{"Score": 0.03, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 11.78, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 44.95, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 44.14, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 10.0, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 13.78, "Name": "MageBench", "BaseModel": "DeepSeek-VL-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 8.07, "Name": "MageBench", "BaseModel": "DeepSeek-VL-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 12.95, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 15.26, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 45.57, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 42.28, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 12.52, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 10.03, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 42.52, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 42.36, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 2.1, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 11.95, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 9.92, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.28, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 42.59, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 18.13, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 6.57, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 15.17, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 43.19, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 43.47, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 3.91, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 7.14, "Name": "MageBench", "BaseModel": "Yi-VL-34B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 12.08, "Name": "MageBench", "BaseModel": "Yi-VL-34B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 7.37, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 13.03, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.21, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 43.22, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 15.75, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 4.71, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 14.46, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 43.46, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 44.07, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 14.46, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 16.22, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 16.76, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 44.56, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 43.58, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 10.5, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 35.09, "Name": "MageBench", "BaseModel": "Llama-3.2-90B-Vision-Instruct", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 27.47, "Name": "MageBench", "BaseModel": "Llama-3.2-90B-Vision-Instruct", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 45.8, "Name": "MageBench", "BaseModel": "Llama-3.2-90B-Vision-Instruct", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 14.28, "Name": "MageBench", "BaseModel": "Llama-3.2-90B-Vision-Instruct", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 64.11, "Name": "MageBench", "BaseModel": "Claude-3.5-Sonnet", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 62.08, "Name": "MageBench", "BaseModel": "Claude-3.5-Sonnet", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 48.26, "Name": "MageBench", "BaseModel": "Claude-3.5-Sonnet", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 45.35, "Name": "MageBench", "BaseModel": "Claude-3.5-Sonnet", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 16.94, "Name": "MageBench", "BaseModel": "Claude-3.5-Sonnet", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 44.79, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 39.3, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.13, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 51.84, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 18.33, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 34.28, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 35.5, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.09, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 53.03, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 21.2, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 0.0, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 0.0, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 41.18, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 41.18, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 2.53, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 0.0, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 0.0, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.61, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.61, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 17.33, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 68.71, "Name": "MageBench", "BaseModel": "Human", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 94.32, "Name": "MageBench", "BaseModel": "Human", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 83.63, "Name": "MageBench", "BaseModel": "Human", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 96.85, "Name": "MageBench", "BaseModel": "Human", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 54.68, "Name": "MageBench", "BaseModel": "Human", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 10.61, "Name": "MageBench", "BaseModel": "InternVL2-1B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 16.14, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-1.8B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 17.33, "Name": "MageBench", "BaseModel": "InternVL2-2B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 9.26, "Name": "MageBench", "BaseModel": "Qwen2-vl-2B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 2.92, "Name": "MageBench", "BaseModel": "InternVL2-4B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 1.36, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 8.08, "Name": "MageBench", "BaseModel": "Yi-VL-6B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 18.22, "Name": "MageBench", "BaseModel": "DeepSeek-VL-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 15.32, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 11.42, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 9.07, "Name": "MageBench", "BaseModel": "Llava-1.6-mistral-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 11.98, "Name": "MageBench", "BaseModel": "Qwen2-vl-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 16.06, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 27.43, "Name": "MageBench", "BaseModel": "InternVL2-8B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 39.22, "Name": "MageBench", "BaseModel": "Llama-3.2-11B-Vision-Instruct", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 13.3, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 31.68, "Name": "MageBench", "BaseModel": "InternVL2-26B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 1.65, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 7.21, "Name": "MageBench", "BaseModel": "Yi-VL-34B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 7.2, "Name": "MageBench", "BaseModel": "InternVL2-40B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 11.7, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 10.36, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 28.45, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 42.21, "Name": "MageBench", "BaseModel": "Llama-3.2-90B-Vision-Instruct", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 40.02, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 52.1, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.01, "Name": "MageBench", "BaseModel": "InternVL2-1B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 45.76, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-1.8B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 45.94, "Name": "MageBench", "BaseModel": "InternVL2-2B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.43, "Name": "MageBench", "BaseModel": "Qwen2-vl-2B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.32, "Name": "MageBench", "BaseModel": "InternVL2-4B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.62, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 45.6, "Name": "MageBench", "BaseModel": "DeepSeek-VL-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.84, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 45.6, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.37, "Name": "MageBench", "BaseModel": "Llava-1.6-mistral-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.38, "Name": "MageBench", "BaseModel": "Qwen2-vl-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.53, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.56, "Name": "MageBench", "BaseModel": "InternVL2-8B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.54, "Name": "MageBench", "BaseModel": "Llama-3.2-11B-Vision-Instruct", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.65, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.77, "Name": "MageBench", "BaseModel": "InternVL2-26B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.06, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 45.65, "Name": "MageBench", "BaseModel": "InternVL2-40B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 47.14, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.39, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.61, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 47.14, "Name": "MageBench", "BaseModel": "Llama-3.2-90B-Vision-Instruct", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 47.46, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 47.65, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.06, "Name": "MageBench", "BaseModel": "InternVL2-1B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 45.6, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-1.8B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.11, "Name": "MageBench", "BaseModel": "InternVL2-2B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.52, "Name": "MageBench", "BaseModel": "Qwen2-vl-2B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.28, "Name": "MageBench", "BaseModel": "InternVL2-4B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.74, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.64, "Name": "MageBench", "BaseModel": "DeepSeek-VL-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.39, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.19, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.23, "Name": "MageBench", "BaseModel": "Llava-1.6-mistral-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.41, "Name": "MageBench", "BaseModel": "Qwen2-vl-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.86, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.35, "Name": "MageBench", "BaseModel": "InternVL2-8B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 47.33, "Name": "MageBench", "BaseModel": "Llama-3.2-11B-Vision-Instruct", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.53, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.5, "Name": "MageBench", "BaseModel": "InternVL2-26B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.48, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.82, "Name": "MageBench", "BaseModel": "InternVL2-40B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 47.84, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 46.68, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 47.09, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 48.63, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 48.33, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": -2.47, "Name": "MageBench", "BaseModel": "InternVL2-1B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 2.0, "Name": "MageBench", "BaseModel": "InternVL2-2B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 0.64, "Name": "MageBench", "BaseModel": "Qwen2-vl-2B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": -0.03, "Name": "MageBench", "BaseModel": "InternVL2-4B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 11.04, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": -0.8, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-7B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": -3.64, "Name": "MageBench", "BaseModel": "Llava-1.6-mistral-7B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 2.68, "Name": "MageBench", "BaseModel": "Qwen2-vl-7B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 3.61, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 7.9, "Name": "MageBench", "BaseModel": "InternVL2-8B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 11.58, "Name": "MageBench", "BaseModel": "Llama-3.2-11B-Vision-Instruct", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 16.59, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 15.62, "Name": "MageBench", "BaseModel": "InternVL2-26B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 3.04, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 12.99, "Name": "MageBench", "BaseModel": "InternVL2-40B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 15.02, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 18.43, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 8.04, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 8.32, "Name": "MageBench", "BaseModel": "Llama-3.2-90B-Vision-Instruct", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 17.78, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 19.61, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 0.0, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 45.6, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 45.6, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 2.36, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 0.0, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 47.4, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 47.4, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}
{"Score": 16.64, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "https://arxiv.org/abs/2412.04531", "State": "Checked"}