": 64.5,
            "image_scene": 88.9,
            "image_style": 82.6,
            "image_topic": 96.7,
            "nature_relation": 94.6,
            "object_localization": 78.1,
            "ocr": 94.4,
            "physical_property_reasoning": 69.6,
            "physical_relation": 58.7,
            "social_relation": 87.9,
            "spatial_relationship": 74.7,
            "structuralized_imagetext_understanding": 65.1,
            "Method": [
                "Step-1.5V",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "Step-1.5",
            "Vision Model": "stepencoder",
            "Org": "StepFun",
            "Time": "2024/10/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 322
        },
        {
            "Overall": 77.8,
            "AR": 85.3,
            "CP": 80.0,
            "FP-C": 69.3,
            "FP-S": 84.2,
            "LR": 65.2,
            "RR": 73.3,
            "action_recognition": 82.1,
            "attribute_comparison": 74.7,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 81.0,
            "function_reasoning": 87.8,
            "future_prediction": 78.7,
            "identity_reasoning": 96.1,
            "image_emotion": 83.3,
            "image_quality": 57.3,
            "image_scene": 88.2,
            "image_style": 77.2,
            "image_topic": 97.8,
            "nature_relation": 82.6,
            "object_localization": 75.2,
            "ocr": 94.4,
            "physical_property_reasoning": 72.2,
            "physical_relation": 46.7,
            "social_relation": 85.7,
            "spatial_relationship": 44.0,
            "structuralized_imagetext_understanding": 56.0,
            "Method": [
                "POINTS-Yi-1.5-9B",
                "https://huggingface.co/WePOINTS/POINTS-Yi-1-5-9B-Chat"
            ],
            "Parameters": "9.5B",
            "Language Model": "Yi-1.5-9B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "WeChat",
            "Time": "2024/10/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTS-Yi-1.5-9B-Chat",
            "key": 362
        },
        {
            "Overall": 76.9,
            "AR": 83.7,
            "CP": 78.9,
            "FP-C": 69.7,
            "FP-S": 82.8,
            "LR": 64.1,
            "RR": 73.3,
            "action_recognition": 82.9,
            "attribute_comparison": 72.0,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 78.2,
            "function_reasoning": 91.1,
            "future_prediction": 78.7,
            "identity_reasoning": 97.4,
            "image_emotion": 78.9,
            "image_quality": 58.1,
            "image_scene": 88.2,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 79.3,
            "object_localization": 73.3,
            "ocr": 95.6,
            "physical_property_reasoning": 62.0,
            "physical_relation": 54.7,
            "social_relation": 82.4,
            "spatial_relationship": 46.7,
            "structuralized_imagetext_understanding": 54.1,
            "Method": [
                "POINTS-Qwen2.5-7B",
                "https://huggingface.co/WePOINTS/POINTS-Qwen-2-5-7B-Chat"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen-2.5-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "WeChat",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTS-Qwen-2.5-7B-Chat",
            "key": 363
        },
        {
            "Overall": 0.9,
            "AR": 0.8,
            "CP": 0.9,
            "FP-C": 0.7,
            "FP-S": 1.6,
            "LR": 0.5,
            "RR": 0.4,
            "action_recognition": 1.7,
            "attribute_comparison": 0.0,
            "attribute_recognition": 2.2,
            "celebrity_recognition": 0.7,
            "function_reasoning": 2.2,
            "future_prediction": 1.3,
            "identity_reasoning": 0.0,
            "image_emotion": 0.0,
            "image_quality": 0.0,
            "image_scene": 0.7,
            "image_style": 0.0,
            "image_topic": 4.4,
            "nature_relation": 1.1,
            "object_localization": 1.0,
            "ocr": 3.3,
            "physical_property_reasoning": 0.0,
            "physical_relation": 0.0,
            "social_relation": 0.0,
            "spatial_relationship": 0.0,
            "structuralized_imagetext_understanding": 0.0,
            "Method": [
                "Kosmos2",
                "https://huggingface.co/microsoft/kosmos-2-patch14-224"
            ],
            "Parameters": "1.7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Microsoft",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kosmos2",
            "key": 364
        },
        {
            "Overall": 75.2,
            "AR": 82.0,
            "CP": 72.6,
            "FP-C": 66.7,
            "FP-S": 85.4,
            "LR": 59.2,
            "RR": 77.1,
            "action_recognition": 82.9,
            "attribute_comparison": 57.3,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 89.1,
            "function_reasoning": 88.9,
            "future_prediction": 70.7,
            "identity_reasoning": 97.4,
            "image_emotion": 64.4,
            "image_quality": 48.4,
            "image_scene": 85.4,
            "image_style": 67.4,
            "image_topic": 98.9,
            "nature_relation": 88.0,
            "object_localization": 72.4,
            "ocr": 94.4,
            "physical_property_reasoning": 59.5,
            "physical_relation": 52.0,
            "social_relation": 86.8,
            "spatial_relationship": 50.7,
            "structuralized_imagetext_understanding": 51.4,
            "Method": [
                "Llama-3.2-90B-Vision-Instruct",
                "https://huggingface.co/meta-llama/Llama-3.2-90B-Vision-Instruct"
            ],
            "Parameters": "88.6B",
            "Language Model": "Llama-3.1-70B",
            "Vision Model": "",
            "Org": "Meta",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Llama-3.2-90B-Vision-Instruct",
            "key": 365
        },
        {
            "Overall": 78.0,
            "AR": 85.3,
            "CP": 75.6,
            "FP-C": 76.4,
            "FP-S": 87.7,
            "LR": 58.7,
            "RR": 75.6,
            "action_recognition": 86.3,
            "attribute_comparison": 70.7,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 86.4,
            "function_reasoning": 94.4,
            "future_prediction": 64.0,
            "identity_reasoning": 98.7,
            "image_emotion": 72.2,
            "image_quality": 54.0,
            "image_scene": 83.3,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 84.8,
            "object_localization": 75.2,
            "ocr": 98.9,
            "physical_property_reasoning": 62.0,
            "physical_relation": 60.0,
            "social_relation": 79.1,
            "spatial_relationship": 66.7,
            "structuralized_imagetext_understanding": 55.0,
            "Method": [
                "NVLM-D-72B",
                "https://huggingface.co/nvidia/NVLM-D-72B"
            ],
            "Parameters": "79.4B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "InternViT-6B",
            "Org": "Nvidia",
            "Time": "2024/10/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "NVLM",
            "key": 366
        },
        {
            "Overall": 28.5,
            "AR": 31.4,
            "CP": 30.6,
            "FP-C": 25.1,
            "FP-S": 29.0,
            "LR": 15.8,
            "RR": 33.3,
            "action_recognition": 29.9,
            "attribute_comparison": 25.3,
            "attribute_recognition": 21.3,
            "celebrity_recognition": 21.1,
            "function_reasoning": 23.3,
            "future_prediction": 20.0,
            "identity_reasoning": 40.8,
            "image_emotion": 33.3,
            "image_quality": 17.7,
            "image_scene": 34.0,
            "image_style": 22.8,
            "image_topic": 47.8,
            "nature_relation": 43.5,
            "object_localization": 13.3,
            "ocr": 67.8,
            "physical_property_reasoning": 31.6,
            "physical_relation": 17.3,
            "social_relation": 36.3,
            "spatial_relationship": 17.3,
            "structuralized_imagetext_understanding": 12.8,
            "Method": [
                "Moondream2",
                "https://huggingface.co/vikhyatk/moondream2"
            ],
            "Parameters": "1.9B",
            "Language Model": "SigLIP-400M",
            "Vision Model": "Phi-1.5",
            "Org": "Moondream",
            "Time": "2024/10/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Moondream2",
            "key": 356
        },
        {
            "Overall": 71.6,
            "AR": 77.6,
            "CP": 72.8,
            "FP-C": 63.7,
            "FP-S": 78.0,
            "LR": 59.2,
            "RR": 69.8,
            "action_recognition": 77.8,
            "attribute_comparison": 66.7,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 72.1,
            "function_reasoning": 80.0,
            "future_prediction": 77.3,
            "identity_reasoning": 97.4,
            "image_emotion": 70.0,
            "image_quality": 47.6,
            "image_scene": 84.7,
            "image_style": 68.5,
            "image_topic": 95.6,
            "nature_relation": 78.3,
            "object_localization": 62.9,
            "ocr": 91.1,
            "physical_property_reasoning": 55.7,
            "physical_relation": 50.7,
            "social_relation": 76.9,
            "spatial_relationship": 38.7,
            "structuralized_imagetext_understanding": 46.8,
            "Method": [
                "Molmo-7B-D",
                "https://huggingface.co/allenai/Molmo-7B-D-0924"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 361,
            "dir_name": "molmo-7B-D-0924"
        },
        {
            "Overall": 56.8,
            "AR": 62.9,
            "CP": 65.2,
            "FP-C": 57.7,
            "FP-S": 49.0,
            "LR": 40.2,
            "RR": 57.4,
            "action_recognition": 70.9,
            "attribute_comparison": 62.7,
            "attribute_recognition": 61.8,
            "celebrity_recognition": 37.4,
            "function_reasoning": 62.2,
            "future_prediction": 56.0,
            "identity_reasoning": 88.2,
            "image_emotion": 68.9,
            "image_quality": 46.8,
            "image_scene": 75.0,
            "image_style": 46.7,
            "image_topic": 90.0,
            "nature_relation": 62.0,
            "object_localization": 27.6,
            "ocr": 80.0,
            "physical_property_reasoning": 39.2,
            "physical_relation": 37.3,
            "social_relation": 69.2,
            "spatial_relationship": 32.0,
            "structuralized_imagetext_understanding": 29.4,
            "Method": [
                "Molmo-7B-O",
                "https://huggingface.co/allenai/Molmo-7B-O-0924"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 367,
            "dir_name": "molmo-7B-O-0924"
        },
        {
            "Overall": 44.2,
            "AR": 55.9,
            "CP": 55.0,
            "FP-C": 40.4,
            "FP-S": 39.2,
            "LR": 25.5,
            "RR": 36.0,
            "action_recognition": 65.0,
            "attribute_comparison": 25.3,
            "attribute_recognition": 61.8,
            "celebrity_recognition": 29.3,
            "function_reasoning": 51.1,
            "future_prediction": 38.7,
            "identity_reasoning": 89.5,
            "image_emotion": 65.6,
            "image_quality": 21.0,
            "image_scene": 70.8,
            "image_style": 37.0,
            "image_topic": 84.4,
            "nature_relation": 27.2,
            "object_localization": 8.6,
            "ocr": 68.9,
            "physical_property_reasoning": 29.1,
            "physical_relation": 25.3,
            "social_relation": 53.8,
            "spatial_relationship": 17.3,
            "structuralized_imagetext_understanding": 16.5,
            "Method": [
                "MolmoE-1B",
                "https://huggingface.co/allenai/MolmoE-1B-0924"
            ],
            "Parameters": "7.2B",
            "Language Model": "OLMoE-1B-7B-0924",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "molmoE-1B-0924",
            "key": 368
        },
        {
            "Overall": 50.4,
            "AR": 65.7,
            "CP": 63.1,
            "FP-C": 43.4,
            "FP-S": 46.9,
            "LR": 19.0,
            "RR": 45.0,
            "action_recognition": 81.2,
            "attribute_comparison": 9.3,
            "attribute_recognition": 78.7,
            "celebrity_recognition": 38.1,
            "function_reasoning": 75.6,
            "future_prediction": 42.7,
            "identity_reasoning": 94.7,
            "image_emotion": 73.3,
            "image_quality": 16.9,
            "image_scene": 78.5,
            "image_style": 59.8,
            "image_topic": 95.6,
            "nature_relation": 46.7,
            "object_localization": 21.9,
            "ocr": 58.9,
            "physical_property_reasoning": 26.6,
            "physical_relation": 20.0,
            "social_relation": 63.7,
            "spatial_relationship": 18.7,
            "structuralized_imagetext_understanding": 2.8,
            "Method": [
                "Janus-1.3B",
                "https://huggingface.co/deepseek-ai/Janus-1.3B"
            ],
            "Parameters": "2.1B",
            "Language Model": "DeepSeek-1B",
            "Vision Model": "SigLIP-400M",
            "Org": "deepseek",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Janus-1.3B",
            "key": 370
        },
        {
            "Overall": 66.2,
            "AR": 76.3,
            "CP": 73.9,
            "FP-C": 58.1,
            "FP-S": 65.7,
            "LR": 50.5,
            "RR": 60.9,
            "action_recognition": 78.6,
            "attribute_comparison": 56.0,
            "attribute_recognition": 80.9,
            "celebrity_recognition": 59.2,
            "function_reasoning": 85.6,
            "future_prediction": 64.0,
            "identity_reasoning": 93.4,
            "image_emotion": 73.3,
            "image_quality": 37.9,
            "image_scene": 88.2,
            "image_style": 77.2,
            "image_topic": 97.8,
            "nature_relation": 56.5,
            "object_localization": 41.9,
            "ocr": 88.9,
            "physical_property_reasoning": 49.4,
            "physical_relation": 37.3,
            "social_relation": 84.6,
            "spatial_relationship": 28.0,
            "structuralized_imagetext_understanding": 41.3,
            "Method": [
                "Vintern-3B-beta",
                "https://huggingface.co/5CD-AI/Vintern-3B-beta"
            ],
            "Parameters": "3.7B",
            "Language Model": "Qwen-2.5-3B",
            "Vision Model": "InternViT-300M",
            "Org": "Fifth Civil Defender",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Vintern-3B-beta",
            "key": 371
        },
        {
            "Overall": 71.9,
            "AR": 84.9,
            "CP": 72.4,
            "FP-C": 65.2,
            "FP-S": 77.0,
            "LR": 58.7,
            "RR": 66.7,
            "action_recognition": 81.2,
            "attribute_comparison": 70.7,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 68.7,
            "function_reasoning": 87.8,
            "future_prediction": 73.3,
            "identity_reasoning": 98.7,
            "image_emotion": 82.2,
            "image_quality": 46.8,
            "image_scene": 84.0,
            "image_style": 56.5,
            "image_topic": 95.6,
            "nature_relation": 70.7,
            "object_localization": 66.7,
            "ocr": 94.4,
            "physical_property_reasoning": 68.4,
            "physical_relation": 44.0,
            "social_relation": 81.3,
            "spatial_relationship": 34.7,
            "structuralized_imagetext_understanding": 48.6,
            "Method": [
                "Ovis1.6-Llama3.2-3B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Llama3.2-3B"
            ],
            "Parameters": "4.1B",
            "Language Model": "Llama-3.2-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis1.6-Llama3.2-3B",
            "key": 372
        },
        {
            "Overall": 74.1,
            "AR": 83.3,
            "CP": 77.2,
            "FP-C": 67.4,
            "FP-S": 78.7,
            "LR": 53.8,
            "RR": 72.9,
            "action_recognition": 87.2,
            "attribute_comparison": 73.3,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 72.1,
            "function_reasoning": 88.9,
            "future_prediction": 73.3,
            "identity_reasoning": 96.1,
            "image_emotion": 82.2,
            "image_quality": 47.6,
            "image_scene": 86.8,
            "image_style": 76.1,
            "image_topic": 98.9,
            "nature_relation": 77.2,
            "object_localization": 66.7,
            "ocr": 92.2,
            "physical_property_reasoning": 64.6,
            "physical_relation": 52.0,
            "social_relation": 85.7,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 40.4,
            "Method": [
                "Aquila-VL-2B",
                "https://huggingface.co/BAAI/Aquila-VL-2B-llava-qwen"
            ],
            "Parameters": "2.2B",
            "Language Model": "Qwen-2.5-1.5B",
            "Vision Model": "SigLIP-400M",
            "Org": "BAAI",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Aquila-VL-2B",
            "key": 373
        },
        {
            "Overall": 79.6,
            "AR": 84.9,
            "CP": 78.7,
            "FP-C": 76.8,
            "FP-S": 83.1,
            "LR": 71.2,
            "RR": 79.8,
            "action_recognition": 80.3,
            "attribute_comparison": 74.7,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 72.8,
            "function_reasoning": 91.1,
            "future_prediction": 80.0,
            "identity_reasoning": 97.4,
            "image_emotion": 77.8,
            "image_quality": 59.7,
            "image_scene": 88.9,
            "image_style": 71.7,
            "image_topic": 96.7,
            "nature_relation": 87.0,
            "object_localization": 79.0,
            "ocr": 95.6,
            "physical_property_reasoning": 65.8,
            "physical_relation": 68.0,
            "social_relation": 82.4,
            "spatial_relationship": 73.3,
            "structuralized_imagetext_understanding": 65.1,
            "Method": [
                "Molmo-72B",
                "https://huggingface.co/allenai/Molmo-72B-0924"
            ],
            "Parameters": "73.3B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "AllenAI",
            "Time": "2024/10/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "molmo-72B-0924",
            "key": 377
        },
        {
            "Overall": 85.8,
            "AR": 88.6,
            "CP": 82.0,
            "FP-C": 88.0,
            "FP-S": 92.8,
            "LR": 79.9,
            "RR": 81.4,
            "action_recognition": 91.5,
            "attribute_comparison": 90.7,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 95.2,
            "function_reasoning": 91.1,
            "future_prediction": 85.3,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 64.5,
            "image_scene": 87.5,
            "image_style": 80.4,
            "image_topic": 98.9,
            "nature_relation": 89.1,
            "object_localization": 86.7,
            "ocr": 97.8,
            "physical_property_reasoning": 77.2,
            "physical_relation": 62.7,
            "social_relation": 89.0,
            "spatial_relationship": 80.0,
            "structuralized_imagetext_understanding": 76.1,
            "Method": [
                "Qwen2-VL-72B",
                "https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct"
            ],
            "Parameters": "73.4B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/10/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2-VL-72B-Instruct",
            "key": 378
        },
        {
            "Overall": 78.0,
            "AR": 84.9,
            "CP": 78.7,
            "FP-C": 73.0,
            "FP-S": 79.8,
            "LR": 66.8,
            "RR": 79.8,
            "action_recognition": 85.5,
            "attribute_comparison": 73.3,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 80.3,
            "function_reasoning": 94.4,
            "future_prediction": 80.0,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 55.6,
            "image_scene": 86.8,
            "image_style": 77.2,
            "image_topic": 97.8,
            "nature_relation": 88.0,
            "object_localization": 61.0,
            "ocr": 93.3,
            "physical_property_reasoning": 62.0,
            "physical_relation": 58.7,
            "social_relation": 89.0,
            "spatial_relationship": 53.3,
            "structuralized_imagetext_understanding": 57.8,
            "Method": [
                "Bumblebee-7B-v2.2",
                "https://github.com/MonolithFoundation/Bumblebee"
            ],
            "Parameters": "7B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "Mono-Encoder",
            "Org": "Monolith Foundation",
            "Time": "2024/10/30",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 379
        },
        {
            "Overall": 82.3,
            "AR": 86.1,
            "CP": 85.7,
            "FP-C": 80.5,
            "FP-S": 83.5,
            "LR": 72.3,
            "RR": 78.7,
            "action_recognition": 84.6,
            "attribute_comparison": 81.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 81.0,
            "function_reasoning": 92.2,
            "future_prediction": 78.7,
            "identity_reasoning": 94.7,
            "image_emotion": 78.9,
            "image_quality": 86.3,
            "image_scene": 88.2,
            "image_style": 76.1,
            "image_topic": 97.8,
            "nature_relation": 92.4,
            "object_localization": 72.4,
            "ocr": 95.6,
            "physical_property_reasoning": 70.9,
            "physical_relation": 61.3,
            "social_relation": 79.1,
            "spatial_relationship": 73.3,
            "structuralized_imagetext_understanding": 67.9,
            "Method": [
                "BlueLM-V-3B",
                "https://developers.vivo.com/product/ai/bluelm"
            ],
            "Parameters": "3B",
            "Language Model": "BlueLM-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "vivo",
            "Time": "2024/10/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "key": 358,
            "dir_name": "BlueLM_V"
        },
        {
            "Overall": 65.6,
            "AR": 77.6,
            "CP": 73.0,
            "FP-C": 61.4,
            "FP-S": 63.1,
            "LR": 39.7,
            "RR": 65.5,
            "action_recognition": 85.5,
            "attribute_comparison": 53.3,
            "attribute_recognition": 76.4,
            "celebrity_recognition": 59.9,
            "function_reasoning": 85.6,
            "future_prediction": 58.7,
            "identity_reasoning": 96.1,
            "image_emotion": 82.2,
            "image_quality": 39.5,
            "image_scene": 88.9,
            "image_style": 60.9,
            "image_topic": 96.7,
            "nature_relation": 76.1,
            "object_localization": 41.0,
            "ocr": 81.1,
            "physical_property_reasoning": 50.6,
            "physical_relation": 38.7,
            "social_relation": 76.9,
            "spatial_relationship": 32.0,
            "structuralized_imagetext_understanding": 26.6,
            "Method": [
                "Falcon2-VLM-11B",
                "https://huggingface.co/tiiuae/falcon-11B-vlm"
            ],
            "Parameters": "11.4B",
            "Language Model": "Falcon2-11B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "Technology Innovation Institute",
            "Time": "2024/10/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Falcon2-VLM-11B",
            "key": 380
        },
        {
            "Overall": 41.5,
            "AR": 56.3,
            "CP": 58.0,
            "FP-C": 27.3,
            "FP-S": 35.7,
            "LR": 15.2,
            "RR": 35.7,
            "action_recognition": 53.8,
            "attribute_comparison": 6.7,
            "attribute_recognition": 48.3,
            "celebrity_recognition": 24.5,
            "function_reasoning": 58.9,
            "future_prediction": 33.3,
            "identity_reasoning": 82.9,
            "image_emotion": 66.7,
            "image_quality": 23.4,
            "image_scene": 75.0,
            "image_style": 42.4,
            "image_topic": 85.6,
            "nature_relation": 37.0,
            "object_localization": 6.7,
            "ocr": 75.6,
            "physical_property_reasoning": 27.8,
            "physical_relation": 4.0,
            "social_relation": 60.4,
            "spatial_relationship": 6.7,
            "structuralized_imagetext_understanding": 2.8,
            "Method": [
                "H2OVL-800M",
                "https://huggingface.co/h2oai/h2ovl-mississippi-800m"
            ],
            "Parameters": "0.83B",
            "Language Model": "H2O-DANUBE3-500M",
            "Vision Model": "InternViT-300M",
            "Org": "H2O.ai",
            "Time": "2024/10/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "h2ovl-mississippi-1b",
            "key": 381
        },
        {
            "Overall": 61.0,
            "AR": 64.9,
            "CP": 71.9,
            "FP-C": 58.8,
            "FP-S": 56.8,
            "LR": 40.8,
            "RR": 58.5,
            "action_recognition": 82.9,
            "attribute_comparison": 49.3,
            "attribute_recognition": 82.0,
            "celebrity_recognition": 32.0,
            "function_reasoning": 73.3,
            "future_prediction": 54.7,
            "identity_reasoning": 90.8,
            "image_emotion": 73.3,
            "image_quality": 40.3,
            "image_scene": 86.1,
            "image_style": 67.4,
            "image_topic": 95.6,
            "nature_relation": 57.6,
            "object_localization": 44.8,
            "ocr": 86.7,
            "physical_property_reasoning": 30.4,
            "physical_relation": 34.7,
            "social_relation": 79.1,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 31.2,
            "Method": [
                "H2OVL-2B",
                "https://huggingface.co/h2oai/h2ovl-mississippi-2b"
            ],
            "Parameters": "2.2B",
            "Language Model": "H2O-DANUBE2-1.8B",
            "Vision Model": "InternViT-300M",
            "Org": "H2O.ai",
            "Time": "2024/10/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "h2ovl-mississippi-2b",
            "key": 382
        },
        {
            "Overall": 85.7,
            "AR": 89.4,
            "CP": 81.3,
            "FP-C": 87.3,
            "FP-S": 93.3,
            "LR": 79.9,
            "RR": 81.0,
            "action_recognition": 91.5,
            "attribute_comparison": 90.7,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 95.2,
            "function_reasoning": 91.1,
            "future_prediction": 85.3,
            "identity_reasoning": 97.4,
            "image_emotion": 81.1,
            "image_quality": 63.7,
            "image_scene": 86.8,
            "image_style": 80.4,
            "image_topic": 97.8,
            "nature_relation": 90.2,
            "object_localization": 87.6,
            "ocr": 97.8,
            "physical_property_reasoning": 79.7,
            "physical_relation": 62.7,
            "social_relation": 86.8,
            "spatial_relationship": 77.3,
            "structuralized_imagetext_understanding": 76.1,
            "Method": [
                "Qwen-VL-Max-0809",
                "https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-qianwen-vl-plus-api"
            ],
            "Parameters": "72B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2024/09/12",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "Qwen-VL-Max-0809",
            "key": 384
        },
        {
            "Overall": 82.5,
            "AR": 85.7,
            "CP": 80.2,
            "FP-C": 80.5,
            "FP-S": 87.9,
            "LR": 83.2,
            "RR": 77.1,
            "action_recognition": 81.2,
            "attribute_comparison": 86.7,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 91.2,
            "function_reasoning": 93.3,
            "future_prediction": 84.0,
            "identity_reasoning": 94.7,
            "image_emotion": 73.3,
            "image_quality": 62.9,
            "image_scene": 88.2,
            "image_style": 80.4,
            "image_topic": 97.8,
            "nature_relation": 91.3,
            "object_localization": 77.1,
            "ocr": 95.6,
            "physical_property_reasoning": 68.4,
            "physical_relation": 52.0,
            "social_relation": 83.5,
            "spatial_relationship": 73.3,
            "structuralized_imagetext_understanding": 82.6,
            "Method": [
                "Claude3.5-Sonnet-20241022",
                "https://docs.anthropic.com/en/docs/build-with-claude/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2024/11/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Claude3-5V_Sonnet_20241022",
            "key": 376
        },
        {
            "Overall": 82.2,
            "AR": 86.1,
            "CP": 82.0,
            "FP-C": 80.1,
            "FP-S": 87.7,
            "LR": 62.0,
            "RR": 86.4,
            "action_recognition": 88.0,
            "attribute_comparison": 88.0,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 90.5,
            "function_reasoning": 91.1,
            "future_prediction": 78.7,
            "identity_reasoning": 100.0,
            "image_emotion": 82.2,
            "image_quality": 61.3,
            "image_scene": 89.6,
            "image_style": 81.5,
            "image_topic": 98.9,
            "nature_relation": 90.2,
            "object_localization": 71.4,
            "ocr": 97.8,
            "physical_property_reasoning": 67.1,
            "physical_relation": 72.0,
            "social_relation": 94.5,
            "spatial_relationship": 60.0,
            "structuralized_imagetext_understanding": 50.5,
            "Method": [
                "bailingMM-mini",
                "https://bailingmm.alipay.com/llm/landing"
            ],
            "Parameters": "17B",
            "Language Model": "bailing-mini",
            "Vision Model": "bailingMM-encoder-1B\nInternViT-6B",
            "Org": "Ant Group",
            "Time": "2024/10/24",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "bailingMM",
            "key": 385
        },
        {
            "Overall": 52.2,
            "AR": 70.6,
            "CP": 60.9,
            "FP-C": 42.7,
            "FP-S": 49.9,
            "LR": 26.6,
            "RR": 48.1,
            "action_recognition": 79.5,
            "attribute_comparison": 14.7,
            "attribute_recognition": 69.7,
            "celebrity_recognition": 46.9,
            "function_reasoning": 72.2,
            "future_prediction": 45.3,
            "identity_reasoning": 89.5,
            "image_emotion": 63.3,
            "image_quality": 12.1,
            "image_scene": 79.9,
            "image_style": 63.0,
            "image_topic": 93.3,
            "nature_relation": 52.2,
            "object_localization": 21.0,
            "ocr": 68.9,
            "physical_property_reasoning": 50.6,
            "physical_relation": 20.0,
            "social_relation": 67.0,
            "spatial_relationship": 13.3,
            "structuralized_imagetext_understanding": 13.8,
            "Method": [
                "Vintern-1B-v2",
                "https://huggingface.co/5CD-AI/Vintern-1B-v2"
            ],
            "Parameters": "3.7B",
            "Language Model": "Qwen2-0.5B",
            "Vision Model": "InternViT-300M",
            "Org": "Fifth Civil Defender",
            "Time": "2024/11/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Vintern-1B-v2",
            "key": 387
        },
        {
            "Overall": 80.3,
            "AR": 83.7,
            "CP": 78.3,
            "FP-C": 76.4,
            "FP-S": 87.7,
            "LR": 74.5,
            "RR": 76.7,
            "action_recognition": 85.5,
            "attribute_comparison": 77.3,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 84.4,
            "function_reasoning": 93.3,
            "future_prediction": 82.7,
            "identity_reasoning": 98.7,
            "image_emotion": 83.3,
            "image_quality": 54.8,
            "image_scene": 86.1,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 84.8,
            "object_localization": 82.9,
            "ocr": 94.4,
            "physical_property_reasoning": 58.2,
            "physical_relation": 53.3,
            "social_relation": 87.9,
            "spatial_relationship": 61.3,
            "structuralized_imagetext_understanding": 68.8,
            "Method": [
                "RBDash-v1.5",
                "https://huggingface.co/RBDash-Team/RBDash-v1.5"
            ],
            "Parameters": "79B",
            "Language Model": "Qwen2-72B",
            "Vision Model": "CLIP ViT-L/14\nInternViT-6B",
            "Org": "DLUT",
            "Time": "2024/11/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "RBDash_72b",
            "key": 388
        },
        {
            "Overall": 81.8,
            "AR": 86.9,
            "CP": 82.2,
            "FP-C": 78.3,
            "FP-S": 86.1,
            "LR": 66.8,
            "RR": 83.3,
            "action_recognition": 91.5,
            "attribute_comparison": 78.7,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 91.8,
            "function_reasoning": 91.1,
            "future_prediction": 80.0,
            "identity_reasoning": 100.0,
            "image_emotion": 88.9,
            "image_quality": 60.5,
            "image_scene": 88.2,
            "image_style": 80.4,
            "image_topic": 97.8,
            "nature_relation": 94.6,
            "object_localization": 67.6,
            "ocr": 96.7,
            "physical_property_reasoning": 69.6,
            "physical_relation": 65.3,
            "social_relation": 86.8,
            "spatial_relationship": 57.3,
            "structuralized_imagetext_understanding": 57.8,
            "Method": [
                "Awaker2.5-VL",
                "https://github.com/MetabrainAGI/Awaker"
            ],
            "Parameters": "10.8B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "QwenViT",
            "Org": "MetabrainAGI",
            "Time": "2024/11/23",
            "Verified": "No",
            "OpenSource": "Yes",
            "key": 389
        },
        {
            "Overall": 76.4,
            "AR": 78.0,
            "CP": 77.2,
            "FP-C": 69.7,
            "FP-S": 85.4,
            "LR": 63.0,
            "RR": 74.4,
            "action_recognition": 82.9,
            "attribute_comparison": 68.0,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 80.3,
            "function_reasoning": 85.6,
            "future_prediction": 68.0,
            "identity_reasoning": 96.1,
            "image_emotion": 76.7,
            "image_quality": 53.2,
            "image_scene": 88.9,
            "image_style": 72.8,
            "image_topic": 96.7,
            "nature_relation": 78.3,
            "object_localization": 81.0,
            "ocr": 93.3,
            "physical_property_reasoning": 51.9,
            "physical_relation": 54.7,
            "social_relation": 86.8,
            "spatial_relationship": 50.7,
            "structuralized_imagetext_understanding": 59.6,
            "Method": [
                "InternVL2-8B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/11/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2-8B-MPO",
            "key": 390
        },
        {
            "Overall": 75.8,
            "AR": 75.1,
            "CP": 77.4,
            "FP-C": 67.8,
            "FP-S": 85.6,
            "LR": 64.1,
            "RR": 73.6,
            "action_recognition": 82.1,
            "attribute_comparison": 66.7,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 79.6,
            "function_reasoning": 82.2,
            "future_prediction": 73.3,
            "identity_reasoning": 93.4,
            "image_emotion": 76.7,
            "image_quality": 56.5,
            "image_scene": 89.6,
            "image_style": 68.5,
            "image_topic": 96.7,
            "nature_relation": 80.4,
            "object_localization": 82.9,
            "ocr": 95.6,
            "physical_property_reasoning": 49.4,
            "physical_relation": 53.3,
            "social_relation": 83.5,
            "spatial_relationship": 46.7,
            "structuralized_imagetext_understanding": 57.8,
            "Method": [
                "InternVL2-8B-MPO-CoT",
                "https://huggingface.co/OpenGVLab/InternVL2-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M",
            "Org": "Shanghai AI Laboratory & SenseTime & Tsinghua University",
            "Time": "2024/11/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2-8B-MPO-CoT",
            "key": 391
        },
        {
            "Overall": 73.7,
            "AR": 80.8,
            "CP": 75.6,
            "FP-C": 65.2,
            "FP-S": 79.1,
            "LR": 61.4,
            "RR": 71.3,
            "action_recognition": 81.2,
            "attribute_comparison": 57.3,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 72.8,
            "function_reasoning": 90.0,
            "future_prediction": 78.7,
            "identity_reasoning": 88.2,
            "image_emotion": 76.7,
            "image_quality": 48.4,
            "image_scene": 84.0,
            "image_style": 76.1,
            "image_topic": 97.8,
            "nature_relation": 79.3,
            "object_localization": 71.4,
            "ocr": 91.1,
            "physical_property_reasoning": 63.3,
            "physical_relation": 50.7,
            "social_relation": 80.2,
            "spatial_relationship": 48.0,
            "structuralized_imagetext_understanding": 49.5,
            "Method": [
                "Eagle-X5-34B-Chat",
                "https://huggingface.co/NVEagle/Eagle-X5-34B-Chat"
            ],
            "Parameters": "36.8B",
            "Language Model": "Yi-34B",
            "Vision Model": "Clip-448\nConvNeXT-1024\nSAM-1024\nDET-1024\nPix2Struct-1024",
            "Org": "Nvidia",
            "Time": "2024/11/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Eagle-X5-34B-Chat",
            "key": 395
        },
        {
            "Overall": 81.5,
            "AR": 90.2,
            "CP": 78.3,
            "FP-C": 77.2,
            "FP-S": 88.2,
            "LR": 72.8,
            "RR": 79.5,
            "action_recognition": 82.1,
            "attribute_comparison": 82.7,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 83.7,
            "function_reasoning": 91.1,
            "future_prediction": 80.0,
            "identity_reasoning": 98.7,
            "image_emotion": 81.1,
            "image_quality": 54.0,
            "image_scene": 84.7,
            "image_style": 78.3,
            "image_topic": 98.9,
            "nature_relation": 91.3,
            "object_localization": 82.9,
            "ocr": 96.7,
            "physical_property_reasoning": 81.0,
            "physical_relation": 62.7,
            "social_relation": 81.3,
            "spatial_relationship": 64.0,
            "structuralized_imagetext_understanding": 67.9,
            "Method": [
                "Ovis1.6-Gemma2-27B",
                "https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-27B"
            ],
            "Parameters": "28.9B",
            "Language Model": "Gemma2-27B",
            "Vision Model": "SigLIP-400M",
            "Org": "Alibaba",
            "Time": "2024/11/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis1.6-Gemma2-27B",
            "key": 396
        },
        {
            "Overall": 81.1,
            "AR": 80.4,
            "CP": 79.8,
            "FP-C": 82.4,
            "FP-S": 87.9,
            "LR": 75.5,
            "RR": 76.0,
            "action_recognition": 90.6,
            "attribute_comparison": 73.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 91.2,
            "function_reasoning": 86.7,
            "future_prediction": 76.0,
            "identity_reasoning": 93.4,
            "image_emotion": 84.4,
            "image_quality": 54.8,
            "image_scene": 86.8,
            "image_style": 81.5,
            "image_topic": 96.7,
            "nature_relation": 89.1,
            "object_localization": 74.3,
            "ocr": 97.8,
            "physical_property_reasoning": 60.8,
            "physical_relation": 57.3,
            "social_relation": 78.0,
            "spatial_relationship": 78.7,
            "structuralized_imagetext_understanding": 75.2,
            "Method": [
                "Gemini-1.5-Pro-002",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/12/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GeminiPro1-5-002",
            "key": 398
        },
        {
            "Overall": 81.0,
            "AR": 84.9,
            "CP": 79.1,
            "FP-C": 79.0,
            "FP-S": 86.8,
            "LR": 73.4,
            "RR": 79.5,
            "action_recognition": 92.3,
            "attribute_comparison": 76.0,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 90.5,
            "function_reasoning": 93.3,
            "future_prediction": 80.0,
            "identity_reasoning": 100.0,
            "image_emotion": 86.7,
            "image_quality": 51.6,
            "image_scene": 84.0,
            "image_style": 82.6,
            "image_topic": 97.8,
            "nature_relation": 94.6,
            "object_localization": 72.4,
            "ocr": 95.6,
            "physical_property_reasoning": 60.8,
            "physical_relation": 49.3,
            "social_relation": 89.0,
            "spatial_relationship": 61.3,
            "structuralized_imagetext_understanding": 68.8,
            "Method": [
                "Gemini-1.5-Flash-002",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2024/12/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GeminiFlash1-5-002",
            "key": 399
        },
        {
            "Overall": 83.9,
            "AR": 89.0,
            "CP": 82.4,
            "FP-C": 86.5,
            "FP-S": 84.5,
            "LR": 80.4,
            "RR": 81.4,
            "action_recognition": 93.2,
            "attribute_comparison": 84.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 70.1,
            "function_reasoning": 93.3,
            "future_prediction": 86.7,
            "identity_reasoning": 98.7,
            "image_emotion": 86.7,
            "image_quality": 58.9,
            "image_scene": 88.2,
            "image_style": 84.8,
            "image_topic": 98.9,
            "nature_relation": 96.7,
            "object_localization": 84.8,
            "ocr": 98.9,
            "physical_property_reasoning": 74.7,
            "physical_relation": 60.0,
            "social_relation": 83.5,
            "spatial_relationship": 78.7,
            "structuralized_imagetext_understanding": 76.1,
            "Method": [
                "GPT-4o (1120, detail-high)",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2024/12/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GPT4o_20241120",
            "key": 400
        },
        {
            "Overall": 76.6,
            "AR": 87.3,
            "CP": 73.5,
            "FP-C": 66.3,
            "FP-S": 85.8,
            "LR": 66.3,
            "RR": 75.2,
            "action_recognition": 79.5,
            "attribute_comparison": 66.7,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 85.7,
            "function_reasoning": 95.6,
            "future_prediction": 73.3,
            "identity_reasoning": 96.1,
            "image_emotion": 53.3,
            "image_quality": 61.3,
            "image_scene": 84.7,
            "image_style": 68.5,
            "image_topic": 97.8,
            "nature_relation": 83.7,
            "object_localization": 74.3,
            "ocr": 95.6,
            "physical_property_reasoning": 69.6,
            "physical_relation": 62.7,
            "social_relation": 76.9,
            "spatial_relationship": 45.3,
            "structuralized_imagetext_understanding": 61.5,
            "Method": [
                "Aria",
                "https://huggingface.co/rhymes-ai/Aria"
            ],
            "Parameters": "25.3B",
            "Language Model": "Aria-MoE",
            "Vision Model": "SigLIP-400M",
            "Org": "Rhymes AI",
            "Time": "2024/12/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Aria",
            "key": 401
        },
        {
            "Overall": 80.2,
            "AR": 86.9,
            "CP": 79.4,
            "FP-C": 76.0,
            "FP-S": 86.5,
            "LR": 65.2,
            "RR": 79.8,
            "action_recognition": 84.6,
            "attribute_comparison": 77.3,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 86.4,
            "function_reasoning": 93.3,
            "future_prediction": 77.3,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 58.9,
            "image_scene": 85.4,
            "image_style": 78.3,
            "image_topic": 96.7,
            "nature_relation": 91.3,
            "object_localization": 71.4,
            "ocr": 94.4,
            "physical_property_reasoning": 69.6,
            "physical_relation": 60.0,
            "social_relation": 84.6,
            "spatial_relationship": 61.3,
            "structuralized_imagetext_understanding": 56.9,
            "Method": [
                "POINTS1.5-Qwen2.5-7B",
                "https://huggingface.co/WePOINTS/POINTS-1-5-Qwen-2-5-7B-Chat"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen-2.5-7B",
            "Vision Model": "NaViT",
            "Org": "WeChat",
            "Time": "2024/12/06",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "POINTSV15-Qwen-2.5-7B-Chat",
            "key": 403
        },
        {
            "Overall": 82.9,
            "AR": 88.6,
            "CP": 83.7,
            "FP-C": 77.9,
            "FP-S": 89.1,
            "LR": 69.6,
            "RR": 80.2,
            "action_recognition": 89.7,
            "attribute_comparison": 81.3,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 85.0,
            "function_reasoning": 93.3,
            "future_prediction": 74.7,
            "identity_reasoning": 96.1,
            "image_emotion": 77.8,
            "image_quality": 68.5,
            "image_scene": 92.4,
            "image_style": 81.5,
            "image_topic": 98.9,
            "nature_relation": 89.1,
            "object_localization": 84.8,
            "ocr": 95.6,
            "physical_property_reasoning": 75.9,
            "physical_relation": 65.3,
            "social_relation": 83.5,
            "spatial_relationship": 56.0,
            "structuralized_imagetext_understanding": 66.1,
            "Method": [
                "BailingMM-Lite-1203",
                "https://zxb.alipay.com/llm/landing"
            ],
            "Parameters": "21B",
            "Language Model": "Bailing-20B",
            "Vision Model": "SigLIP-400M",
            "Org": "Ant Group",
            "Time": "2024/12/08",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "bailingMM-Lite",
            "key": 404
        },
        {
            "Overall": 81.0,
            "AR": 86.1,
            "CP": 75.7,
            "FP-C": 82.8,
            "FP-S": 86.8,
            "LR": 77.2,
            "RR": 78.7,
            "action_recognition": 88.0,
            "attribute_comparison": 80.0,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 84.4,
            "function_reasoning": 92.2,
            "future_prediction": 76.0,
            "identity_reasoning": 98.7,
            "image_emotion": 58.9,
            "image_quality": 57.3,
            "image_scene": 86.1,
            "image_style": 79.3,
            "image_topic": 97.8,
            "nature_relation": 90.2,
            "object_localization": 79.0,
            "ocr": 98.9,
            "physical_property_reasoning": 67.1,
            "physical_relation": 70.7,
            "social_relation": 73.6,
            "spatial_relationship": 77.3,
            "structuralized_imagetext_understanding": 78.0,
            "Method": [
                "GLM-4v-Plus",
                "https://open.bigmodel.cn/dev/api/normal-model/glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GLM4V_PLUS",
            "key": 412
        },
        {
            "Overall": 79.6,
            "AR": 86.1,
            "CP": 78.7,
            "FP-C": 72.7,
            "FP-S": 88.9,
            "LR": 64.7,
            "RR": 77.5,
            "action_recognition": 88.0,
            "attribute_comparison": 73.3,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 94.6,
            "function_reasoning": 93.3,
            "future_prediction": 76.0,
            "identity_reasoning": 100.0,
            "image_emotion": 78.9,
            "image_quality": 51.6,
            "image_scene": 88.9,
            "image_style": 80.4,
            "image_topic": 97.8,
            "nature_relation": 90.2,
            "object_localization": 80.0,
            "ocr": 94.4,
            "physical_property_reasoning": 64.6,
            "physical_relation": 54.7,
            "social_relation": 83.5,
            "spatial_relationship": 48.0,
            "structuralized_imagetext_understanding": 56.9,
            "Method": [
                "Step-1.5V-mini",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "StepFun",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Step1.5V-mini",
            "key": 413
        },
        {
            "Overall": 57.5,
            "AR": 66.5,
            "CP": 65.7,
            "FP-C": 46.8,
            "FP-S": 56.4,
            "LR": 47.8,
            "RR": 51.2,
            "action_recognition": 76.1,
            "attribute_comparison": 16.0,
            "attribute_recognition": 66.3,
            "celebrity_recognition": 39.5,
            "function_reasoning": 76.7,
            "future_prediction": 54.7,
            "identity_reasoning": 84.2,
            "image_emotion": 71.1,
            "image_quality": 29.0,
            "image_scene": 81.2,
            "image_style": 58.7,
            "image_topic": 93.3,
            "nature_relation": 68.5,
            "object_localization": 40.0,
            "ocr": 93.3,
            "physical_property_reasoning": 38.0,
            "physical_relation": 33.3,
            "social_relation": 48.4,
            "spatial_relationship": 32.0,
            "structuralized_imagetext_understanding": 43.1,
            "Method": [
                "abab6.5s",
                "https://www.minimaxi.com/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "MiniMax",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "abab6.5s",
            "key": 414
        },
        {
            "Overall": 80.6,
            "AR": 82.9,
            "CP": 78.1,
            "FP-C": 79.4,
            "FP-S": 88.6,
            "LR": 70.7,
            "RR": 78.7,
            "action_recognition": 82.9,
            "attribute_comparison": 80.0,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 81.0,
            "function_reasoning": 92.2,
            "future_prediction": 80.0,
            "identity_reasoning": 89.5,
            "image_emotion": 75.6,
            "image_quality": 60.5,
            "image_scene": 86.8,
            "image_style": 71.7,
            "image_topic": 97.8,
            "nature_relation": 91.3,
            "object_localization": 85.7,
            "ocr": 97.8,
            "physical_property_reasoning": 65.8,
            "physical_relation": 58.7,
            "social_relation": 82.4,
            "spatial_relationship": 73.3,
            "structuralized_imagetext_understanding": 64.2,
            "Method": [
                "abab7-preview",
                "https://www.minimaxi.com/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "MiniMax",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "abab7-preview",
            "key": 415
        },
        {
            "Overall": 85.2,
            "AR": 85.3,
            "CP": 82.2,
            "FP-C": 85.8,
            "FP-S": 92.6,
            "LR": 77.7,
            "RR": 83.7,
            "action_recognition": 87.2,
            "attribute_comparison": 89.3,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 91.2,
            "function_reasoning": 92.2,
            "future_prediction": 78.7,
            "identity_reasoning": 98.7,
            "image_emotion": 83.3,
            "image_quality": 62.1,
            "image_scene": 91.0,
            "image_style": 80.4,
            "image_topic": 96.7,
            "nature_relation": 88.0,
            "object_localization": 87.6,
            "ocr": 97.8,
            "physical_property_reasoning": 64.6,
            "physical_relation": 76.0,
            "social_relation": 85.7,
            "spatial_relationship": 80.0,
            "structuralized_imagetext_understanding": 77.1,
            "Method": [
                "SenseNova",
                "https://platform.sensenova.cn/home"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "SenseTime",
            "Time": "2024/12/12",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SenseChat-Vision",
            "key": 416
        },
        {
            "Overall": 85.0,
            "AR": 91.0,
            "CP": 83.1,
            "FP-C": 84.3,
            "FP-S": 89.8,
            "LR": 72.8,
            "RR": 84.9,
            "action_recognition": 88.9,
            "attribute_comparison": 86.7,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 89.1,
            "function_reasoning": 93.3,
            "future_prediction": 84.0,
            "identity_reasoning": 97.4,
            "image_emotion": 85.6,
            "image_quality": 66.1,
            "image_scene": 89.6,
            "image_style": 78.3,
            "image_topic": 98.9,
            "nature_relation": 92.4,
            "object_localization": 82.9,
            "ocr": 94.4,
            "physical_property_reasoning": 82.3,
            "physical_relation": 69.3,
            "social_relation": 90.1,
            "spatial_relationship": 74.7,
            "structuralized_imagetext_understanding": 65.1,
            "Method": [
                "Taiyi",
                "https://taiyi.megvii.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Megvii & StepFun",
            "Time": "2024/12/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Taiyi",
            "key": 383
        },
        {
            "Overall": 64.8,
            "AR": 70.2,
            "CP": 73.1,
            "FP-C": 56.9,
            "FP-S": 67.5,
            "LR": 46.2,
            "RR": 59.3,
            "action_recognition": 86.3,
            "attribute_comparison": 33.3,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 56.5,
            "function_reasoning": 80.0,
            "future_prediction": 65.3,
            "identity_reasoning": 94.7,
            "image_emotion": 77.8,
            "image_quality": 42.7,
            "image_scene": 85.4,
            "image_style": 67.4,
            "image_topic": 96.7,
            "nature_relation": 52.2,
            "object_localization": 47.6,
            "ocr": 92.2,
            "physical_property_reasoning": 35.4,
            "physical_relation": 48.0,
            "social_relation": 75.8,
            "spatial_relationship": 34.7,
            "structuralized_imagetext_understanding": 33.0,
            "Method": [
                "InternVL2.5-1B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-1B"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen-2.5-0.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-1B",
            "key": 417
        },
        {
            "Overall": 69.4,
            "AR": 81.2,
            "CP": 76.7,
            "FP-C": 62.9,
            "FP-S": 71.7,
            "LR": 46.7,
            "RR": 61.6,
            "action_recognition": 86.3,
            "attribute_comparison": 54.7,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 66.0,
            "function_reasoning": 85.6,
            "future_prediction": 61.3,
            "identity_reasoning": 94.7,
            "image_emotion": 74.4,
            "image_quality": 50.0,
            "image_scene": 91.0,
            "image_style": 71.7,
            "image_topic": 97.8,
            "nature_relation": 63.0,
            "object_localization": 49.5,
            "ocr": 87.8,
            "physical_property_reasoning": 63.3,
            "physical_relation": 40.0,
            "social_relation": 78.0,
            "spatial_relationship": 34.7,
            "structuralized_imagetext_understanding": 36.7,
            "Method": [
                "InternVL2.5-2B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-2B"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2.5-1.8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-2B",
            "key": 418
        },
        {
            "Overall": 77.6,
            "AR": 85.7,
            "CP": 80.2,
            "FP-C": 68.9,
            "FP-S": 82.1,
            "LR": 66.3,
            "RR": 74.0,
            "action_recognition": 87.2,
            "attribute_comparison": 66.7,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 76.9,
            "function_reasoning": 93.3,
            "future_prediction": 78.7,
            "identity_reasoning": 97.4,
            "image_emotion": 85.6,
            "image_quality": 52.4,
            "image_scene": 91.7,
            "image_style": 78.3,
            "image_topic": 96.7,
            "nature_relation": 66.3,
            "object_localization": 70.5,
            "ocr": 94.4,
            "physical_property_reasoning": 65.8,
            "physical_relation": 65.3,
            "social_relation": 89.0,
            "spatial_relationship": 42.7,
            "structuralized_imagetext_understanding": 57.8,
            "Method": [
                "InternVL2.5-4B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-4B"
            ],
            "Parameters": "4B",
            "Language Model": "Qwen-2.5-3B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-4B",
            "key": 419
        },
        {
            "Overall": 81.7,
            "AR": 83.7,
            "CP": 82.2,
            "FP-C": 78.3,
            "FP-S": 88.9,
            "LR": 70.1,
            "RR": 78.7,
            "action_recognition": 88.9,
            "attribute_comparison": 84.0,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 83.0,
            "function_reasoning": 88.9,
            "future_prediction": 78.7,
            "identity_reasoning": 98.7,
            "image_emotion": 84.4,
            "image_quality": 58.9,
            "image_scene": 92.4,
            "image_style": 81.5,
            "image_topic": 96.7,
            "nature_relation": 87.0,
            "object_localization": 83.8,
            "ocr": 96.7,
            "physical_property_reasoning": 63.3,
            "physical_relation": 58.7,
            "social_relation": 86.8,
            "spatial_relationship": 56.0,
            "structuralized_imagetext_understanding": 64.2,
            "Method": [
                "InternVL2.5-8B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-8B"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-8B",
            "key": 420
        },
        {
            "Overall": 84.7,
            "AR": 85.7,
            "CP": 84.3,
            "FP-C": 83.5,
            "FP-S": 90.5,
            "LR": 73.9,
            "RR": 83.7,
            "action_recognition": 94.0,
            "attribute_comparison": 81.3,
            "attribute_recognition": 97.8,
            "celebrity_recognition": 83.7,
            "function_reasoning": 94.4,
            "future_prediction": 80.0,
            "identity_reasoning": 98.7,
            "image_emotion": 86.7,
            "image_quality": 65.3,
            "image_scene": 91.0,
            "image_style": 82.6,
            "image_topic": 98.9,
            "nature_relation": 89.1,
            "object_localization": 89.5,
            "ocr": 95.6,
            "physical_property_reasoning": 63.3,
            "physical_relation": 69.3,
            "social_relation": 90.1,
            "spatial_relationship": 69.3,
            "structuralized_imagetext_understanding": 69.7,
            "Method": [
                "InternVL2.5-26B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-26B"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2.5-20B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-26B",
            "key": 421
        },
        {
            "Overall": 85.6,
            "AR": 88.6,
            "CP": 82.6,
            "FP-C": 85.0,
            "FP-S": 90.7,
            "LR": 82.1,
            "RR": 83.7,
            "action_recognition": 90.6,
            "attribute_comparison": 81.3,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 85.7,
            "function_reasoning": 92.2,
            "future_prediction": 84.0,
            "identity_reasoning": 97.4,
            "image_emotion": 84.4,
            "image_quality": 56.5,
            "image_scene": 92.4,
            "image_style": 84.8,
            "image_topic": 98.9,
            "nature_relation": 88.0,
            "object_localization": 87.6,
            "ocr": 98.9,
            "physical_property_reasoning": 75.9,
            "physical_relation": 74.7,
            "social_relation": 86.8,
            "spatial_relationship": 80.0,
            "structuralized_imagetext_understanding": 80.7,
            "Method": [
                "InternVL2.5-38B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-38B"
            ],
            "Parameters": "38B",
            "Language Model": "Qwen-2.5-32B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-38B",
            "key": 422
        },
        {
            "Overall": 87.8,
            "AR": 90.2,
            "CP": 85.2,
            "FP-C": 86.5,
            "FP-S": 92.8,
            "LR": 83.7,
            "RR": 87.2,
            "action_recognition": 93.2,
            "attribute_comparison": 84.0,
            "attribute_recognition": 98.9,
            "celebrity_recognition": 89.1,
            "function_reasoning": 95.6,
            "future_prediction": 88.0,
            "identity_reasoning": 98.7,
            "image_emotion": 87.8,
            "image_quality": 62.9,
            "image_scene": 93.1,
            "image_style": 87.0,
            "image_topic": 98.9,
            "nature_relation": 95.7,
            "object_localization": 88.6,
            "ocr": 97.8,
            "physical_property_reasoning": 75.9,
            "physical_relation": 72.0,
            "social_relation": 91.2,
            "spatial_relationship": 78.7,
            "structuralized_imagetext_understanding": 80.7,
            "Method": [
                "InternVL2.5-78B",
                "https://huggingface.co/OpenGVLab/InternVL2_5-78B"
            ],
            "Parameters": "78B",
            "Language Model": "Qwen-2.5-72B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-78B",
            "key": 423
        },
        {
            "Overall": 71.8,
            "AR": 82.0,
            "CP": 74.1,
            "FP-C": 65.2,
            "FP-S": 77.3,
            "LR": 53.3,
            "RR": 68.2,
            "action_recognition": 81.2,
            "attribute_comparison": 72.0,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 70.1,
            "function_reasoning": 86.7,
            "future_prediction": 65.3,
            "identity_reasoning": 94.7,
            "image_emotion": 78.9,
            "image_quality": 41.9,
            "image_scene": 85.4,
            "image_style": 72.8,
            "image_topic": 96.7,
            "nature_relation": 72.8,
            "object_localization": 62.9,
            "ocr": 91.1,
            "physical_property_reasoning": 64.6,
            "physical_relation": 38.7,
            "social_relation": 87.9,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 45.0,
            "Method": [
                "SAIL-VL-2B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL-2B"
            ],
            "Parameters": "2.1B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "InternViT-300M",
            "Org": "ByteDance",
            "Time": "2024/12/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL-2B",
            "key": 424
        },
        {
            "Overall": 64.3,
            "AR": 69.4,
            "CP": 72.6,
            "FP-C": 55.8,
            "FP-S": 68.7,
            "LR": 43.5,
            "RR": 58.5,
            "action_recognition": 83.8,
            "attribute_comparison": 37.3,
            "attribute_recognition": 83.1,
            "celebrity_recognition": 56.5,
            "function_reasoning": 80.0,
            "future_prediction": 61.3,
            "identity_reasoning": 93.4,
            "image_emotion": 76.7,
            "image_quality": 42.7,
            "image_scene": 85.4,
            "image_style": 65.2,
            "image_topic": 96.7,
            "nature_relation": 52.2,
            "object_localization": 52.4,
            "ocr": 93.3,
            "physical_property_reasoning": 34.2,
            "physical_relation": 45.3,
            "social_relation": 75.8,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 31.2,
            "Method": [
                "InternVL2.5-1B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-1B-MPO"
            ],
            "Parameters": "1B",
            "Language Model": "Qwen-2.5-0.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-1B-MPO",
            "key": 425
        },
        {
            "Overall": 69.5,
            "AR": 79.6,
            "CP": 75.6,
            "FP-C": 64.0,
            "FP-S": 73.3,
            "LR": 47.3,
            "RR": 62.0,
            "action_recognition": 84.6,
            "attribute_comparison": 58.7,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 65.3,
            "function_reasoning": 84.4,
            "future_prediction": 62.7,
            "identity_reasoning": 96.1,
            "image_emotion": 74.4,
            "image_quality": 47.6,
            "image_scene": 91.0,
            "image_style": 69.6,
            "image_topic": 96.7,
            "nature_relation": 62.0,
            "object_localization": 54.3,
            "ocr": 91.1,
            "physical_property_reasoning": 58.2,
            "physical_relation": 42.7,
            "social_relation": 78.0,
            "spatial_relationship": 37.3,
            "structuralized_imagetext_understanding": 36.7,
            "Method": [
                "InternVL2.5-2B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-2B-MPO"
            ],
            "Parameters": "2B",
            "Language Model": "InternLM2.5-1.8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-2B-MPO",
            "key": 426
        },
        {
            "Overall": 76.9,
            "AR": 84.1,
            "CP": 79.1,
            "FP-C": 70.4,
            "FP-S": 81.9,
            "LR": 64.7,
            "RR": 72.5,
            "action_recognition": 86.3,
            "attribute_comparison": 73.3,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 73.5,
            "function_reasoning": 91.1,
            "future_prediction": 78.7,
            "identity_reasoning": 97.4,
            "image_emotion": 83.3,
            "image_quality": 56.5,
            "image_scene": 88.9,
            "image_style": 73.9,
            "image_topic": 95.6,
            "nature_relation": 64.1,
            "object_localization": 73.3,
            "ocr": 94.4,
            "physical_property_reasoning": 63.3,
            "physical_relation": 65.3,
            "social_relation": 86.8,
            "spatial_relationship": 42.7,
            "structuralized_imagetext_understanding": 55.0,
            "Method": [
                "InternVL2.5-4B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-4B-MPO"
            ],
            "Parameters": "4B",
            "Language Model": "Qwen-2.5-3B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-4B-MPO",
            "key": 427
        },
        {
            "Overall": 81.5,
            "AR": 82.9,
            "CP": 81.3,
            "FP-C": 80.1,
            "FP-S": 88.9,
            "LR": 69.6,
            "RR": 78.3,
            "action_recognition": 88.0,
            "attribute_comparison": 88.0,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 83.7,
            "function_reasoning": 86.7,
            "future_prediction": 78.7,
            "identity_reasoning": 98.7,
            "image_emotion": 81.1,
            "image_quality": 57.3,
            "image_scene": 92.4,
            "image_style": 81.5,
            "image_topic": 96.7,
            "nature_relation": 85.9,
            "object_localization": 82.9,
            "ocr": 96.7,
            "physical_property_reasoning": 63.3,
            "physical_relation": 58.7,
            "social_relation": 86.8,
            "spatial_relationship": 60.0,
            "structuralized_imagetext_understanding": 63.3,
            "Method": [
                "InternVL2.5-8B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-8B-MPO"
            ],
            "Parameters": "8B",
            "Language Model": "InternLM2.5-7B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-8B-MPO",
            "key": 428
        },
        {
            "Overall": 84.1,
            "AR": 86.5,
            "CP": 82.2,
            "FP-C": 83.5,
            "FP-S": 89.8,
            "LR": 73.9,
            "RR": 83.7,
            "action_recognition": 91.5,
            "attribute_comparison": 82.7,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 83.7,
            "function_reasoning": 93.3,
            "future_prediction": 80.0,
            "identity_reasoning": 97.4,
            "image_emotion": 85.6,
            "image_quality": 59.7,
            "image_scene": 90.3,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 88.0,
            "object_localization": 87.6,
            "ocr": 95.6,
            "physical_property_reasoning": 68.4,
            "physical_relation": 72.0,
            "social_relation": 89.0,
            "spatial_relationship": 72.0,
            "structuralized_imagetext_understanding": 69.7,
            "Method": [
                "InternVL2.5-26B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-26B-MPO"
            ],
            "Parameters": "26B",
            "Language Model": "InternLM2.5-20B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-26B-MPO",
            "key": 429
        },
        {
            "Overall": 85.4,
            "AR": 88.2,
            "CP": 80.9,
            "FP-C": 86.5,
            "FP-S": 91.4,
            "LR": 80.4,
            "RR": 84.1,
            "action_recognition": 91.5,
            "attribute_comparison": 80.0,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 86.4,
            "function_reasoning": 92.2,
            "future_prediction": 81.3,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 54.0,
            "image_scene": 90.3,
            "image_style": 83.7,
            "image_topic": 98.9,
            "nature_relation": 90.2,
            "object_localization": 87.6,
            "ocr": 98.9,
            "physical_property_reasoning": 74.7,
            "physical_relation": 73.3,
            "social_relation": 86.8,
            "spatial_relationship": 85.3,
            "structuralized_imagetext_understanding": 79.8,
            "Method": [
                "InternVL2.5-38B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-38B-MPO"
            ],
            "Parameters": "38B",
            "Language Model": "Qwen-2.5-32B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-38B-MPO",
            "key": 430
        },
        {
            "Overall": 79.9,
            "AR": 88.2,
            "CP": 79.4,
            "FP-C": 73.4,
            "FP-S": 87.7,
            "LR": 65.8,
            "RR": 77.1,
            "action_recognition": 87.2,
            "attribute_comparison": 76.0,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 86.4,
            "function_reasoning": 94.4,
            "future_prediction": 84.0,
            "identity_reasoning": 97.4,
            "image_emotion": 82.2,
            "image_quality": 57.3,
            "image_scene": 86.1,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 87.0,
            "object_localization": 79.0,
            "ocr": 96.7,
            "physical_property_reasoning": 72.2,
            "physical_relation": 53.3,
            "social_relation": 86.8,
            "spatial_relationship": 49.3,
            "structuralized_imagetext_understanding": 53.2,
            "Method": [
                "Valley-Eagle",
                "https://huggingface.co/bytedance-research/Valley-Eagle-7B"
            ],
            "Parameters": "8.9B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "Qwen-ViT\nSigLIP-400M",
            "Org": "ByteDance",
            "Time": "2024/12/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "valley_eagle",
            "key": 431
        },
        {
            "Overall": 87.5,
            "AR": 89.8,
            "CP": 84.6,
            "FP-C": 88.0,
            "FP-S": 91.9,
            "LR": 83.7,
            "RR": 86.4,
            "action_recognition": 90.6,
            "attribute_comparison": 88.0,
            "attribute_recognition": 97.8,
            "celebrity_recognition": 88.4,
            "function_reasoning": 95.6,
            "future_prediction": 86.7,
            "identity_reasoning": 98.7,
            "image_emotion": 86.7,
            "image_quality": 62.1,
            "image_scene": 93.1,
            "image_style": 85.9,
            "image_topic": 98.9,
            "nature_relation": 95.7,
            "object_localization": 87.6,
            "ocr": 96.7,
            "physical_property_reasoning": 74.7,
            "physical_relation": 73.3,
            "social_relation": 87.9,
            "spatial_relationship": 84.0,
            "structuralized_imagetext_understanding": 81.7,
            "Method": [
                "InternVL2.5-78B-MPO",
                "https://huggingface.co/OpenGVLab/InternVL2_5-78B-MPO"
            ],
            "Parameters": "78B",
            "Language Model": "Qwen-2.5-72B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2024/12/29",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL2_5-78B-MPO",
            "key": 432
        },
        {
            "Overall": 78.3,
            "AR": 86.5,
            "CP": 76.3,
            "FP-C": 72.7,
            "FP-S": 83.5,
            "LR": 73.4,
            "RR": 75.6,
            "action_recognition": 84.6,
            "attribute_comparison": 66.7,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 83.0,
            "function_reasoning": 95.6,
            "future_prediction": 82.7,
            "identity_reasoning": 98.7,
            "image_emotion": 71.1,
            "image_quality": 54.0,
            "image_scene": 88.2,
            "image_style": 72.8,
            "image_topic": 96.7,
            "nature_relation": 79.3,
            "object_localization": 69.5,
            "ocr": 95.6,
            "physical_property_reasoning": 64.6,
            "physical_relation": 62.7,
            "social_relation": 82.4,
            "spatial_relationship": 60.0,
            "structuralized_imagetext_understanding": 67.0,
            "Method": [
                "TeleMM",
                "https://docs.siliconflow.cn/api-reference/chat-completions/chat-completions"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "China Telecom",
            "Time": "2024/12/31",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "TeleMM",
            "key": 397
        },
        {
            "Overall": 70.1,
            "AR": 78.8,
            "CP": 73.0,
            "FP-C": 63.7,
            "FP-S": 75.2,
            "LR": 46.7,
            "RR": 70.9,
            "action_recognition": 82.1,
            "attribute_comparison": 65.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 72.8,
            "function_reasoning": 85.6,
            "future_prediction": 62.7,
            "identity_reasoning": 96.1,
            "image_emotion": 73.3,
            "image_quality": 41.1,
            "image_scene": 84.0,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 72.8,
            "object_localization": 56.2,
            "ocr": 87.8,
            "physical_property_reasoning": 54.4,
            "physical_relation": 58.7,
            "social_relation": 79.1,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 35.8,
            "Method": [
                "DeepSeek-VL2-Tiny",
                "https://huggingface.co/deepseek-ai/deepseek-vl2-tiny"
            ],
            "Parameters": "3.4B",
            "Language Model": "DeepSeekMoE-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2_tiny",
            "key": 433
        },
        {
            "Overall": 79.1,
            "AR": 81.6,
            "CP": 81.5,
            "FP-C": 74.5,
            "FP-S": 84.5,
            "LR": 66.3,
            "RR": 76.4,
            "action_recognition": 84.6,
            "attribute_comparison": 80.0,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 83.0,
            "function_reasoning": 90.0,
            "future_prediction": 80.0,
            "identity_reasoning": 96.1,
            "image_emotion": 80.0,
            "image_quality": 59.7,
            "image_scene": 88.9,
            "image_style": 83.7,
            "image_topic": 98.9,
            "nature_relation": 80.4,
            "object_localization": 72.4,
            "ocr": 94.4,
            "physical_property_reasoning": 58.2,
            "physical_relation": 61.3,
            "social_relation": 84.6,
            "spatial_relationship": 53.3,
            "structuralized_imagetext_understanding": 56.9,
            "Method": [
                "DeepSeek-VL2-Small",
                "https://huggingface.co/deepseek-ai/deepseek-vl2-small"
            ],
            "Parameters": "16.1B",
            "Language Model": "DeepSeekMoE-16B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2_small",
            "key": 434
        },
        {
            "Overall": 80.1,
            "AR": 87.3,
            "CP": 79.3,
            "FP-C": 77.2,
            "FP-S": 86.1,
            "LR": 70.7,
            "RR": 74.4,
            "action_recognition": 82.1,
            "attribute_comparison": 86.7,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 80.3,
            "function_reasoning": 93.3,
            "future_prediction": 78.7,
            "identity_reasoning": 98.7,
            "image_emotion": 82.2,
            "image_quality": 56.5,
            "image_scene": 88.9,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 77.2,
            "object_localization": 83.8,
            "ocr": 94.4,
            "physical_property_reasoning": 69.6,
            "physical_relation": 61.3,
            "social_relation": 82.4,
            "spatial_relationship": 60.0,
            "structuralized_imagetext_understanding": 65.1,
            "Method": [
                "VARCO-VISION-14B",
                "https://huggingface.co/NCSOFT/VARCO-VISION-14B-HF"
            ],
            "Parameters": "15.2B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "SigLIP-400M",
            "Org": "NC Research",
            "Time": "2025/01/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "varco-vision-hf",
            "key": 437
        },
        {
            "Overall": 71.6,
            "AR": 69.4,
            "CP": 68.5,
            "FP-C": 72.7,
            "FP-S": 78.0,
            "LR": 71.2,
            "RR": 68.6,
            "action_recognition": 78.6,
            "attribute_comparison": 68.0,
            "attribute_recognition": 79.8,
            "celebrity_recognition": 82.3,
            "function_reasoning": 74.4,
            "future_prediction": 74.7,
            "identity_reasoning": 86.8,
            "image_emotion": 74.4,
            "image_quality": 45.2,
            "image_scene": 75.0,
            "image_style": 72.8,
            "image_topic": 80.0,
            "nature_relation": 78.3,
            "object_localization": 68.6,
            "ocr": 80.0,
            "physical_property_reasoning": 46.8,
            "physical_relation": 46.7,
            "social_relation": 76.9,
            "spatial_relationship": 68.0,
            "structuralized_imagetext_understanding": 68.8,
            "Method": [
                "Gemini-2.0-Flash",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2025/01/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GeminiFlash2-0",
            "key": 438
        },
        {
            "Overall": 71.4,
            "AR": 82.4,
            "CP": 70.9,
            "FP-C": 66.3,
            "FP-S": 76.6,
            "LR": 54.9,
            "RR": 70.2,
            "action_recognition": 81.2,
            "attribute_comparison": 62.7,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 83.0,
            "function_reasoning": 87.8,
            "future_prediction": 68.0,
            "identity_reasoning": 94.7,
            "image_emotion": 64.4,
            "image_quality": 40.3,
            "image_scene": 85.4,
            "image_style": 70.7,
            "image_topic": 96.7,
            "nature_relation": 82.6,
            "object_localization": 48.6,
            "ocr": 91.1,
            "physical_property_reasoning": 64.6,
            "physical_relation": 46.7,
            "social_relation": 76.9,
            "spatial_relationship": 46.7,
            "structuralized_imagetext_understanding": 45.9,
            "Method": [
                "LLaVA-CoT",
                "https://huggingface.co/Xkev/Llama-3.2V-11B-cot"
            ],
            "Parameters": "11B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Peking University",
            "Time": "2025/01/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "LLaVA-CoT",
            "key": 402
        },
        {
            "Overall": 87.0,
            "AR": 89.8,
            "CP": 83.0,
            "FP-C": 87.6,
            "FP-S": 95.1,
            "LR": 79.3,
            "RR": 83.7,
            "action_recognition": 93.2,
            "attribute_comparison": 85.3,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 98.6,
            "function_reasoning": 94.4,
            "future_prediction": 89.3,
            "identity_reasoning": 98.7,
            "image_emotion": 88.9,
            "image_quality": 62.9,
            "image_scene": 86.8,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 94.6,
            "object_localization": 88.6,
            "ocr": 97.8,
            "physical_property_reasoning": 75.9,
            "physical_relation": 61.3,
            "social_relation": 91.2,
            "spatial_relationship": 81.3,
            "structuralized_imagetext_understanding": 72.5,
            "Method": [
                "Step-1o",
                "https://platform.stepfun.com"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "StepFun",
            "Time": "2025/01/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Step1o",
            "key": 439
        },
        {
            "Overall": 83.3,
            "AR": 90.6,
            "CP": 79.3,
            "FP-C": 80.1,
            "FP-S": 90.3,
            "LR": 79.9,
            "RR": 79.1,
            "action_recognition": 87.2,
            "attribute_comparison": 77.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 94.6,
            "function_reasoning": 92.2,
            "future_prediction": 80.0,
            "identity_reasoning": 98.7,
            "image_emotion": 73.3,
            "image_quality": 57.3,
            "image_scene": 91.0,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 89.1,
            "object_localization": 81.0,
            "ocr": 95.6,
            "physical_property_reasoning": 81.0,
            "physical_relation": 62.7,
            "social_relation": 82.4,
            "spatial_relationship": 72.0,
            "structuralized_imagetext_understanding": 79.8,
            "Method": [
                "HunYuan-Standard-Vision",
                "https://cloud.tencent.com/document/product/1729/104753"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Tencent",
            "Time": "2025/01/15",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "HunYuan-Standard-Vision",
            "key": 440
        },
        {
            "Overall": 73.8,
            "AR": 86.5,
            "CP": 78.3,
            "FP-C": 68.5,
            "FP-S": 76.6,
            "LR": 54.9,
            "RR": 66.7,
            "action_recognition": 90.6,
            "attribute_comparison": 72.0,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 76.2,
            "function_reasoning": 90.0,
            "future_prediction": 76.0,
            "identity_reasoning": 96.1,
            "image_emotion": 82.2,
            "image_quality": 50.8,
            "image_scene": 87.5,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 72.8,
            "object_localization": 53.3,
            "ocr": 90.0,
            "physical_property_reasoning": 73.4,
            "physical_relation": 40.0,
            "social_relation": 82.4,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 40.4,
            "Method": [
                "Ross-Qwen2-7B",
                "https://huggingface.co/HaochenWang/ross-qwen2-7b"
            ],
            "Parameters": "8.2B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "CLIP ViT-L/14",
            "Org": "CASIA",
            "Time": "2025/01/17",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "ross-qwen2-7b",
            "key": 441
        },
        {
            "Overall": 76.1,
            "AR": 82.9,
            "CP": 75.9,
            "FP-C": 69.3,
            "FP-S": 83.1,
            "LR": 60.9,
            "RR": 76.0,
            "action_recognition": 83.8,
            "attribute_comparison": 68.0,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 78.9,
            "function_reasoning": 87.8,
            "future_prediction": 74.7,
            "identity_reasoning": 93.4,
            "image_emotion": 78.9,
            "image_quality": 46.8,
            "image_scene": 85.4,
            "image_style": 75.0,
            "image_topic": 98.9,
            "nature_relation": 80.4,
            "object_localization": 71.4,
            "ocr": 100.0,
            "physical_property_reasoning": 67.1,
            "physical_relation": 60.0,
            "social_relation": 84.6,
            "spatial_relationship": 48.0,
            "structuralized_imagetext_understanding": 51.4,
            "Method": [
                "VITA-1.5",
                "https://huggingface.co/VITA-MLLM/VITA-1.5"
            ],
            "Parameters": "8.3B",
            "Language Model": "Qwen2-7B",
            "Vision Model": "InternViT-300M",
            "Org": "NJU",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "vita_qwen2",
            "key": 442
        },
        {
            "Overall": 68.7,
            "AR": 79.6,
            "CP": 71.7,
            "FP-C": 59.6,
            "FP-S": 69.8,
            "LR": 56.5,
            "RR": 68.6,
            "action_recognition": 81.2,
            "attribute_comparison": 52.0,
            "attribute_recognition": 83.1,
            "celebrity_recognition": 65.3,
            "function_reasoning": 88.9,
            "future_prediction": 70.7,
            "identity_reasoning": 94.7,
            "image_emotion": 80.0,
            "image_quality": 41.1,
            "image_scene": 84.7,
            "image_style": 60.9,
            "image_topic": 95.6,
            "nature_relation": 76.1,
            "object_localization": 47.6,
            "ocr": 90.0,
            "physical_property_reasoning": 54.4,
            "physical_relation": 42.7,
            "social_relation": 82.4,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 46.8,
            "Method": [
                "VITA",
                "https://huggingface.co/VITA-MLLM/VITA"
            ],
            "Parameters": "47B",
            "Language Model": "Mixtral-8x7B",
            "Vision Model": "InternViT-300M",
            "Org": "NJU",
            "Time": "2025/01/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "vita",
            "key": 443
        },
        {
            "Overall": 79.9,
            "AR": 87.8,
            "CP": 79.4,
            "FP-C": 71.9,
            "FP-S": 87.7,
            "LR": 64.7,
            "RR": 79.5,
            "action_recognition": 80.3,
            "attribute_comparison": 77.3,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 86.4,
            "function_reasoning": 95.6,
            "future_prediction": 76.0,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 58.1,
            "image_scene": 89.6,
            "image_style": 72.8,
            "image_topic": 98.9,
            "nature_relation": 89.1,
            "object_localization": 78.1,
            "ocr": 94.4,
            "physical_property_reasoning": 69.6,
            "physical_relation": 60.0,
            "social_relation": 85.7,
            "spatial_relationship": 53.3,
            "structuralized_imagetext_understanding": 56.9,
            "Method": [
                "MiniCPM-o-2.6",
                "https://huggingface.co/openbmb/MiniCPM-o-2_6"
            ],
            "Parameters": "8.67B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "OpenBMB",
            "Time": "2025/01/21",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MiniCPM-o-2_6",
            "key": 444
        },
        {
            "Overall": 86.5,
            "AR": 92.7,
            "CP": 84.8,
            "FP-C": 80.9,
            "FP-S": 92.3,
            "LR": 83.7,
            "RR": 82.2,
            "action_recognition": 88.0,
            "attribute_comparison": 74.7,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 95.2,
            "function_reasoning": 94.4,
            "future_prediction": 85.3,
            "identity_reasoning": 98.7,
            "image_emotion": 82.2,
            "image_quality": 71.8,
            "image_scene": 93.8,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 91.3,
            "object_localization": 83.8,
            "ocr": 95.6,
            "physical_property_reasoning": 84.8,
            "physical_relation": 62.7,
            "social_relation": 89.0,
            "spatial_relationship": 76.0,
            "structuralized_imagetext_understanding": 82.6,
            "Method": [
                "BailingMM-Pro-0120",
                "https://zxb.alipay.com/llm/landing"
            ],
            "Parameters": "81B",
            "Language Model": "Bailing-80B",
            "Vision Model": "SigLIP-400M",
            "Org": "Ant Group",
            "Time": "2025/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "BailingMM-Pro-0120",
            "key": 445
        },
        {
            "Overall": 83.9,
            "AR": 82.0,
            "CP": 79.4,
            "FP-C": 85.8,
            "FP-S": 90.5,
            "LR": 83.7,
            "RR": 82.2,
            "action_recognition": 87.2,
            "attribute_comparison": 86.7,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 90.5,
            "function_reasoning": 93.3,
            "future_prediction": 82.7,
            "identity_reasoning": 92.1,
            "image_emotion": 78.9,
            "image_quality": 64.5,
            "image_scene": 83.3,
            "image_style": 78.3,
            "image_topic": 95.6,
            "nature_relation": 94.6,
            "object_localization": 85.7,
            "ocr": 97.8,
            "physical_property_reasoning": 59.5,
            "physical_relation": 69.3,
            "social_relation": 80.2,
            "spatial_relationship": 82.7,
            "structuralized_imagetext_understanding": 84.4,
            "Method": [
                "Doubao-1.5-Pro",
                "https://team.doubao.com/zh/special/doubao_1_5_pro"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "ByteDance",
            "Time": "2025/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "DoubaoVL",
            "key": 446
        },
        {
            "Overall": 84.1,
            "AR": 87.3,
            "CP": 79.3,
            "FP-C": 82.4,
            "FP-S": 91.2,
            "LR": 83.7,
            "RR": 81.0,
            "action_recognition": 82.1,
            "attribute_comparison": 84.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 86.4,
            "function_reasoning": 91.1,
            "future_prediction": 84.0,
            "identity_reasoning": 96.1,
            "image_emotion": 73.3,
            "image_quality": 60.5,
            "image_scene": 90.3,
            "image_style": 78.3,
            "image_topic": 94.4,
            "nature_relation": 93.5,
            "object_localization": 90.5,
            "ocr": 97.8,
            "physical_property_reasoning": 74.7,
            "physical_relation": 61.3,
            "social_relation": 84.6,
            "spatial_relationship": 81.3,
            "structuralized_imagetext_understanding": 83.5,
            "Method": [
                "GLM-4v-Plus-20250111",
                "https://open.bigmodel.cn/dev/api/normal-model/glm-4v"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Zhipu AI",
            "Time": "2025/01/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GLM4V_PLUS_20250111",
            "key": 447
        },
        {
            "Overall": 46.1,
            "AR": 52.2,
            "CP": 58.5,
            "FP-C": 45.3,
            "FP-S": 41.5,
            "LR": 26.1,
            "RR": 37.2,
            "action_recognition": 64.1,
            "attribute_comparison": 40.0,
            "attribute_recognition": 53.9,
            "celebrity_recognition": 25.2,
            "function_reasoning": 47.8,
            "future_prediction": 42.7,
            "identity_reasoning": 68.4,
            "image_emotion": 58.9,
            "image_quality": 24.2,
            "image_scene": 74.3,
            "image_style": 44.6,
            "image_topic": 94.4,
            "nature_relation": 26.1,
            "object_localization": 29.5,
            "ocr": 70.0,
            "physical_property_reasoning": 41.8,
            "physical_relation": 26.7,
            "social_relation": 57.1,
            "spatial_relationship": 21.3,
            "structuralized_imagetext_understanding": 14.7,
            "Method": [
                "Emu3_chat",
                "https://huggingface.co/BAAI/Emu3-Chat"
            ],
            "Parameters": "8.49B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Beijing Academy of Artificial Intelligence",
            "Time": "2025/01/26",
            "OpenSource": "Yes",
            "Verified": "Yes",
            "dir_name": "emu3_chat",
            "key": 448
        },
        {
            "Overall": 50.3,
            "AR": 65.7,
            "CP": 55.4,
            "FP-C": 46.4,
            "FP-S": 43.6,
            "LR": 33.7,
            "RR": 52.3,
            "action_recognition": 79.5,
            "attribute_comparison": 21.3,
            "attribute_recognition": 48.3,
            "celebrity_recognition": 30.6,
            "function_reasoning": 65.6,
            "future_prediction": 42.7,
            "identity_reasoning": 80.3,
            "image_emotion": 66.7,
            "image_quality": 19.4,
            "image_scene": 70.1,
            "image_style": 38.0,
            "image_topic": 87.8,
            "nature_relation": 60.9,
            "object_localization": 20.0,
            "ocr": 87.8,
            "physical_property_reasoning": 51.9,
            "physical_relation": 21.3,
            "social_relation": 69.2,
            "spatial_relationship": 20.0,
            "structuralized_imagetext_understanding": 27.5,
            "Method": [
                "SmolVLM-Instruct",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM",
            "key": 392
        },
        {
            "Overall": 48.1,
            "AR": 66.9,
            "CP": 52.4,
            "FP-C": 43.4,
            "FP-S": 43.2,
            "LR": 28.3,
            "RR": 48.4,
            "action_recognition": 75.2,
            "attribute_comparison": 20.0,
            "attribute_recognition": 50.6,
            "celebrity_recognition": 30.6,
            "function_reasoning": 68.9,
            "future_prediction": 44.0,
            "identity_reasoning": 78.9,
            "image_emotion": 66.7,
            "image_quality": 6.5,
            "image_scene": 71.5,
            "image_style": 39.1,
            "image_topic": 84.4,
            "nature_relation": 53.3,
            "object_localization": 18.1,
            "ocr": 85.6,
            "physical_property_reasoning": 53.2,
            "physical_relation": 20.0,
            "social_relation": 67.0,
            "spatial_relationship": 17.3,
            "structuralized_imagetext_understanding": 17.4,
            "Method": [
                "SmolVLM-Instruct-DPO",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct-DPO"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-DPO",
            "key": 393
        },
        {
            "Overall": 35.3,
            "AR": 46.9,
            "CP": 43.1,
            "FP-C": 36.3,
            "FP-S": 26.9,
            "LR": 17.9,
            "RR": 33.3,
            "action_recognition": 69.2,
            "attribute_comparison": 9.3,
            "attribute_recognition": 25.8,
            "celebrity_recognition": 17.7,
            "function_reasoning": 47.8,
            "future_prediction": 36.0,
            "identity_reasoning": 68.4,
            "image_emotion": 47.8,
            "image_quality": 0.8,
            "image_scene": 59.7,
            "image_style": 27.2,
            "image_topic": 86.7,
            "nature_relation": 41.3,
            "object_localization": 6.7,
            "ocr": 66.7,
            "physical_property_reasoning": 25.3,
            "physical_relation": 9.3,
            "social_relation": 45.1,
            "spatial_relationship": 12.0,
            "structuralized_imagetext_understanding": 5.5,
            "Method": [
                "SmolVLM-Synthetic",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-Synthetic"
            ],
            "Parameters": "2.3B",
            "Language Model": "SmolLM2-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-Synthetic",
            "key": 394
        },
        {
            "Overall": 14.5,
            "AR": 20.4,
            "CP": 17.8,
            "FP-C": 4.1,
            "FP-S": 18.1,
            "LR": 5.4,
            "RR": 13.2,
            "action_recognition": 7.7,
            "attribute_comparison": 1.3,
            "attribute_recognition": 12.4,
            "celebrity_recognition": 6.1,
            "function_reasoning": 18.9,
            "future_prediction": 5.3,
            "identity_reasoning": 36.8,
            "image_emotion": 33.3,
            "image_quality": 2.4,
            "image_scene": 16.7,
            "image_style": 14.1,
            "image_topic": 28.9,
            "nature_relation": 16.3,
            "object_localization": 3.8,
            "ocr": 60.0,
            "physical_property_reasoning": 6.3,
            "physical_relation": 6.7,
            "social_relation": 15.4,
            "spatial_relationship": 1.3,
            "structuralized_imagetext_understanding": 5.5,
            "Method": [
                "SmolVLM-256M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-256M-Instruct"
            ],
            "Parameters": "0.26B",
            "Language Model": "SmolLM2-135M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-256M",
            "key": 449
        },
        {
            "Overall": 33.7,
            "AR": 43.7,
            "CP": 44.1,
            "FP-C": 29.6,
            "FP-S": 27.8,
            "LR": 15.8,
            "RR": 29.5,
            "action_recognition": 53.8,
            "attribute_comparison": 9.3,
            "attribute_recognition": 41.6,
            "celebrity_recognition": 9.5,
            "function_reasoning": 37.8,
            "future_prediction": 34.7,
            "identity_reasoning": 64.5,
            "image_emotion": 43.3,
            "image_quality": 9.7,
            "image_scene": 61.1,
            "image_style": 29.3,
            "image_topic": 80.0,
            "nature_relation": 39.1,
            "object_localization": 9.5,
            "ocr": 65.6,
            "physical_property_reasoning": 30.4,
            "physical_relation": 5.3,
            "social_relation": 39.6,
            "spatial_relationship": 12.0,
            "structuralized_imagetext_understanding": 2.8,
            "Method": [
                "SmolVLM-500M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM-500M-Instruct"
            ],
            "Parameters": "0.51B",
            "Language Model": "SmolLM2-360M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/01/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM-500M",
            "key": 450
        },
        {
            "Overall": 58.3,
            "AR": 64.1,
            "CP": 66.9,
            "FP-C": 52.8,
            "FP-S": 61.7,
            "LR": 29.3,
            "RR": 55.4,
            "action_recognition": 78.6,
            "attribute_comparison": 32.0,
            "attribute_recognition": 80.9,
            "celebrity_recognition": 59.2,
            "function_reasoning": 63.3,
            "future_prediction": 53.3,
            "identity_reasoning": 92.1,
            "image_emotion": 63.3,
            "image_quality": 30.6,
            "image_scene": 81.9,
            "image_style": 66.3,
            "image_topic": 96.7,
            "nature_relation": 60.9,
            "object_localization": 27.6,
            "ocr": 86.7,
            "physical_property_reasoning": 38.0,
            "physical_relation": 30.7,
            "social_relation": 70.3,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 12.8,
            "Method": [
                "Janus-Pro-7B",
                "https://huggingface.co/deepseek-ai/Janus-Pro-7B"
            ],
            "Parameters": "7.42B",
            "Language Model": "DeepSeek-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "deepseek",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Janus-Pro-7B",
            "key": 454
        },
        {
            "Overall": 83.2,
            "AR": 93.1,
            "CP": 80.0,
            "FP-C": 81.6,
            "FP-S": 86.8,
            "LR": 73.9,
            "RR": 82.6,
            "action_recognition": 89.7,
            "attribute_comparison": 82.7,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 85.0,
            "function_reasoning": 96.7,
            "future_prediction": 85.3,
            "identity_reasoning": 100.0,
            "image_emotion": 77.8,
            "image_quality": 60.5,
            "image_scene": 88.2,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 92.4,
            "object_localization": 76.2,
            "ocr": 95.6,
            "physical_property_reasoning": 82.3,
            "physical_relation": 64.0,
            "social_relation": 87.9,
            "spatial_relationship": 68.0,
            "structuralized_imagetext_understanding": 66.1,
            "Method": [
                "Ola-7b",
                "https://huggingface.co/THUdyh/Ola-7b"
            ],
            "Parameters": "8.88B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "Oryx-ViT",
            "Org": "THU",
            "Time": "2025/02/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "ola",
            "key": 455
        },
        {
            "Overall": 66.6,
            "AR": 79.6,
            "CP": 71.1,
            "FP-C": 56.6,
            "FP-S": 70.1,
            "LR": 44.0,
            "RR": 65.5,
            "action_recognition": 79.5,
            "attribute_comparison": 46.7,
            "attribute_recognition": 82.0,
            "celebrity_recognition": 55.8,
            "function_reasoning": 87.8,
            "future_prediction": 60.0,
            "identity_reasoning": 90.8,
            "image_emotion": 68.9,
            "image_quality": 42.7,
            "image_scene": 81.9,
            "image_style": 68.5,
            "image_topic": 97.8,
            "nature_relation": 69.6,
            "object_localization": 58.1,
            "ocr": 95.6,
            "physical_property_reasoning": 59.5,
            "physical_relation": 50.7,
            "social_relation": 73.6,
            "spatial_relationship": 30.7,
            "structuralized_imagetext_understanding": 33.0,
            "Method": [
                "Ovis2-1B",
                "https://huggingface.co/AIDC-AI/Ovis2-1B"
            ],
            "Parameters": "1.27B",
            "Language Model": "Qwen2.5-0.5B",
            "Vision Model": "AIMv2 Large",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-1B",
            "key": 456
        },
        {
            "Overall": 76.8,
            "AR": 84.1,
            "CP": 78.9,
            "FP-C": 72.7,
            "FP-S": 80.3,
            "LR": 62.0,
            "RR": 74.4,
            "action_recognition": 87.2,
            "attribute_comparison": 78.7,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 69.4,
            "function_reasoning": 92.2,
            "future_prediction": 70.7,
            "identity_reasoning": 96.1,
            "image_emotion": 82.2,
            "image_quality": 55.6,
            "image_scene": 86.1,
            "image_style": 76.1,
            "image_topic": 98.9,
            "nature_relation": 72.8,
            "object_localization": 72.4,
            "ocr": 95.6,
            "physical_property_reasoning": 63.3,
            "physical_relation": 65.3,
            "social_relation": 83.5,
            "spatial_relationship": 44.0,
            "structuralized_imagetext_understanding": 56.0,
            "Method": [
                "Ovis2-2B",
                "https://huggingface.co/AIDC-AI/Ovis2-2B"
            ],
            "Parameters": "2.46B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "AIMv2 Large",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-2B",
            "key": 457
        },
        {
            "Overall": 81.0,
            "AR": 87.8,
            "CP": 80.4,
            "FP-C": 75.7,
            "FP-S": 86.8,
            "LR": 70.7,
            "RR": 79.1,
            "action_recognition": 84.6,
            "attribute_comparison": 81.3,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 82.3,
            "function_reasoning": 92.2,
            "future_prediction": 81.3,
            "identity_reasoning": 100.0,
            "image_emotion": 83.3,
            "image_quality": 57.3,
            "image_scene": 88.2,
            "image_style": 79.3,
            "image_topic": 97.8,
            "nature_relation": 80.4,
            "object_localization": 82.9,
            "ocr": 95.6,
            "physical_property_reasoning": 70.9,
            "physical_relation": 69.3,
            "social_relation": 85.7,
            "spatial_relationship": 56.0,
            "structuralized_imagetext_understanding": 63.3,
            "Method": [
                "Ovis2-4B",
                "https://huggingface.co/AIDC-AI/Ovis2-4B"
            ],
            "Parameters": "4.62B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-4B",
            "key": 458
        },
        {
            "Overall": 83.4,
            "AR": 89.4,
            "CP": 81.9,
            "FP-C": 81.6,
            "FP-S": 87.5,
            "LR": 71.2,
            "RR": 84.5,
            "action_recognition": 91.5,
            "attribute_comparison": 88.0,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 83.7,
            "function_reasoning": 96.7,
            "future_prediction": 78.7,
            "identity_reasoning": 94.7,
            "image_emotion": 86.7,
            "image_quality": 62.1,
            "image_scene": 90.3,
            "image_style": 75.0,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 78.1,
            "ocr": 97.8,
            "physical_property_reasoning": 75.9,
            "physical_relation": 69.3,
            "social_relation": 87.9,
            "spatial_relationship": 60.0,
            "structuralized_imagetext_understanding": 66.1,
            "Method": [
                "Ovis2-8B",
                "https://huggingface.co/AIDC-AI/Ovis2-8B"
            ],
            "Parameters": "8.94B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-8B",
            "key": 459
        },
        {
            "Overall": 85.5,
            "AR": 90.2,
            "CP": 81.5,
            "FP-C": 90.6,
            "FP-S": 88.6,
            "LR": 79.3,
            "RR": 82.9,
            "action_recognition": 91.5,
            "attribute_comparison": 96.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 83.7,
            "function_reasoning": 94.4,
            "future_prediction": 84.0,
            "identity_reasoning": 97.4,
            "image_emotion": 81.1,
            "image_quality": 65.3,
            "image_scene": 88.2,
            "image_style": 76.1,
            "image_topic": 98.9,
            "nature_relation": 88.0,
            "object_localization": 81.9,
            "ocr": 100.0,
            "physical_property_reasoning": 78.5,
            "physical_relation": 76.0,
            "social_relation": 83.5,
            "spatial_relationship": 84.0,
            "structuralized_imagetext_understanding": 76.1,
            "Method": [
                "Ovis2-16B",
                "https://huggingface.co/AIDC-AI/Ovis2-16B"
            ],
            "Parameters": "16.2B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "AIMv2 Huge",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-16B",
            "key": 460
        },
        {
            "Overall": 86.5,
            "AR": 93.1,
            "CP": 82.0,
            "FP-C": 86.5,
            "FP-S": 91.6,
            "LR": 81.5,
            "RR": 84.9,
            "action_recognition": 88.0,
            "attribute_comparison": 90.7,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 85.7,
            "function_reasoning": 94.4,
            "future_prediction": 86.7,
            "identity_reasoning": 98.7,
            "image_emotion": 82.2,
            "image_quality": 64.5,
            "image_scene": 88.2,
            "image_style": 79.3,
            "image_topic": 98.9,
            "nature_relation": 94.6,
            "object_localization": 90.5,
            "ocr": 98.9,
            "physical_property_reasoning": 86.1,
            "physical_relation": 72.0,
            "social_relation": 85.7,
            "spatial_relationship": 80.0,
            "structuralized_imagetext_understanding": 78.0,
            "Method": [
                "Ovis2-34B",
                "https://huggingface.co/AIDC-AI/Ovis2-34B"
            ],
            "Parameters": "34.9B",
            "Language Model": "Qwen2.5-32B",
            "Vision Model": "AIMv2-1B",
            "Org": "Alibaba",
            "Time": "2025/02/18",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis2-34B",
            "key": 461
        },
        {
            "Overall": 76.5,
            "AR": 79.2,
            "CP": 78.5,
            "FP-C": 65.2,
            "FP-S": 85.2,
            "LR": 67.4,
            "RR": 73.3,
            "action_recognition": 82.9,
            "attribute_comparison": 68.0,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 92.5,
            "function_reasoning": 91.1,
            "future_prediction": 74.7,
            "identity_reasoning": 92.1,
            "image_emotion": 78.9,
            "image_quality": 53.2,
            "image_scene": 92.4,
            "image_style": 71.7,
            "image_topic": 97.8,
            "nature_relation": 77.2,
            "object_localization": 64.8,
            "ocr": 95.6,
            "physical_property_reasoning": 53.2,
            "physical_relation": 48.0,
            "social_relation": 90.1,
            "spatial_relationship": 34.7,
            "structuralized_imagetext_understanding": 62.4,
            "Method": [
                "Qwen2.5-VL-3B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct"
            ],
            "Parameters": "3.75B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-3B-Instruct",
            "key": 462
        },
        {
            "Overall": 82.1,
            "AR": 85.3,
            "CP": 83.1,
            "FP-C": 77.2,
            "FP-S": 89.6,
            "LR": 71.2,
            "RR": 77.5,
            "action_recognition": 87.2,
            "attribute_comparison": 76.0,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 91.2,
            "function_reasoning": 92.2,
            "future_prediction": 80.0,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 64.5,
            "image_scene": 92.4,
            "image_style": 82.6,
            "image_topic": 97.8,
            "nature_relation": 82.6,
            "object_localization": 82.9,
            "ocr": 95.6,
            "physical_property_reasoning": 65.8,
            "physical_relation": 56.0,
            "social_relation": 90.1,
            "spatial_relationship": 62.7,
            "structuralized_imagetext_understanding": 65.1,
            "Method": [
                "Qwen2.5-VL-7B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct"
            ],
            "Parameters": "8.29B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-7B-Instruct",
            "key": 463
        },
        {
            "Overall": 87.4,
            "AR": 86.9,
            "CP": 84.8,
            "FP-C": 85.8,
            "FP-S": 96.3,
            "LR": 83.2,
            "RR": 82.9,
            "action_recognition": 86.3,
            "attribute_comparison": 86.7,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 96.6,
            "function_reasoning": 93.3,
            "future_prediction": 81.3,
            "identity_reasoning": 96.1,
            "image_emotion": 81.1,
            "image_quality": 70.2,
            "image_scene": 91.7,
            "image_style": 83.7,
            "image_topic": 98.9,
            "nature_relation": 91.3,
            "object_localization": 92.4,
            "ocr": 100.0,
            "physical_property_reasoning": 70.9,
            "physical_relation": 62.7,
            "social_relation": 91.2,
            "spatial_relationship": 84.0,
            "structuralized_imagetext_understanding": 84.4,
            "Method": [
                "Qwen2.5-VL-72B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct"
            ],
            "Parameters": "73.4B",
            "Language Model": "Qwen2.5-72B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/02/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-72B-Instruct",
            "key": 464
        },
        {
            "Overall": 83.5,
            "AR": 84.5,
            "CP": 79.4,
            "FP-C": 85.4,
            "FP-S": 92.6,
            "LR": 77.2,
            "RR": 78.7,
            "action_recognition": 91.5,
            "attribute_comparison": 82.7,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 97.3,
            "function_reasoning": 93.3,
            "future_prediction": 76.0,
            "identity_reasoning": 98.7,
            "image_emotion": 78.9,
            "image_quality": 56.5,
            "image_scene": 87.5,
            "image_style": 82.6,
            "image_topic": 95.6,
            "nature_relation": 92.4,
            "object_localization": 83.8,
            "ocr": 97.8,
            "physical_property_reasoning": 60.8,
            "physical_relation": 54.7,
            "social_relation": 84.6,
            "spatial_relationship": 78.7,
            "structuralized_imagetext_understanding": 78.0,
            "Method": [
                "Gemini-2.0-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2025/02/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GeminiPro2-0",
            "key": 465
        },
        {
            "Overall": 79.5,
            "AR": 85.7,
            "CP": 80.7,
            "FP-C": 82.4,
            "FP-S": 77.3,
            "LR": 75.0,
            "RR": 75.2,
            "action_recognition": 82.1,
            "attribute_comparison": 86.7,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 58.5,
            "function_reasoning": 95.6,
            "future_prediction": 72.0,
            "identity_reasoning": 94.7,
            "image_emotion": 81.1,
            "image_quality": 56.5,
            "image_scene": 88.9,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 90.2,
            "object_localization": 79.0,
            "ocr": 96.7,
            "physical_property_reasoning": 65.8,
            "physical_relation": 53.3,
            "social_relation": 78.0,
            "spatial_relationship": 78.7,
            "structuralized_imagetext_understanding": 77.1,
            "Method": [
                "Claude3.7-Sonnet",
                "https://docs.anthropic.com/claude/docs/vision"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Anthropic",
            "Time": "2025/02/27",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Claude3-7V_Sonnet",
            "key": 466
        },
        {
            "Overall": 76.2,
            "AR": 78.0,
            "CP": 76.7,
            "FP-C": 69.3,
            "FP-S": 80.3,
            "LR": 72.8,
            "RR": 76.0,
            "action_recognition": 76.9,
            "attribute_comparison": 69.3,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 74.1,
            "function_reasoning": 87.8,
            "future_prediction": 77.3,
            "identity_reasoning": 93.4,
            "image_emotion": 74.4,
            "image_quality": 50.8,
            "image_scene": 88.2,
            "image_style": 75.0,
            "image_topic": 97.8,
            "nature_relation": 82.6,
            "object_localization": 72.4,
            "ocr": 94.4,
            "physical_property_reasoning": 51.9,
            "physical_relation": 60.0,
            "social_relation": 82.4,
            "spatial_relationship": 57.3,
            "structuralized_imagetext_understanding": 69.7,
            "Method": [
                "moonshot-v1-8k",
                "https://platform.moonshot.cn/docs/api/chat"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Moonshot AI",
            "Time": "2025/03/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "moonshot-v1-8k",
            "key": 467
        },
        {
            "Overall": 82.5,
            "AR": 89.4,
            "CP": 78.0,
            "FP-C": 80.9,
            "FP-S": 91.2,
            "LR": 73.9,
            "RR": 78.7,
            "action_recognition": 86.3,
            "attribute_comparison": 76.0,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 89.1,
            "function_reasoning": 95.6,
            "future_prediction": 82.7,
            "identity_reasoning": 98.7,
            "image_emotion": 82.2,
            "image_quality": 50.0,
            "image_scene": 86.8,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 81.9,
            "ocr": 100.0,
            "physical_property_reasoning": 73.4,
            "physical_relation": 52.0,
            "social_relation": 85.7,
            "spatial_relationship": 77.3,
            "structuralized_imagetext_understanding": 67.9,
            "Method": [
                "grok-2-vision-1212",
                "https://docs.x.ai/docs/overview"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "xAI",
            "Time": "2025/03/03",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "grok-2-vision-1212",
            "key": 468
        },
        {
            "Overall": 80.1,
            "AR": 83.3,
            "CP": 80.9,
            "FP-C": 78.3,
            "FP-S": 86.1,
            "LR": 69.6,
            "RR": 74.8,
            "action_recognition": 86.3,
            "attribute_comparison": 81.3,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 83.7,
            "function_reasoning": 90.0,
            "future_prediction": 80.0,
            "identity_reasoning": 96.1,
            "image_emotion": 81.1,
            "image_quality": 60.5,
            "image_scene": 89.6,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 81.5,
            "object_localization": 78.1,
            "ocr": 94.4,
            "physical_property_reasoning": 63.3,
            "physical_relation": 58.7,
            "social_relation": 81.3,
            "spatial_relationship": 62.7,
            "structuralized_imagetext_understanding": 62.4,
            "Method": [
                "DeepSeek-VL2",
                "https://huggingface.co/deepseek-ai/deepseek-vl2"
            ],
            "Parameters": "27.5B",
            "Language Model": "DeepSeekMoE-27B",
            "Vision Model": "SigLIP-400M",
            "Org": "DeepSeek",
            "Time": "2025/01/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "deepseek_vl2",
            "key": 469
        },
        {
            "Overall": 53.2,
            "AR": 67.3,
            "CP": 60.4,
            "FP-C": 49.4,
            "FP-S": 47.6,
            "LR": 38.6,
            "RR": 48.8,
            "action_recognition": 84.6,
            "attribute_comparison": 22.7,
            "attribute_recognition": 62.9,
            "celebrity_recognition": 31.3,
            "function_reasoning": 73.3,
            "future_prediction": 52.0,
            "identity_reasoning": 82.9,
            "image_emotion": 66.7,
            "image_quality": 28.2,
            "image_scene": 80.6,
            "image_style": 42.4,
            "image_topic": 84.4,
            "nature_relation": 46.7,
            "object_localization": 25.7,
            "ocr": 84.4,
            "physical_property_reasoning": 45.6,
            "physical_relation": 29.3,
            "social_relation": 67.0,
            "spatial_relationship": 21.3,
            "structuralized_imagetext_understanding": 29.4,
            "Method": [
                "SmolVLM2",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct"
            ],
            "Parameters": "2.25B",
            "Language Model": "SmolLM2-1.7M",
            "Vision Model": "SigLIP-400M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2",
            "key": 470
        },
        {
            "Overall": 1.9,
            "AR": 1.6,
            "CP": 1.5,
            "FP-C": 0.4,
            "FP-S": 3.9,
            "LR": 0.5,
            "RR": 1.9,
            "action_recognition": 0.9,
            "attribute_comparison": 0.0,
            "attribute_recognition": 1.1,
            "celebrity_recognition": 0.0,
            "function_reasoning": 0.0,
            "future_prediction": 0.0,
            "identity_reasoning": 1.3,
            "image_emotion": 0.0,
            "image_quality": 5.6,
            "image_scene": 0.0,
            "image_style": 1.1,
            "image_topic": 0.0,
            "nature_relation": 5.4,
            "object_localization": 0.0,
            "ocr": 17.8,
            "physical_property_reasoning": 3.8,
            "physical_relation": 0.0,
            "social_relation": 0.0,
            "spatial_relationship": 0.0,
            "structuralized_imagetext_understanding": 0.9,
            "Method": [
                "SmolVLM2-256M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-256M-Video-Instruct"
            ],
            "Parameters": "0.26B",
            "Language Model": "SmolLM2-135M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2-256M",
            "key": 471
        },
        {
            "Overall": 33.4,
            "AR": 45.3,
            "CP": 41.9,
            "FP-C": 24.3,
            "FP-S": 28.3,
            "LR": 16.3,
            "RR": 34.1,
            "action_recognition": 44.4,
            "attribute_comparison": 10.7,
            "attribute_recognition": 38.2,
            "celebrity_recognition": 7.5,
            "function_reasoning": 40.0,
            "future_prediction": 34.7,
            "identity_reasoning": 64.5,
            "image_emotion": 41.1,
            "image_quality": 7.3,
            "image_scene": 62.5,
            "image_style": 31.5,
            "image_topic": 67.8,
            "nature_relation": 45.7,
            "object_localization": 8.6,
            "ocr": 75.6,
            "physical_property_reasoning": 32.9,
            "physical_relation": 4.0,
            "social_relation": 47.3,
            "spatial_relationship": 6.7,
            "structuralized_imagetext_understanding": 3.7,
            "Method": [
                "SmolVLM2-500M",
                "https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
            ],
            "Parameters": "0.51B",
            "Language Model": "SmolLM2-360M",
            "Vision Model": "ViT-93M",
            "Org": "HuggingFace",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SmolVLM2-500M",
            "key": 472
        },
        {
            "Overall": 74.9,
            "AR": 84.9,
            "CP": 78.3,
            "FP-C": 69.3,
            "FP-S": 76.6,
            "LR": 62.0,
            "RR": 70.2,
            "action_recognition": 80.3,
            "attribute_comparison": 76.0,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 70.7,
            "function_reasoning": 88.9,
            "future_prediction": 69.3,
            "identity_reasoning": 94.7,
            "image_emotion": 76.7,
            "image_quality": 55.6,
            "image_scene": 89.6,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 78.3,
            "object_localization": 64.8,
            "ocr": 91.1,
            "physical_property_reasoning": 70.9,
            "physical_relation": 49.3,
            "social_relation": 79.1,
            "spatial_relationship": 45.3,
            "structuralized_imagetext_understanding": 56.9,
            "Method": [
                "Phi-4-MultiModal",
                "https://huggingface.co/microsoft/Phi-4-multimodal-instruct"
            ],
            "Parameters": "5.57B",
            "Language Model": "Phi-4-Mini",
            "Vision Model": "SigLIP-400M",
            "Org": "Microsoft",
            "Time": "2025/03/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Phi-4-Vision",
            "key": 473
        },
        {
            "Overall": 81.6,
            "AR": 84.1,
            "CP": 82.4,
            "FP-C": 76.4,
            "FP-S": 86.3,
            "LR": 72.3,
            "RR": 81.8,
            "action_recognition": 88.0,
            "attribute_comparison": 81.3,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 78.9,
            "function_reasoning": 92.2,
            "future_prediction": 82.7,
            "identity_reasoning": 97.4,
            "image_emotion": 87.8,
            "image_quality": 62.9,
            "image_scene": 88.2,
            "image_style": 78.3,
            "image_topic": 98.9,
            "nature_relation": 88.0,
            "object_localization": 79.0,
            "ocr": 97.8,
            "physical_property_reasoning": 62.0,
            "physical_relation": 60.0,
            "social_relation": 93.4,
            "spatial_relationship": 53.3,
            "structuralized_imagetext_understanding": 65.1,
            "Method": [
                "MUG-U-7B",
                "https://github.com/Shopee-MUG/MUG-U"
            ],
            "Parameters": "7B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Shopee",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MUG-U-7B",
            "key": 474
        },
        {
            "Overall": 66.8,
            "AR": 78.0,
            "CP": 72.2,
            "FP-C": 54.3,
            "FP-S": 67.3,
            "LR": 52.2,
            "RR": 67.4,
            "action_recognition": 83.8,
            "attribute_comparison": 41.3,
            "attribute_recognition": 83.1,
            "celebrity_recognition": 78.2,
            "function_reasoning": 88.9,
            "future_prediction": 70.7,
            "identity_reasoning": 94.7,
            "image_emotion": 76.7,
            "image_quality": 33.9,
            "image_scene": 85.4,
            "image_style": 72.8,
            "image_topic": 98.9,
            "nature_relation": 81.5,
            "object_localization": 19.0,
            "ocr": 90.0,
            "physical_property_reasoning": 49.4,
            "physical_relation": 25.3,
            "social_relation": 87.9,
            "spatial_relationship": 21.3,
            "structuralized_imagetext_understanding": 39.4,
            "Method": [
                "Gemma3-4B",
                "https://huggingface.co/google/gemma-3-4b-it"
            ],
            "Parameters": "4.3B",
            "Language Model": "Gemma3-4B",
            "Vision Model": "SigLIP-400M",
            "Org": "Google",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Gemma3-4B",
            "key": 475
        },
        {
            "Overall": 74.3,
            "AR": 84.1,
            "CP": 75.0,
            "FP-C": 65.5,
            "FP-S": 77.7,
            "LR": 66.8,
            "RR": 72.5,
            "action_recognition": 83.8,
            "attribute_comparison": 61.3,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 83.0,
            "function_reasoning": 91.1,
            "future_prediction": 78.7,
            "identity_reasoning": 97.4,
            "image_emotion": 74.4,
            "image_quality": 45.2,
            "image_scene": 84.0,
            "image_style": 79.3,
            "image_topic": 97.8,
            "nature_relation": 89.1,
            "object_localization": 52.4,
            "ocr": 91.1,
            "physical_property_reasoning": 63.3,
            "physical_relation": 32.0,
            "social_relation": 89.0,
            "spatial_relationship": 41.3,
            "structuralized_imagetext_understanding": 58.7,
            "Method": [
                "Gemma3-12B",
                "https://huggingface.co/google/gemma-3-12b-it"
            ],
            "Parameters": "12.2B",
            "Language Model": "Gemma3-12B",
            "Vision Model": "SigLIP-400M",
            "Org": "Google",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Gemma3-12B",
            "key": 476
        },
        {
            "Overall": 78.2,
            "AR": 87.3,
            "CP": 77.8,
            "FP-C": 70.0,
            "FP-S": 82.8,
            "LR": 72.3,
            "RR": 75.2,
            "action_recognition": 80.3,
            "attribute_comparison": 70.7,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 89.8,
            "function_reasoning": 91.1,
            "future_prediction": 81.3,
            "identity_reasoning": 100.0,
            "image_emotion": 81.1,
            "image_quality": 48.4,
            "image_scene": 86.1,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 89.1,
            "object_localization": 60.0,
            "ocr": 95.6,
            "physical_property_reasoning": 70.9,
            "physical_relation": 45.3,
            "social_relation": 85.7,
            "spatial_relationship": 53.3,
            "structuralized_imagetext_understanding": 66.1,
            "Method": [
                "Gemma3-27B",
                "https://huggingface.co/google/gemma-3-27b-it"
            ],
            "Parameters": "27.4B",
            "Language Model": "Gemma3-27B",
            "Vision Model": "SigLIP-400M",
            "Org": "Google",
            "Time": "2025/03/19",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Gemma3-27B",
            "key": 477
        },
        {
            "Overall": 45.3,
            "AR": 58.8,
            "CP": 50.4,
            "FP-C": 40.8,
            "FP-S": 39.2,
            "LR": 23.9,
            "RR": 51.9,
            "action_recognition": 61.5,
            "attribute_comparison": 29.3,
            "attribute_recognition": 44.9,
            "celebrity_recognition": 32.0,
            "function_reasoning": 61.1,
            "future_prediction": 42.7,
            "identity_reasoning": 77.6,
            "image_emotion": 54.4,
            "image_quality": 4.8,
            "image_scene": 75.0,
            "image_style": 39.1,
            "image_topic": 81.1,
            "nature_relation": 57.6,
            "object_localization": 19.0,
            "ocr": 68.9,
            "physical_property_reasoning": 38.0,
            "physical_relation": 24.0,
            "social_relation": 69.2,
            "spatial_relationship": 20.0,
            "structuralized_imagetext_understanding": 11.0,
            "Method": [
                "AKI-4B",
                "https://huggingface.co/Sony/AKI-4B-phi-3.5-mini"
            ],
            "Parameters": "4.33B",
            "Language Model": "Phi-3.5",
            "Vision Model": "SigLIP-400M",
            "Org": "Sony",
            "Time": "2025/03/25",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "AKI",
            "key": 478
        },
        {
            "Overall": 83.3,
            "AR": 89.0,
            "CP": 81.9,
            "FP-C": 88.8,
            "FP-S": 82.4,
            "LR": 77.2,
            "RR": 81.4,
            "action_recognition": 92.3,
            "attribute_comparison": 81.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 67.3,
            "function_reasoning": 92.2,
            "future_prediction": 80.0,
            "identity_reasoning": 97.4,
            "image_emotion": 87.8,
            "image_quality": 59.7,
            "image_scene": 87.5,
            "image_style": 81.5,
            "image_topic": 97.8,
            "nature_relation": 96.7,
            "object_localization": 85.7,
            "ocr": 96.7,
            "physical_property_reasoning": 77.2,
            "physical_relation": 57.3,
            "social_relation": 85.7,
            "spatial_relationship": 90.7,
            "structuralized_imagetext_understanding": 75.2,
            "Method": [
                "GPT-4.5",
                "https://openai.com/index/introducing-gpt-4-5/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/03/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "GPT4.5",
            "key": 479
        },
        {
            "Overall": 79.1,
            "AR": 86.1,
            "CP": 80.6,
            "FP-C": 72.7,
            "FP-S": 84.2,
            "LR": 67.4,
            "RR": 75.6,
            "action_recognition": 88.0,
            "attribute_comparison": 76.0,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 79.6,
            "function_reasoning": 93.3,
            "future_prediction": 78.7,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 58.9,
            "image_scene": 88.2,
            "image_style": 82.6,
            "image_topic": 96.7,
            "nature_relation": 70.7,
            "object_localization": 76.2,
            "ocr": 94.4,
            "physical_property_reasoning": 67.1,
            "physical_relation": 68.0,
            "social_relation": 86.8,
            "spatial_relationship": 45.3,
            "structuralized_imagetext_understanding": 59.6,
            "Method": [
                "Ristretto-3B",
                "https://huggingface.co/LiAutoAD/Ristretto-3B"
            ],
            "Parameters": "3.84B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "SigLIP-400M",
            "Org": "LiAutoAD",
            "Time": "2025/04/01",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ristretto-3B",
            "key": 480
        },
        {
            "Overall": 85.2,
            "AR": 90.2,
            "CP": 83.7,
            "FP-C": 88.0,
            "FP-S": 84.2,
            "LR": 87.5,
            "RR": 81.0,
            "action_recognition": 95.7,
            "attribute_comparison": 81.3,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 72.1,
            "function_reasoning": 94.4,
            "future_prediction": 88.0,
            "identity_reasoning": 98.7,
            "image_emotion": 84.4,
            "image_quality": 70.2,
            "image_scene": 86.1,
            "image_style": 82.6,
            "image_topic": 98.9,
            "nature_relation": 94.6,
            "object_localization": 82.9,
            "ocr": 98.9,
            "physical_property_reasoning": 77.2,
            "physical_relation": 54.7,
            "social_relation": 89.0,
            "spatial_relationship": 82.7,
            "structuralized_imagetext_understanding": 87.2,
            "Method": [
                "ChatGPT-4o-latest",
                "https://openai.com/index/hello-gpt-4o/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/07",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "ChatGPT4o",
            "key": 481
        },
        {
            "Overall": 88.1,
            "AR": 86.1,
            "CP": 85.2,
            "FP-C": 92.9,
            "FP-S": 93.3,
            "LR": 87.5,
            "RR": 82.9,
            "action_recognition": 94.0,
            "attribute_comparison": 94.7,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 93.2,
            "function_reasoning": 90.0,
            "future_prediction": 78.7,
            "identity_reasoning": 94.7,
            "image_emotion": 84.4,
            "image_quality": 68.5,
            "image_scene": 88.2,
            "image_style": 90.2,
            "image_topic": 98.9,
            "nature_relation": 93.5,
            "object_localization": 90.5,
            "ocr": 96.7,
            "physical_property_reasoning": 73.4,
            "physical_relation": 65.3,
            "social_relation": 86.8,
            "spatial_relationship": 89.3,
            "structuralized_imagetext_understanding": 93.6,
            "Method": [
                "Gemini-2.5-Pro",
                "https://deepmind.google/technologies/gemini/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "Google",
            "Time": "2025/04/07",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "GeminiPro2-5",
            "key": 482
        },
        {
            "Overall": 80.6,
            "AR": 84.1,
            "CP": 81.1,
            "FP-C": 74.9,
            "FP-S": 89.3,
            "LR": 69.0,
            "RR": 76.0,
            "action_recognition": 87.2,
            "attribute_comparison": 74.7,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 89.1,
            "function_reasoning": 94.4,
            "future_prediction": 80.0,
            "identity_reasoning": 97.4,
            "image_emotion": 75.6,
            "image_quality": 63.7,
            "image_scene": 89.6,
            "image_style": 79.3,
            "image_topic": 98.9,
            "nature_relation": 83.7,
            "object_localization": 83.8,
            "ocr": 93.3,
            "physical_property_reasoning": 59.5,
            "physical_relation": 57.3,
            "social_relation": 83.5,
            "spatial_relationship": 56.0,
            "structuralized_imagetext_understanding": 61.5,
            "Method": [
                "Kimi-VL-A3B-Instruct",
                "https://huggingface.co/moonshotai/Kimi-VL-A3B-Instruct"
            ],
            "Parameters": "16.4B",
            "Language Model": "Moonlight-16B-A3B",
            "Vision Model": "MoonViT",
            "Org": "moonshot.ai",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kimi-VL-A3B-Instruct",
            "key": 483
        },
        {
            "Overall": 66.4,
            "AR": 73.1,
            "CP": 72.8,
            "FP-C": 59.2,
            "FP-S": 71.5,
            "LR": 42.4,
            "RR": 62.8,
            "action_recognition": 85.5,
            "attribute_comparison": 45.3,
            "attribute_recognition": 80.9,
            "celebrity_recognition": 60.5,
            "function_reasoning": 80.0,
            "future_prediction": 65.3,
            "identity_reasoning": 94.7,
            "image_emotion": 77.8,
            "image_quality": 35.5,
            "image_scene": 89.6,
            "image_style": 68.5,
            "image_topic": 96.7,
            "nature_relation": 57.6,
            "object_localization": 61.0,
            "ocr": 92.2,
            "physical_property_reasoning": 44.3,
            "physical_relation": 44.0,
            "social_relation": 83.5,
            "spatial_relationship": 32.0,
            "structuralized_imagetext_understanding": 26.6,
            "Method": [
                "InternVL3-1B",
                "https://huggingface.co/OpenGVLab/InternVL3-1B"
            ],
            "Parameters": "0.94B",
            "Language Model": "Qwen2.5-0.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-1B",
            "key": 484
        },
        {
            "Overall": 77.0,
            "AR": 83.3,
            "CP": 79.1,
            "FP-C": 70.8,
            "FP-S": 82.4,
            "LR": 62.5,
            "RR": 74.4,
            "action_recognition": 88.0,
            "attribute_comparison": 74.7,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 74.8,
            "function_reasoning": 91.1,
            "future_prediction": 73.3,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 58.1,
            "image_scene": 86.8,
            "image_style": 75.0,
            "image_topic": 98.9,
            "nature_relation": 81.5,
            "object_localization": 76.2,
            "ocr": 94.4,
            "physical_property_reasoning": 60.8,
            "physical_relation": 45.3,
            "social_relation": 91.2,
            "spatial_relationship": 40.0,
            "structuralized_imagetext_understanding": 55.0,
            "Method": [
                "InternVL3-2B",
                "https://huggingface.co/OpenGVLab/InternVL3-2B"
            ],
            "Parameters": "2.09B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-2B",
            "key": 485
        },
        {
            "Overall": 81.9,
            "AR": 85.7,
            "CP": 81.1,
            "FP-C": 79.0,
            "FP-S": 86.8,
            "LR": 69.6,
            "RR": 83.7,
            "action_recognition": 92.3,
            "attribute_comparison": 78.7,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 81.6,
            "function_reasoning": 91.1,
            "future_prediction": 77.3,
            "identity_reasoning": 98.7,
            "image_emotion": 85.6,
            "image_quality": 60.5,
            "image_scene": 88.9,
            "image_style": 75.0,
            "image_topic": 98.9,
            "nature_relation": 89.1,
            "object_localization": 79.0,
            "ocr": 96.7,
            "physical_property_reasoning": 67.1,
            "physical_relation": 70.7,
            "social_relation": 89.0,
            "spatial_relationship": 58.7,
            "structuralized_imagetext_understanding": 64.2,
            "Method": [
                "InternVL3-8B",
                "https://huggingface.co/OpenGVLab/InternVL3-8B"
            ],
            "Parameters": "7.94B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-8B",
            "key": 486
        },
        {
            "Overall": 82.4,
            "AR": 82.4,
            "CP": 81.3,
            "FP-C": 79.8,
            "FP-S": 87.7,
            "LR": 74.5,
            "RR": 84.1,
            "action_recognition": 89.7,
            "attribute_comparison": 89.3,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 81.6,
            "function_reasoning": 93.3,
            "future_prediction": 84.0,
            "identity_reasoning": 98.7,
            "image_emotion": 84.4,
            "image_quality": 58.9,
            "image_scene": 91.0,
            "image_style": 77.2,
            "image_topic": 97.8,
            "nature_relation": 91.3,
            "object_localization": 82.9,
            "ocr": 96.7,
            "physical_property_reasoning": 54.4,
            "physical_relation": 66.7,
            "social_relation": 91.2,
            "spatial_relationship": 54.7,
            "structuralized_imagetext_understanding": 67.9,
            "Method": [
                "InternVL3-9B",
                "https://huggingface.co/OpenGVLab/InternVL3-9B"
            ],
            "Parameters": "9.14B",
            "Language Model": "InternLM3-8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-9B",
            "key": 487
        },
        {
            "Overall": 83.3,
            "AR": 87.8,
            "CP": 80.6,
            "FP-C": 80.5,
            "FP-S": 87.9,
            "LR": 77.7,
            "RR": 83.7,
            "action_recognition": 86.3,
            "attribute_comparison": 80.0,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 83.0,
            "function_reasoning": 94.4,
            "future_prediction": 82.7,
            "identity_reasoning": 96.1,
            "image_emotion": 80.0,
            "image_quality": 59.7,
            "image_scene": 88.9,
            "image_style": 78.3,
            "image_topic": 98.9,
            "nature_relation": 88.0,
            "object_localization": 85.7,
            "ocr": 97.8,
            "physical_property_reasoning": 72.2,
            "physical_relation": 73.3,
            "social_relation": 87.9,
            "spatial_relationship": 72.0,
            "structuralized_imagetext_understanding": 74.3,
            "Method": [
                "InternVL3-14B",
                "https://huggingface.co/OpenGVLab/InternVL3-14B"
            ],
            "Parameters": "15.1B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-14B",
            "key": 488
        },
        {
            "Overall": 86.6,
            "AR": 91.8,
            "CP": 81.9,
            "FP-C": 85.8,
            "FP-S": 92.3,
            "LR": 83.2,
            "RR": 85.3,
            "action_recognition": 91.5,
            "attribute_comparison": 89.3,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 87.1,
            "function_reasoning": 94.4,
            "future_prediction": 82.7,
            "identity_reasoning": 98.7,
            "image_emotion": 83.3,
            "image_quality": 62.1,
            "image_scene": 91.0,
            "image_style": 76.1,
            "image_topic": 98.9,
            "nature_relation": 89.1,
            "object_localization": 90.5,
            "ocr": 98.9,
            "physical_property_reasoning": 82.3,
            "physical_relation": 76.0,
            "social_relation": 89.0,
            "spatial_relationship": 73.3,
            "structuralized_imagetext_understanding": 83.5,
            "Method": [
                "InternVL3-38B",
                "https://huggingface.co/OpenGVLab/InternVL3-38B"
            ],
            "Parameters": "38.4B",
            "Language Model": "Qwen2.5-32B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-38B",
            "key": 489
        },
        {
            "Overall": 87.9,
            "AR": 91.8,
            "CP": 84.1,
            "FP-C": 89.9,
            "FP-S": 93.3,
            "LR": 79.9,
            "RR": 86.8,
            "action_recognition": 94.0,
            "attribute_comparison": 89.3,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 91.2,
            "function_reasoning": 95.6,
            "future_prediction": 81.3,
            "identity_reasoning": 98.7,
            "image_emotion": 82.2,
            "image_quality": 64.5,
            "image_scene": 92.4,
            "image_style": 84.8,
            "image_topic": 98.9,
            "nature_relation": 94.6,
            "object_localization": 90.5,
            "ocr": 98.9,
            "physical_property_reasoning": 81.0,
            "physical_relation": 80.0,
            "social_relation": 84.6,
            "spatial_relationship": 84.0,
            "structuralized_imagetext_understanding": 78.9,
            "Method": [
                "InternVL3-78B",
                "https://huggingface.co/OpenGVLab/InternVL3-78B"
            ],
            "Parameters": "78.4B",
            "Language Model": "Qwen2.5-72B",
            "Vision Model": "InternViT-6B-v2.5",
            "Org": "Shanghai AI Laboratory & Tsinghua University",
            "Time": "2025/04/14",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "InternVL3-78B",
            "key": 490
        },
        {
            "Overall": 86.2,
            "AR": 90.6,
            "CP": 83.9,
            "FP-C": 88.0,
            "FP-S": 87.9,
            "LR": 87.0,
            "RR": 81.8,
            "action_recognition": 95.7,
            "attribute_comparison": 84.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 81.6,
            "function_reasoning": 94.4,
            "future_prediction": 86.7,
            "identity_reasoning": 98.7,
            "image_emotion": 85.6,
            "image_quality": 67.7,
            "image_scene": 88.2,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 95.7,
            "object_localization": 81.9,
            "ocr": 100.0,
            "physical_property_reasoning": 78.5,
            "physical_relation": 57.3,
            "social_relation": 87.9,
            "spatial_relationship": 80.0,
            "structuralized_imagetext_understanding": 87.2,
            "Method": [
                "GPT-4.1-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-2025-04-14",
            "key": 491
        },
        {
            "Overall": 78.6,
            "AR": 81.6,
            "CP": 77.6,
            "FP-C": 79.0,
            "FP-S": 83.1,
            "LR": 65.2,
            "RR": 79.5,
            "action_recognition": 88.9,
            "attribute_comparison": 69.3,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 79.6,
            "function_reasoning": 91.1,
            "future_prediction": 80.0,
            "identity_reasoning": 96.1,
            "image_emotion": 84.4,
            "image_quality": 54.0,
            "image_scene": 85.4,
            "image_style": 72.8,
            "image_topic": 95.6,
            "nature_relation": 91.3,
            "object_localization": 79.0,
            "ocr": 91.1,
            "physical_property_reasoning": 57.0,
            "physical_relation": 58.7,
            "social_relation": 84.6,
            "spatial_relationship": 73.3,
            "structuralized_imagetext_understanding": 55.0,
            "Method": [
                "GPT-4.1-mini-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-mini-2025-04-14",
            "key": 492
        },
        {
            "Overall": 60.4,
            "AR": 77.6,
            "CP": 69.4,
            "FP-C": 50.2,
            "FP-S": 56.4,
            "LR": 47.8,
            "RR": 51.6,
            "action_recognition": 70.9,
            "attribute_comparison": 41.3,
            "attribute_recognition": 74.2,
            "celebrity_recognition": 41.5,
            "function_reasoning": 85.6,
            "future_prediction": 65.3,
            "identity_reasoning": 92.1,
            "image_emotion": 70.0,
            "image_quality": 31.5,
            "image_scene": 83.3,
            "image_style": 72.8,
            "image_topic": 95.6,
            "nature_relation": 47.8,
            "object_localization": 39.0,
            "ocr": 83.3,
            "physical_property_reasoning": 54.4,
            "physical_relation": 30.7,
            "social_relation": 72.5,
            "spatial_relationship": 26.7,
            "structuralized_imagetext_understanding": 35.8,
            "Method": [
                "GPT-4.1-nano-20250414",
                "https://openai.com/index/gpt-4-1/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/04/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "gpt-4.1-nano-2025-04-14",
            "key": 493
        },
        {
            "Overall": 64.1,
            "AR": 74.3,
            "CP": 68.7,
            "FP-C": 50.9,
            "FP-S": 67.1,
            "LR": 52.7,
            "RR": 61.2,
            "action_recognition": 70.1,
            "attribute_comparison": 46.7,
            "attribute_recognition": 74.2,
            "celebrity_recognition": 69.4,
            "function_reasoning": 85.6,
            "future_prediction": 60.0,
            "identity_reasoning": 96.1,
            "image_emotion": 72.2,
            "image_quality": 39.5,
            "image_scene": 75.7,
            "image_style": 68.5,
            "image_topic": 94.4,
            "nature_relation": 80.4,
            "object_localization": 38.1,
            "ocr": 90.0,
            "physical_property_reasoning": 40.5,
            "physical_relation": 29.3,
            "social_relation": 68.1,
            "spatial_relationship": 25.3,
            "structuralized_imagetext_understanding": 47.7,
            "Method": [
                "Kimi-VL-A3B-Thinking",
                "https://huggingface.co/moonshotai/Kimi-VL-A3B-Thinking"
            ],
            "Parameters": "16.4B",
            "Language Model": "Moonlight-16B-A3B",
            "Vision Model": "MoonViT",
            "Org": "moonshot.ai",
            "Time": "2025/04/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kimi-VL-A3B-Thinking",
            "key": 494
        },
        {
            "Overall": 77.5,
            "AR": 87.3,
            "CP": 79.3,
            "FP-C": 70.4,
            "FP-S": 81.7,
            "LR": 66.8,
            "RR": 72.1,
            "action_recognition": 88.0,
            "attribute_comparison": 72.0,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 72.8,
            "function_reasoning": 93.3,
            "future_prediction": 78.7,
            "identity_reasoning": 97.4,
            "image_emotion": 81.1,
            "image_quality": 56.5,
            "image_scene": 88.9,
            "image_style": 75.0,
            "image_topic": 97.8,
            "nature_relation": 77.2,
            "object_localization": 71.4,
            "ocr": 94.4,
            "physical_property_reasoning": 70.9,
            "physical_relation": 53.3,
            "social_relation": 82.4,
            "spatial_relationship": 41.3,
            "structuralized_imagetext_understanding": 58.7,
            "Method": [
                "SAIL-VL-1.5-2B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL-1d5-2B"
            ],
            "Parameters": "2.47B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "AIMv2 Huge",
            "Org": "ByteDance",
            "Time": "2025/04/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL-1.5-2B",
            "key": 495
        },
        {
            "Overall": 81.7,
            "AR": 88.6,
            "CP": 80.0,
            "FP-C": 79.0,
            "FP-S": 85.8,
            "LR": 73.9,
            "RR": 79.8,
            "action_recognition": 87.2,
            "attribute_comparison": 81.3,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 78.2,
            "function_reasoning": 93.3,
            "future_prediction": 81.3,
            "identity_reasoning": 94.7,
            "image_emotion": 82.2,
            "image_quality": 57.3,
            "image_scene": 90.3,
            "image_style": 75.0,
            "image_topic": 97.8,
            "nature_relation": 81.5,
            "object_localization": 78.1,
            "ocr": 97.8,
            "physical_property_reasoning": 77.2,
            "physical_relation": 68.0,
            "social_relation": 87.9,
            "spatial_relationship": 64.0,
            "structuralized_imagetext_understanding": 68.8,
            "Method": [
                "SAIL-VL-1.5-8B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL-1d5-8B"
            ],
            "Parameters": "7.95B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "InternViT-300B",
            "Org": "ByteDance",
            "Time": "2025/04/23",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL-1.5-8B",
            "key": 496
        },
        {
            "Overall": 83.7,
            "AR": 88.6,
            "CP": 83.3,
            "FP-C": 79.0,
            "FP-S": 88.4,
            "LR": 72.8,
            "RR": 84.9,
            "action_recognition": 91.5,
            "attribute_comparison": 76.0,
            "attribute_recognition": 98.9,
            "celebrity_recognition": 83.7,
            "function_reasoning": 96.7,
            "future_prediction": 81.3,
            "identity_reasoning": 97.4,
            "image_emotion": 86.7,
            "image_quality": 61.3,
            "image_scene": 93.8,
            "image_style": 78.3,
            "image_topic": 98.9,
            "nature_relation": 94.6,
            "object_localization": 79.0,
            "ocr": 96.7,
            "physical_property_reasoning": 70.9,
            "physical_relation": 73.3,
            "social_relation": 84.6,
            "spatial_relationship": 62.7,
            "structuralized_imagetext_understanding": 67.0,
            "Method": [
                "SAIL-VL-1.6-8B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL-1d6-8B"
            ],
            "Parameters": "8.33B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "AIMv2 Huge",
            "Org": "ByteDance",
            "Time": "2025/04/24",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL-1.6-8B",
            "key": 497
        },
        {
            "Overall": 87.6,
            "AR": 89.0,
            "CP": 83.7,
            "FP-C": 89.9,
            "FP-S": 94.2,
            "LR": 83.2,
            "RR": 84.5,
            "action_recognition": 93.2,
            "attribute_comparison": 89.3,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 91.8,
            "function_reasoning": 92.2,
            "future_prediction": 85.3,
            "identity_reasoning": 97.4,
            "image_emotion": 86.7,
            "image_quality": 68.5,
            "image_scene": 89.6,
            "image_style": 80.4,
            "image_topic": 95.6,
            "nature_relation": 92.4,
            "object_localization": 92.4,
            "ocr": 97.8,
            "physical_property_reasoning": 77.2,
            "physical_relation": 70.7,
            "social_relation": 87.9,
            "spatial_relationship": 85.3,
            "structuralized_imagetext_understanding": 81.7,
            "Method": [
                "SenseNova-V6-Pro",
                "https://platform.sensenova.cn/technology/fusion/Pro/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "SenseTime",
            "Time": "2025/05/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SenseNova-V6-Pro",
            "key": 498
        },
        {
            "Overall": 69.6,
            "AR": 82.0,
            "CP": 76.1,
            "FP-C": 63.7,
            "FP-S": 72.4,
            "LR": 46.2,
            "RR": 62.4,
            "action_recognition": 85.5,
            "attribute_comparison": 57.3,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 66.7,
            "function_reasoning": 87.8,
            "future_prediction": 62.7,
            "identity_reasoning": 96.1,
            "image_emotion": 75.6,
            "image_quality": 46.8,
            "image_scene": 91.0,
            "image_style": 71.7,
            "image_topic": 97.8,
            "nature_relation": 65.2,
            "object_localization": 51.4,
            "ocr": 88.9,
            "physical_property_reasoning": 62.0,
            "physical_relation": 38.7,
            "social_relation": 79.1,
            "spatial_relationship": 36.0,
            "structuralized_imagetext_understanding": 34.9,
            "Method": [
                "QTuneVL1-2B",
                "https://huggingface.co/hanchaow/QTuneVL1-2B"
            ],
            "Parameters": "2.21B",
            "Language Model": "InternLM2.5-1.8B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Reconova AI Lab",
            "Time": "2025/05/05",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "QTuneVL1-2B",
            "key": 499
        },
        {
            "Overall": 88.3,
            "AR": 91.0,
            "CP": 84.8,
            "FP-C": 90.3,
            "FP-S": 93.3,
            "LR": 83.7,
            "RR": 85.7,
            "action_recognition": 94.0,
            "attribute_comparison": 90.7,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 91.2,
            "function_reasoning": 93.3,
            "future_prediction": 86.7,
            "identity_reasoning": 98.7,
            "image_emotion": 85.6,
            "image_quality": 65.3,
            "image_scene": 92.4,
            "image_style": 84.8,
            "image_topic": 98.9,
            "nature_relation": 92.4,
            "object_localization": 90.5,
            "ocr": 98.9,
            "physical_property_reasoning": 81.0,
            "physical_relation": 77.3,
            "social_relation": 85.7,
            "spatial_relationship": 84.0,
            "structuralized_imagetext_understanding": 81.7,
            "Method": [
                "CongRong-v2.0",
                "http://115.120.28.181:20228/web/#/document-center"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "CloudWalk",
            "Time": "2025/05/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "CongRong-v2.0",
            "key": 500
        },
        {
            "Overall": 81.1,
            "AR": 80.8,
            "CP": 81.1,
            "FP-C": 75.3,
            "FP-S": 90.0,
            "LR": 75.5,
            "RR": 76.7,
            "action_recognition": 85.5,
            "attribute_comparison": 74.7,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 89.8,
            "function_reasoning": 91.1,
            "future_prediction": 78.7,
            "identity_reasoning": 97.4,
            "image_emotion": 77.8,
            "image_quality": 58.9,
            "image_scene": 91.0,
            "image_style": 82.6,
            "image_topic": 97.8,
            "nature_relation": 85.9,
            "object_localization": 86.7,
            "ocr": 98.9,
            "physical_property_reasoning": 53.2,
            "physical_relation": 53.3,
            "social_relation": 86.8,
            "spatial_relationship": 60.0,
            "structuralized_imagetext_understanding": 73.4,
            "Method": [
                "WeThink-Qwen2.5VL-7B",
                "https://huggingface.co/yangjie-cv/WeThink-Qwen2.5VL-7B"
            ],
            "Parameters": "8.29B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "QwenViT",
            "Org": "WeChat Vision",
            "Time": "2025/05/26",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "WeThink-Qwen2.5VL-7B",
            "key": 501
        },
        {
            "Overall": 80.7,
            "AR": 90.6,
            "CP": 79.6,
            "FP-C": 74.2,
            "FP-S": 87.5,
            "LR": 66.8,
            "RR": 79.1,
            "action_recognition": 88.0,
            "attribute_comparison": 74.7,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 85.7,
            "function_reasoning": 95.6,
            "future_prediction": 82.7,
            "identity_reasoning": 98.7,
            "image_emotion": 84.4,
            "image_quality": 56.5,
            "image_scene": 87.5,
            "image_style": 76.1,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 78.1,
            "ocr": 95.6,
            "physical_property_reasoning": 77.2,
            "physical_relation": 52.0,
            "social_relation": 86.8,
            "spatial_relationship": 52.0,
            "structuralized_imagetext_understanding": 56.0,
            "Method": [
                "valley2",
                "https://huggingface.co/bytedance-research/Valley-Eagle-7B"
            ],
            "Parameters": "8.88B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2025/05/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "valley2",
            "key": 502
        },
        {
            "Overall": 81.6,
            "AR": 90.2,
            "CP": 80.6,
            "FP-C": 74.5,
            "FP-S": 88.6,
            "LR": 70.1,
            "RR": 79.1,
            "action_recognition": 88.0,
            "attribute_comparison": 76.0,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 87.1,
            "function_reasoning": 96.7,
            "future_prediction": 82.7,
            "identity_reasoning": 98.7,
            "image_emotion": 84.4,
            "image_quality": 58.9,
            "image_scene": 86.8,
            "image_style": 78.3,
            "image_topic": 98.9,
            "nature_relation": 91.3,
            "object_localization": 81.0,
            "ocr": 96.7,
            "physical_property_reasoning": 74.7,
            "physical_relation": 53.3,
            "social_relation": 87.9,
            "spatial_relationship": 52.0,
            "structuralized_imagetext_understanding": 61.5,
            "Method": [
                "valley2_dpo",
                "https://huggingface.co/bytedance-research/Valley2-DPO"
            ],
            "Parameters": "8.88B",
            "Language Model": "Qwen2.5-7B",
            "Vision Model": "SigLIP-400M",
            "Org": "ByteDance",
            "Time": "2025/05/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "valley2_dpo",
            "key": 503
        },
        {
            "Overall": 74.4,
            "AR": 81.6,
            "CP": 76.7,
            "FP-C": 69.7,
            "FP-S": 78.0,
            "LR": 60.3,
            "RR": 72.1,
            "action_recognition": 83.8,
            "attribute_comparison": 74.7,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 72.8,
            "function_reasoning": 87.8,
            "future_prediction": 73.3,
            "identity_reasoning": 96.1,
            "image_emotion": 77.8,
            "image_quality": 50.8,
            "image_scene": 88.2,
            "image_style": 71.7,
            "image_topic": 97.8,
            "nature_relation": 76.1,
            "object_localization": 63.8,
            "ocr": 94.4,
            "physical_property_reasoning": 60.8,
            "physical_relation": 58.7,
            "social_relation": 79.1,
            "spatial_relationship": 42.7,
            "structuralized_imagetext_understanding": 51.4,
            "Method": [
                "Flash-VL-2B-Dynamic-ISS",
                "https://huggingface.co/FlashVL/FlashVL-2B-Dynamic-ISS"
            ],
            "Parameters": "2.53B",
            "Language Model": "Qwen-2.5-1.5B-Instruct",
            "Vision Model": "SigLIP2-400M-512",
            "Org": "Meituan",
            "Time": "2025/05/30",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Flash-VL-2B-Dynamic-ISS",
            "key": 504
        },
        {
            "Overall": 89.0,
            "AR": 84.5,
            "CP": 84.8,
            "FP-C": 92.1,
            "FP-S": 96.1,
            "LR": 90.2,
            "RR": 86.4,
            "action_recognition": 92.3,
            "attribute_comparison": 92.0,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 98.0,
            "function_reasoning": 95.6,
            "future_prediction": 85.3,
            "identity_reasoning": 98.7,
            "image_emotion": 81.1,
            "image_quality": 72.6,
            "image_scene": 88.2,
            "image_style": 85.9,
            "image_topic": 98.9,
            "nature_relation": 96.7,
            "object_localization": 90.5,
            "ocr": 100.0,
            "physical_property_reasoning": 58.2,
            "physical_relation": 73.3,
            "social_relation": 86.8,
            "spatial_relationship": 92.0,
            "structuralized_imagetext_understanding": 93.6,
            "Method": [
                "Seed1.5-VL",
                "https://github.com/ByteDance-Seed/Seed1.5-VL"
            ],
            "Parameters": "",
            "Language Model": "Seed1.5-LLM",
            "Vision Model": "Seed-ViT",
            "Org": "ByteDance",
            "Time": "2025/05/30",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "Seed1.5-VL",
            "key": 505
        },
        {
            "Overall": 75.9,
            "AR": 83.7,
            "CP": 79.1,
            "FP-C": 70.8,
            "FP-S": 79.8,
            "LR": 64.1,
            "RR": 69.4,
            "action_recognition": 82.9,
            "attribute_comparison": 68.0,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 71.4,
            "function_reasoning": 86.7,
            "future_prediction": 70.7,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 57.3,
            "image_scene": 88.2,
            "image_style": 73.9,
            "image_topic": 98.9,
            "nature_relation": 69.6,
            "object_localization": 70.5,
            "ocr": 98.9,
            "physical_property_reasoning": 67.1,
            "physical_relation": 58.7,
            "social_relation": 78.0,
            "spatial_relationship": 54.7,
            "structuralized_imagetext_understanding": 59.6,
            "Method": [
                "Long-VITA-16K",
                "https://huggingface.co/VITA-MLLM/Long-VITA-16K"
            ],
            "Parameters": "14B",
            "Language Model": "Qwen2.5-14B",
            "Vision Model": "InternViT-300M",
            "Org": "Tencent Youtu Lab & Nanjing University",
            "Time": "2025/06/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Long-VITA-16K",
            "key": 506
        },
        {
            "Overall": 63.8,
            "AR": 75.5,
            "CP": 70.0,
            "FP-C": 56.2,
            "FP-S": 68.4,
            "LR": 40.2,
            "RR": 56.6,
            "action_recognition": 80.3,
            "attribute_comparison": 50.7,
            "attribute_recognition": 80.9,
            "celebrity_recognition": 73.5,
            "function_reasoning": 84.4,
            "future_prediction": 53.3,
            "identity_reasoning": 93.4,
            "image_emotion": 77.8,
            "image_quality": 32.3,
            "image_scene": 82.6,
            "image_style": 67.4,
            "image_topic": 96.7,
            "nature_relation": 64.1,
            "object_localization": 31.4,
            "ocr": 91.1,
            "physical_property_reasoning": 48.1,
            "physical_relation": 25.3,
            "social_relation": 74.7,
            "spatial_relationship": 24.0,
            "structuralized_imagetext_understanding": 31.2,
            "Method": [
                "HawkVL-2B",
                "https://huggingface.co/xjtupanda/HawkVL-2B"
            ],
            "Parameters": "2.44B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "QwenViT",
            "Org": " Reconova AI Lab & USTC",
            "Time": "2025/06/16",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "HawkVL-2B",
            "key": 507
        },
        {
            "Overall": 64.4,
            "AR": 74.7,
            "CP": 70.9,
            "FP-C": 66.7,
            "FP-S": 57.3,
            "LR": 49.5,
            "RR": 61.2,
            "action_recognition": 82.9,
            "attribute_comparison": 72.0,
            "attribute_recognition": 68.5,
            "celebrity_recognition": 40.1,
            "function_reasoning": 72.2,
            "future_prediction": 56.0,
            "identity_reasoning": 90.8,
            "image_emotion": 77.8,
            "image_quality": 38.7,
            "image_scene": 86.8,
            "image_style": 59.8,
            "image_topic": 94.4,
            "nature_relation": 59.8,
            "object_localization": 44.8,
            "ocr": 88.9,
            "physical_property_reasoning": 62.0,
            "physical_relation": 42.7,
            "social_relation": 78.0,
            "spatial_relationship": 36.0,
            "structuralized_imagetext_understanding": 45.0,
            "Method": [
                "granite-vision-3.1-2b-preview",
                "https://huggingface.co/ibm-granite/granite-vision-3.1-2b-preview"
            ],
            "Parameters": "2.98B",
            "Language Model": "granite-3.1-2b-instruct",
            "Vision Model": "SigLip",
            "Org": "IBM",
            "Time": "2025/06/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "granite_vision_3.1_2b_preview",
            "key": 508
        },
        {
            "Overall": 65.7,
            "AR": 75.5,
            "CP": 70.9,
            "FP-C": 65.9,
            "FP-S": 61.7,
            "LR": 50.5,
            "RR": 62.8,
            "action_recognition": 82.9,
            "attribute_comparison": 73.3,
            "attribute_recognition": 76.4,
            "celebrity_recognition": 44.2,
            "function_reasoning": 78.9,
            "future_prediction": 57.3,
            "identity_reasoning": 93.4,
            "image_emotion": 75.6,
            "image_quality": 44.4,
            "image_scene": 81.2,
            "image_style": 63.0,
            "image_topic": 94.4,
            "nature_relation": 62.0,
            "object_localization": 49.5,
            "ocr": 90.0,
            "physical_property_reasoning": 54.4,
            "physical_relation": 42.7,
            "social_relation": 80.2,
            "spatial_relationship": 32.0,
            "structuralized_imagetext_understanding": 45.9,
            "Method": [
                "granite-vision-3.2-2b",
                "https://huggingface.co/ibm-granite/granite-vision-3.2-2b"
            ],
            "Parameters": "2.98B",
            "Language Model": "granite-3.1-2b-instruct",
            "Vision Model": "SigLip",
            "Org": "IBM",
            "Time": "2025/06/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "granite_vision_3.2_2b",
            "key": 509
        },
        {
            "Overall": 65.0,
            "AR": 75.5,
            "CP": 68.5,
            "FP-C": 62.5,
            "FP-S": 66.8,
            "LR": 45.1,
            "RR": 61.6,
            "action_recognition": 82.1,
            "attribute_comparison": 70.7,
            "attribute_recognition": 78.7,
            "celebrity_recognition": 49.0,
            "function_reasoning": 80.0,
            "future_prediction": 48.0,
            "identity_reasoning": 93.4,
            "image_emotion": 71.1,
            "image_quality": 38.7,
            "image_scene": 81.2,
            "image_style": 56.5,
            "image_topic": 98.9,
            "nature_relation": 62.0,
            "object_localization": 60.0,
            "ocr": 92.2,
            "physical_property_reasoning": 53.2,
            "physical_relation": 38.7,
            "social_relation": 80.2,
            "spatial_relationship": 24.0,
            "structuralized_imagetext_understanding": 43.1,
            "Method": [
                "granite-vision-3.3-2b",
                "https://huggingface.co/ibm-granite/granite-vision-3.3-2b"
            ],
            "Parameters": "2.98B",
            "Language Model": "granite-3.1-2b-instruct",
            "Vision Model": "SigLIP2-400M",
            "Org": "IBM",
            "Time": "2025/06/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "granite_vision_3.3_2b",
            "key": 510
        },
        {
            "Overall": 79.8,
            "AR": 77.1,
            "CP": 79.1,
            "FP-C": 75.7,
            "FP-S": 87.0,
            "LR": 78.8,
            "RR": 76.7,
            "action_recognition": 85.5,
            "attribute_comparison": 78.7,
            "attribute_recognition": 85.4,
            "celebrity_recognition": 88.4,
            "function_reasoning": 88.9,
            "future_prediction": 72.0,
            "identity_reasoning": 94.7,
            "image_emotion": 72.2,
            "image_quality": 64.5,
            "image_scene": 86.8,
            "image_style": 73.9,
            "image_topic": 98.9,
            "nature_relation": 87.0,
            "object_localization": 78.1,
            "ocr": 96.7,
            "physical_property_reasoning": 46.8,
            "physical_relation": 60.0,
            "social_relation": 80.2,
            "spatial_relationship": 57.3,
            "structuralized_imagetext_understanding": 83.5,
            "Method": [
                "MiMo-VL-7B",
                "https://huggingface.co/XiaomiMiMo/MiMo-VL-7B-RL"
            ],
            "Parameters": "8.31B",
            "Language Model": "Mimo-7B",
            "Vision Model": "Qwen2.5-ViT",
            "Org": "Xiaomi",
            "Time": "2025/07/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MiMo-VL-7B-RL",
            "key": 511
        },
        {
            "Overall": 83.2,
            "AR": 85.3,
            "CP": 81.1,
            "FP-C": 79.0,
            "FP-S": 90.3,
            "LR": 82.1,
            "RR": 79.1,
            "action_recognition": 80.3,
            "attribute_comparison": 82.7,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 90.5,
            "function_reasoning": 94.4,
            "future_prediction": 77.3,
            "identity_reasoning": 98.7,
            "image_emotion": 80.0,
            "image_quality": 62.1,
            "image_scene": 88.9,
            "image_style": 78.3,
            "image_topic": 98.9,
            "nature_relation": 88.0,
            "object_localization": 84.8,
            "ocr": 98.9,
            "physical_property_reasoning": 62.0,
            "physical_relation": 58.7,
            "social_relation": 86.8,
            "spatial_relationship": 73.3,
            "structuralized_imagetext_understanding": 85.3,
            "Method": [
                "Qwen2.5-VL-32B",
                "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct"
            ],
            "Parameters": "33.5B",
            "Language Model": "Qwen2.5-32B",
            "Vision Model": "QwenViT",
            "Org": "Alibaba",
            "Time": "2025/07/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Qwen2.5-VL-32B-Instruct",
            "key": 512
        },
        {
            "Overall": 79.8,
            "AR": 83.3,
            "CP": 78.7,
            "FP-C": 73.8,
            "FP-S": 86.1,
            "LR": 76.6,
            "RR": 77.1,
            "action_recognition": 86.3,
            "attribute_comparison": 73.3,
            "attribute_recognition": 87.6,
            "celebrity_recognition": 86.4,
            "function_reasoning": 91.1,
            "future_prediction": 77.3,
            "identity_reasoning": 98.7,
            "image_emotion": 77.8,
            "image_quality": 58.9,
            "image_scene": 86.8,
            "image_style": 77.2,
            "image_topic": 95.6,
            "nature_relation": 88.0,
            "object_localization": 76.2,
            "ocr": 95.6,
            "physical_property_reasoning": 59.5,
            "physical_relation": 58.7,
            "social_relation": 81.3,
            "spatial_relationship": 54.7,
            "structuralized_imagetext_understanding": 76.1,
            "Method": [
                "Kimi-VL-A3B-Thinking-2506",
                "https://huggingface.co/moonshotai/Kimi-VL-A3B-Thinking-2506"
            ],
            "Parameters": "16.4B",
            "Language Model": "Moonlight-16B-A3B",
            "Vision Model": "MoonViT",
            "Org": "moonshot.ai",
            "Time": "2025/07/02",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Kimi-VL-A3B-Thinking-2506",
            "key": 513
        },
        {
            "Overall": 75.5,
            "AR": 75.5,
            "CP": 76.9,
            "FP-C": 70.8,
            "FP-S": 80.5,
            "LR": 71.2,
            "RR": 72.5,
            "action_recognition": 82.1,
            "attribute_comparison": 76.0,
            "attribute_recognition": 84.3,
            "celebrity_recognition": 75.5,
            "function_reasoning": 90.0,
            "future_prediction": 66.7,
            "identity_reasoning": 92.1,
            "image_emotion": 71.1,
            "image_quality": 62.1,
            "image_scene": 85.4,
            "image_style": 69.6,
            "image_topic": 96.7,
            "nature_relation": 83.7,
            "object_localization": 72.4,
            "ocr": 94.4,
            "physical_property_reasoning": 43.0,
            "physical_relation": 50.7,
            "social_relation": 79.1,
            "spatial_relationship": 48.0,
            "structuralized_imagetext_understanding": 74.3,
            "Method": [
                "BlueLM-2.5-3B",
                "https://arxiv.org/pdf/2507.05934"
            ],
            "Parameters": "2.9B",
            "Language Model": "BlueLM-base-3B",
            "Vision Model": "Siglip2-So400M",
            "Org": "Vivo",
            "Time": "2025/07/16",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "BlueLM-2.5-3B",
            "key": 514
        },
        {
            "Overall": 77.6,
            "AR": 82.0,
            "CP": 80.9,
            "FP-C": 72.7,
            "FP-S": 82.8,
            "LR": 62.0,
            "RR": 74.0,
            "action_recognition": 90.6,
            "attribute_comparison": 76.0,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 76.2,
            "function_reasoning": 90.0,
            "future_prediction": 76.0,
            "identity_reasoning": 97.4,
            "image_emotion": 77.8,
            "image_quality": 66.1,
            "image_scene": 89.6,
            "image_style": 75.0,
            "image_topic": 96.7,
            "nature_relation": 70.7,
            "object_localization": 71.4,
            "ocr": 96.7,
            "physical_property_reasoning": 58.2,
            "physical_relation": 65.3,
            "social_relation": 84.6,
            "spatial_relationship": 41.3,
            "structuralized_imagetext_understanding": 52.3,
            "Method": [
                "Ovis-U1-3B",
                "https://huggingface.co/AIDC-AI/Ovis-U1-3B"
            ],
            "Parameters": "3.64B",
            "Language Model": "Qwen3-1.7B",
            "Vision Model": "aimv2-large-path14-448",
            "Org": "Ovis Team, Alibaba Group",
            "Time": "2025/07/20",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "Ovis-U1-3B",
            "key": 515
        },
        {
            "Overall": 70.8,
            "AR": 80.8,
            "CP": 74.8,
            "FP-C": 67.4,
            "FP-S": 72.4,
            "LR": 51.6,
            "RR": 67.1,
            "action_recognition": 88.0,
            "attribute_comparison": 76.0,
            "attribute_recognition": 80.9,
            "celebrity_recognition": 66.7,
            "function_reasoning": 85.6,
            "future_prediction": 68.0,
            "identity_reasoning": 98.7,
            "image_emotion": 75.6,
            "image_quality": 48.4,
            "image_scene": 84.7,
            "image_style": 71.7,
            "image_topic": 97.8,
            "nature_relation": 70.7,
            "object_localization": 60.0,
            "ocr": 87.8,
            "physical_property_reasoning": 58.2,
            "physical_relation": 42.7,
            "social_relation": 83.5,
            "spatial_relationship": 26.7,
            "structuralized_imagetext_understanding": 40.4,
            "Method": [
                "VARCO-VISION-2.0-1.7B",
                "https://huggingface.co/NCSOFT/VARCO-VISION-2.0-1.7B"
            ],
            "Parameters": "2.12B",
            "Language Model": "Qwen3-1.7B",
            "Vision Model": "SigLIP-400M",
            "Org": "NCSOFT",
            "Time": "2025/08/04",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "varco-vision-2-1.7b",
            "key": 516
        },
        {
            "Overall": 83.0,
            "AR": 89.0,
            "CP": 80.4,
            "FP-C": 81.6,
            "FP-S": 86.5,
            "LR": 76.1,
            "RR": 83.3,
            "action_recognition": 87.2,
            "attribute_comparison": 88.0,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 76.2,
            "function_reasoning": 94.4,
            "future_prediction": 82.7,
            "identity_reasoning": 98.7,
            "image_emotion": 80.0,
            "image_quality": 58.1,
            "image_scene": 90.3,
            "image_style": 77.2,
            "image_topic": 98.9,
            "nature_relation": 93.5,
            "object_localization": 82.9,
            "ocr": 98.9,
            "physical_property_reasoning": 73.4,
            "physical_relation": 68.0,
            "social_relation": 85.7,
            "spatial_relationship": 66.7,
            "structuralized_imagetext_understanding": 71.6,
            "Method": [
                "VARCO-VISION-2.0-14B",
                "https://huggingface.co/NCSOFT/VARCO-VISION-2.0-14B"
            ],
            "Parameters": "15.2B",
            "Language Model": "Qwen3-14B",
            "Vision Model": "SigLIP-400M",
            "Org": "NCSOFT",
            "Time": "2025/08/04",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "varco-vision-2-14b",
            "key": 517
        },
        {
            "Overall": 86.6,
            "AR": 91.4,
            "CP": 82.2,
            "FP-C": 88.4,
            "FP-S": 92.1,
            "LR": 82.1,
            "RR": 83.3,
            "action_recognition": 87.2,
            "attribute_comparison": 90.7,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 91.8,
            "function_reasoning": 96.7,
            "future_prediction": 86.7,
            "identity_reasoning": 100.0,
            "image_emotion": 85.6,
            "image_quality": 62.1,
            "image_scene": 86.8,
            "image_style": 82.6,
            "image_topic": 98.9,
            "nature_relation": 90.2,
            "object_localization": 85.7,
            "ocr": 96.7,
            "physical_property_reasoning": 77.2,
            "physical_relation": 68.0,
            "social_relation": 89.0,
            "spatial_relationship": 88.0,
            "structuralized_imagetext_understanding": 78.9,
            "Method": [
                "JT-VL-Chat-V3.0",
                "https://github.com/jiutiancv/JT-VL-Chat/tree/main"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "China Mobile",
            "Time": "2025/08/04",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "JTVL-V3",
            "key": 386
        },
        {
            "Overall": 76.9,
            "AR": 83.3,
            "CP": 79.4,
            "FP-C": 70.8,
            "FP-S": 82.1,
            "LR": 61.4,
            "RR": 74.0,
            "action_recognition": 88.9,
            "attribute_comparison": 73.3,
            "attribute_recognition": 89.9,
            "celebrity_recognition": 74.8,
            "function_reasoning": 91.1,
            "future_prediction": 73.3,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 58.9,
            "image_scene": 87.5,
            "image_style": 75.0,
            "image_topic": 98.9,
            "nature_relation": 80.4,
            "object_localization": 75.2,
            "ocr": 94.4,
            "physical_property_reasoning": 60.8,
            "physical_relation": 45.3,
            "social_relation": 91.2,
            "spatial_relationship": 40.0,
            "structuralized_imagetext_understanding": 53.2,
            "Method": [
                "QTuneVL1.5-2B",
                "https://huggingface.co/hanchaow/QTuneVL1_5-2B"
            ],
            "Parameters": "2.09B",
            "Language Model": "Qwen2.5-1.5B",
            "Vision Model": "InternViT-300M-v2.5",
            "Org": "Reconova AI Lab & BDAA-Lab ",
            "Time": "2025/08/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "QTuneVL1_5-2B",
            "key": 518
        },
        {
            "Overall": 77.1,
            "AR": 83.7,
            "CP": 78.3,
            "FP-C": 65.2,
            "FP-S": 85.8,
            "LR": 66.3,
            "RR": 73.6,
            "action_recognition": 84.6,
            "attribute_comparison": 66.7,
            "attribute_recognition": 86.5,
            "celebrity_recognition": 92.5,
            "function_reasoning": 95.6,
            "future_prediction": 70.7,
            "identity_reasoning": 98.7,
            "image_emotion": 80.0,
            "image_quality": 52.4,
            "image_scene": 92.4,
            "image_style": 70.7,
            "image_topic": 97.8,
            "nature_relation": 77.2,
            "object_localization": 67.6,
            "ocr": 95.6,
            "physical_property_reasoning": 55.7,
            "physical_relation": 49.3,
            "social_relation": 90.1,
            "spatial_relationship": 33.3,
            "structuralized_imagetext_understanding": 63.3,
            "Method": [
                "QTuneVL1.5-3B",
                "https://huggingface.co/hanchaow/QTuneVL1_5-3B"
            ],
            "Parameters": "3.75B",
            "Language Model": "Qwen2.5-3B",
            "Vision Model": "QwenViT",
            "Org": "Reconova AI Lab & BDAA-Lab ",
            "Time": "2025/08/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "QTuneVL1_5-3B",
            "key": 519
        },
        {
            "Overall": 81.8,
            "AR": 82.9,
            "CP": 80.0,
            "FP-C": 82.4,
            "FP-S": 86.1,
            "LR": 80.4,
            "RR": 77.5,
            "action_recognition": 86.3,
            "attribute_comparison": 90.7,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 78.2,
            "function_reasoning": 90.0,
            "future_prediction": 69.3,
            "identity_reasoning": 97.4,
            "image_emotion": 76.7,
            "image_quality": 64.5,
            "image_scene": 85.4,
            "image_style": 78.3,
            "image_topic": 97.8,
            "nature_relation": 90.2,
            "object_localization": 81.0,
            "ocr": 100.0,
            "physical_property_reasoning": 60.8,
            "physical_relation": 60.0,
            "social_relation": 79.1,
            "spatial_relationship": 68.0,
            "structuralized_imagetext_understanding": 88.1,
            "Method": [
                "R-4B",
                "https://huggingface.co/YannQi/R-4B"
            ],
            "Parameters": "4.82B",
            "Language Model": "Qwen3-4B",
            "Vision Model": "SigLip-400M",
            "Org": "",
            "Time": "2025/08/11",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "X-VL-4B",
            "key": 520
        },
        {
            "Overall": 86.4,
            "AR": 91.8,
            "CP": 85.6,
            "FP-C": 94.0,
            "FP-S": 78.2,
            "LR": 91.3,
            "RR": 85.7,
            "action_recognition": 95.7,
            "attribute_comparison": 92.0,
            "attribute_recognition": 94.4,
            "celebrity_recognition": 51.0,
            "function_reasoning": 96.7,
            "future_prediction": 88.0,
            "identity_reasoning": 98.7,
            "image_emotion": 85.6,
            "image_quality": 70.2,
            "image_scene": 91.7,
            "image_style": 84.8,
            "image_topic": 97.8,
            "nature_relation": 95.7,
            "object_localization": 83.8,
            "ocr": 100.0,
            "physical_property_reasoning": 79.7,
            "physical_relation": 72.0,
            "social_relation": 86.8,
            "spatial_relationship": 93.3,
            "structuralized_imagetext_understanding": 93.6,
            "Method": [
                "GPT-5-20250807",
                "https://openai.com/index/introducing-gpt-5/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/08/14",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "gpt-5-2025-08-07",
            "key": 521
        },
        {
            "Overall": 79.6,
            "AR": 85.3,
            "CP": 80.6,
            "FP-C": 83.5,
            "FP-S": 73.1,
            "LR": 84.2,
            "RR": 75.6,
            "action_recognition": 81.2,
            "attribute_comparison": 89.3,
            "attribute_recognition": 88.8,
            "celebrity_recognition": 49.0,
            "function_reasoning": 91.1,
            "future_prediction": 82.7,
            "identity_reasoning": 96.1,
            "image_emotion": 78.9,
            "image_quality": 62.1,
            "image_scene": 87.5,
            "image_style": 78.3,
            "image_topic": 98.9,
            "nature_relation": 84.8,
            "object_localization": 75.2,
            "ocr": 94.4,
            "physical_property_reasoning": 68.4,
            "physical_relation": 58.7,
            "social_relation": 80.2,
            "spatial_relationship": 81.3,
            "structuralized_imagetext_understanding": 85.3,
            "Method": [
                "GPT-5-nano-20250807",
                "https://openai.com/index/introducing-gpt-5/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/08/14",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "gpt-5-nano-2025-08-07",
            "key": 522
        },
        {
            "Overall": 86.1,
            "AR": 90.2,
            "CP": 87.2,
            "FP-C": 92.1,
            "FP-S": 78.7,
            "LR": 89.7,
            "RR": 83.7,
            "action_recognition": 91.5,
            "attribute_comparison": 90.7,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 51.7,
            "function_reasoning": 96.7,
            "future_prediction": 84.0,
            "identity_reasoning": 97.4,
            "image_emotion": 86.7,
            "image_quality": 74.2,
            "image_scene": 92.4,
            "image_style": 85.9,
            "image_topic": 98.9,
            "nature_relation": 94.6,
            "object_localization": 84.8,
            "ocr": 98.9,
            "physical_property_reasoning": 75.9,
            "physical_relation": 70.7,
            "social_relation": 83.5,
            "spatial_relationship": 94.7,
            "structuralized_imagetext_understanding": 93.6,
            "Method": [
                "GPT-5-mini-20250807",
                "https://openai.com/index/introducing-gpt-5/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "OpenAI",
            "Time": "2025/08/14",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "gpt-5-mini-2025-08-07",
            "key": 523
        },
        {
            "Overall": 87.0,
            "AR": 90.2,
            "CP": 81.9,
            "FP-C": 88.4,
            "FP-S": 93.3,
            "LR": 81.5,
            "RR": 86.4,
            "action_recognition": 88.9,
            "attribute_comparison": 92.0,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 90.5,
            "function_reasoning": 95.6,
            "future_prediction": 77.3,
            "identity_reasoning": 98.7,
            "image_emotion": 86.7,
            "image_quality": 59.7,
            "image_scene": 86.8,
            "image_style": 83.7,
            "image_topic": 97.8,
            "nature_relation": 97.8,
            "object_localization": 89.5,
            "ocr": 98.9,
            "physical_property_reasoning": 75.9,
            "physical_relation": 72.0,
            "social_relation": 86.8,
            "spatial_relationship": 84.0,
            "structuralized_imagetext_understanding": 84.4,
            "Method": [
                "SenseNova-V6-5-Pro",
                "https://platform.sensenova.cn/technology/fusion/Pro/"
            ],
            "Parameters": "",
            "Language Model": "",
            "Vision Model": "",
            "Org": "SenseTime",
            "Time": "2025/09/03",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "SenseNova-V6-5-Pro",
            "key": 524
        },
        {
            "Overall": 86.4,
            "AR": 84.9,
            "CP": 86.5,
            "FP-C": 85.8,
            "FP-S": 91.9,
            "LR": 82.1,
            "RR": 82.2,
            "action_recognition": 88.9,
            "attribute_comparison": 82.7,
            "attribute_recognition": 92.1,
            "celebrity_recognition": 89.1,
            "function_reasoning": 92.2,
            "future_prediction": 78.7,
            "identity_reasoning": 98.7,
            "image_emotion": 75.6,
            "image_quality": 79.8,
            "image_scene": 92.4,
            "image_style": 85.9,
            "image_topic": 97.8,
            "nature_relation": 91.3,
            "object_localization": 89.5,
            "ocr": 98.9,
            "physical_property_reasoning": 63.3,
            "physical_relation": 66.7,
            "social_relation": 85.7,
            "spatial_relationship": 84.0,
            "structuralized_imagetext_understanding": 84.4,
            "Method": [
                "BlueLM-2.5-3B-0909",
                "https://developers.vivo.com/product/ai/bluelm"
            ],
            "Parameters": "3B",
            "Language Model": "BlueLM-base-3B",
            "Vision Model": "Siglip2-So400M",
            "Org": "Vivo",
            "Time": "2025/09/17",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "BlueLM-2.6-3B",
            "key": 525
        },
        {
            "Overall": 79.2,
            "AR": 84.5,
            "CP": 79.4,
            "FP-C": 74.9,
            "FP-S": 85.2,
            "LR": 64.7,
            "RR": 78.3,
            "action_recognition": 92.3,
            "attribute_comparison": 73.3,
            "attribute_recognition": 98.9,
            "celebrity_recognition": 75.5,
            "function_reasoning": 93.3,
            "future_prediction": 80.0,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 58.9,
            "image_scene": 91.0,
            "image_style": 71.7,
            "image_topic": 96.7,
            "nature_relation": 83.7,
            "object_localization": 78.1,
            "ocr": 95.6,
            "physical_property_reasoning": 62.0,
            "physical_relation": 60.0,
            "social_relation": 87.9,
            "spatial_relationship": 49.3,
            "structuralized_imagetext_understanding": 54.1,
            "Method": [
                "SAIL-VL2-2B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL2-2B"
            ],
            "Parameters": "2.73B",
            "Language Model": "Qwen3-1.7B",
            "Vision Model": "SAILViT-Huge",
            "Org": "Douyin",
            "Time": "2025/09/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL2-2B",
            "key": 526
        },
        {
            "Overall": 84.7,
            "AR": 90.2,
            "CP": 81.9,
            "FP-C": 83.5,
            "FP-S": 88.2,
            "LR": 79.9,
            "RR": 84.1,
            "action_recognition": 92.3,
            "attribute_comparison": 88.0,
            "attribute_recognition": 97.8,
            "celebrity_recognition": 78.2,
            "function_reasoning": 92.2,
            "future_prediction": 81.3,
            "identity_reasoning": 97.4,
            "image_emotion": 83.3,
            "image_quality": 64.5,
            "image_scene": 89.6,
            "image_style": 76.1,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 86.7,
            "ocr": 96.7,
            "physical_property_reasoning": 81.0,
            "physical_relation": 73.3,
            "social_relation": 83.5,
            "spatial_relationship": 65.3,
            "structuralized_imagetext_understanding": 78.9,
            "Method": [
                "SAIL-VL2-8B",
                "https://huggingface.co/BytedanceDouyinContent/SAIL-VL2-8B"
            ],
            "Parameters": "8.91B",
            "Language Model": "Qwen3-8B",
            "Vision Model": "SAILViT-Huge",
            "Org": "Douyin",
            "Time": "2025/09/28",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "SAIL-VL2-8B",
            "key": 527
        },
        {
            "Overall": 83.0,
            "AR": 86.1,
            "CP": 84.1,
            "FP-C": 79.8,
            "FP-S": 85.8,
            "LR": 74.5,
            "RR": 82.2,
            "action_recognition": 90.6,
            "attribute_comparison": 85.3,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 78.9,
            "function_reasoning": 91.1,
            "future_prediction": 85.3,
            "identity_reasoning": 98.7,
            "image_emotion": 86.7,
            "image_quality": 67.7,
            "image_scene": 85.4,
            "image_style": 88.0,
            "image_topic": 97.8,
            "nature_relation": 89.1,
            "object_localization": 78.1,
            "ocr": 96.7,
            "physical_property_reasoning": 68.4,
            "physical_relation": 69.3,
            "social_relation": 85.7,
            "spatial_relationship": 57.3,
            "structuralized_imagetext_understanding": 67.0,
            "Method": [
                "JT-VL-Chat-Mini",
                "https://github.com/jiutiancv/JT-VL-Chat/tree/main"
            ],
            "Parameters": "3.8B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "China Mobile",
            "Time": "2025/10/26",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "JTVL-Mini",
            "key": 528
        },
        {
            "Overall": 78.8,
            "AR": 84.9,
            "CP": 78.9,
            "FP-C": 75.3,
            "FP-S": 84.5,
            "LR": 61.4,
            "RR": 79.1,
            "action_recognition": 88.0,
            "attribute_comparison": 82.7,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 80.3,
            "function_reasoning": 90.0,
            "future_prediction": 70.7,
            "identity_reasoning": 97.4,
            "image_emotion": 81.1,
            "image_quality": 57.3,
            "image_scene": 85.4,
            "image_style": 78.3,
            "image_topic": 96.7,
            "nature_relation": 87.0,
            "object_localization": 73.3,
            "ocr": 95.6,
            "physical_property_reasoning": 67.1,
            "physical_relation": 56.0,
            "social_relation": 90.1,
            "spatial_relationship": 48.0,
            "structuralized_imagetext_understanding": 55.0,
            "Method": [
                "JT-VL-Chat-2B",
                "https://github.com/jiutiancv/JT-VL-Chat/tree/main"
            ],
            "Parameters": "2B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "China Mobile",
            "Time": "2025/11/10",
            "Verified": "Yes",
            "OpenSource": "No",
            "dir_name": "JTVL-2B",
            "key": 529
        },
        {
            "Overall": 87.2,
            "AR": 90.6,
            "CP": 83.5,
            "FP-C": 85.4,
            "FP-S": 93.0,
            "LR": 83.7,
            "RR": 86.4,
            "action_recognition": 91.5,
            "attribute_comparison": 86.7,
            "attribute_recognition": 96.6,
            "celebrity_recognition": 87.1,
            "function_reasoning": 94.4,
            "future_prediction": 84.0,
            "identity_reasoning": 98.7,
            "image_emotion": 83.3,
            "image_quality": 63.7,
            "image_scene": 92.4,
            "image_style": 81.5,
            "image_topic": 98.9,
            "nature_relation": 90.2,
            "object_localization": 93.3,
            "ocr": 98.9,
            "physical_property_reasoning": 78.5,
            "physical_relation": 76.0,
            "social_relation": 91.2,
            "spatial_relationship": 74.7,
            "structuralized_imagetext_understanding": 83.5,
            "Method": [
                "RBDashMM3-DPO-38B",
                "https://huggingface.co/RBDash-Team/RBDash-v2.0"
            ],
            "Parameters": "38B",
            "Language Model": "",
            "Vision Model": "",
            "Org": "RBDash Team",
            "Time": "2025/11/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "rbdashmm3_DPO_38B_api",
            "key": 530
        },
        {
            "Overall": 82.6,
            "AR": 86.1,
            "CP": 79.6,
            "FP-C": 79.4,
            "FP-S": 89.1,
            "LR": 78.3,
            "RR": 81.4,
            "action_recognition": 89.7,
            "attribute_comparison": 82.7,
            "attribute_recognition": 93.3,
            "celebrity_recognition": 86.4,
            "function_reasoning": 93.3,
            "future_prediction": 82.7,
            "identity_reasoning": 97.4,
            "image_emotion": 81.1,
            "image_quality": 57.3,
            "image_scene": 86.8,
            "image_style": 79.3,
            "image_topic": 97.8,
            "nature_relation": 93.5,
            "object_localization": 81.9,
            "ocr": 97.8,
            "physical_property_reasoning": 67.1,
            "physical_relation": 60.0,
            "social_relation": 86.8,
            "spatial_relationship": 60.0,
            "structuralized_imagetext_understanding": 75.2,
            "Method": [
                "Valley3",
                "https://huggingface.co/bytedance-research/Valley3"
            ],
            "Parameters": "9B",
            "Language Model": "Qwen3-8B",
            "Vision Model": "Qwen2-VL-ViT",
            "Org": "ByteDance",
            "Time": "2025/11/10",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "valley3",
            "key": 531
        },
        {
            "Overall": 79.6,
            "AR": 84.9,
            "CP": 80.9,
            "FP-C": 74.9,
            "FP-S": 84.2,
            "LR": 63.0,
            "RR": 81.0,
            "action_recognition": 85.5,
            "attribute_comparison": 84.0,
            "attribute_recognition": 91.0,
            "celebrity_recognition": 81.0,
            "function_reasoning": 90.0,
            "future_prediction": 76.0,
            "identity_reasoning": 97.4,
            "image_emotion": 85.6,
            "image_quality": 59.7,
            "image_scene": 90.3,
            "image_style": 73.9,
            "image_topic": 97.8,
            "nature_relation": 85.9,
            "object_localization": 74.3,
            "ocr": 94.4,
            "physical_property_reasoning": 67.1,
            "physical_relation": 66.7,
            "social_relation": 87.9,
            "spatial_relationship": 49.3,
            "structuralized_imagetext_understanding": 54.1,
            "Method": [
                "MiniCPM-V-4",
                "https://huggingface.co/openbmb/MiniCPM-V-4"
            ],
            "Parameters": "4.1B",
            "Language Model": "MiniCPM4-3B",
            "Vision Model": "SigLIP2-400M",
            "Org": "OpenBMB",
            "Time": "2025/11/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MiniCPM-V-4",
            "key": 532
        },
        {
            "Overall": 84.1,
            "AR": 86.5,
            "CP": 80.6,
            "FP-C": 80.9,
            "FP-S": 91.4,
            "LR": 82.1,
            "RR": 81.8,
            "action_recognition": 85.5,
            "attribute_comparison": 81.3,
            "attribute_recognition": 95.5,
            "celebrity_recognition": 88.4,
            "function_reasoning": 92.2,
            "future_prediction": 81.3,
            "identity_reasoning": 97.4,
            "image_emotion": 80.0,
            "image_quality": 60.5,
            "image_scene": 86.8,
            "image_style": 80.4,
            "image_topic": 98.9,
            "nature_relation": 93.5,
            "object_localization": 86.7,
            "ocr": 97.8,
            "physical_property_reasoning": 69.6,
            "physical_relation": 64.0,
            "social_relation": 84.6,
            "spatial_relationship": 73.3,
            "structuralized_imagetext_understanding": 82.6,
            "Method": [
                "MiniCPM-V-4_5",
                "https://huggingface.co/openbmb/MiniCPM-V-4_5"
            ],
            "Parameters": "8B",
            "Language Model": "Qwen3-8B",
            "Vision Model": "SigLIP2-400M",
            "Org": "OpenBMB",
            "Time": "2025/11/13",
            "Verified": "Yes",
            "OpenSource": "Yes",
            "dir_name": "MiniCPM-V-4_5",
            "key": 533
        }
    ]
}