Spaces:
Running
Running
Update commit_results.jsonl
Browse files- commit_results.jsonl +179 -179
commit_results.jsonl
CHANGED
|
@@ -1,179 +1,179 @@
|
|
| 1 |
-
{"Score": 0.03, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 2 |
-
{"Score": 11.78, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 3 |
-
{"Score": 44.95, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 4 |
-
{"Score": 44.14, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 5 |
-
{"Score": 10.0, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 6 |
-
{"Score": 13.78, "Name": "MageBench", "BaseModel": "DeepSeek-VL-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 7 |
-
{"Score": 8.07, "Name": "MageBench", "BaseModel": "DeepSeek-VL-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 8 |
-
{"Score": 12.95, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 9 |
-
{"Score": 15.26, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 10 |
-
{"Score": 45.57, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 11 |
-
{"Score": 42.28, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 12 |
-
{"Score": 12.52, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 13 |
-
{"Score": 10.03, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 14 |
-
{"Score": 42.52, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 15 |
-
{"Score": 42.36, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 16 |
-
{"Score": 2.1, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 17 |
-
{"Score": 11.95, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 18 |
-
{"Score": 9.92, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 19 |
-
{"Score": 46.28, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 20 |
-
{"Score": 42.59, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 21 |
-
{"Score": 18.13, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 22 |
-
{"Score": 6.57, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 23 |
-
{"Score": 15.17, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 24 |
-
{"Score": 43.19, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 25 |
-
{"Score": 43.47, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 26 |
-
{"Score": 3.91, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 27 |
-
{"Score": 7.14, "Name": "MageBench", "BaseModel": "Yi-VL-34B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 28 |
-
{"Score": 12.08, "Name": "MageBench", "BaseModel": "Yi-VL-34B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 29 |
-
{"Score": 7.37, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 30 |
-
{"Score": 13.03, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 31 |
-
{"Score": 46.21, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 32 |
-
{"Score": 43.22, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 33 |
-
{"Score": 15.75, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 34 |
-
{"Score": 4.71, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 35 |
-
{"Score": 14.46, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 36 |
-
{"Score": 43.46, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 37 |
-
{"Score": 44.07, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 38 |
-
{"Score": 14.46, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 39 |
-
{"Score": 16.22, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 40 |
-
{"Score": 16.76, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 41 |
-
{"Score": 44.56, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 42 |
-
{"Score": 43.58, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 43 |
-
{"Score": 10.5, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 44 |
-
{"Score": 35.09, "Name": "MageBench", "BaseModel": "Llama-3.2-90B-Vision-Instruct", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 45 |
-
{"Score": 27.47, "Name": "MageBench", "BaseModel": "Llama-3.2-90B-Vision-Instruct", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 46 |
-
{"Score": 45.8, "Name": "MageBench", "BaseModel": "Llama-3.2-90B-Vision-Instruct", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 47 |
-
{"Score": 14.28, "Name": "MageBench", "BaseModel": "Llama-3.2-90B-Vision-Instruct", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 48 |
-
{"Score": 64.11, "Name": "MageBench", "BaseModel": "Claude-3.5-Sonnet", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 49 |
-
{"Score": 62.08, "Name": "MageBench", "BaseModel": "Claude-3.5-Sonnet", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 50 |
-
{"Score": 48.26, "Name": "MageBench", "BaseModel": "Claude-3.5-Sonnet", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 51 |
-
{"Score": 45.35, "Name": "MageBench", "BaseModel": "Claude-3.5-Sonnet", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 52 |
-
{"Score": 16.94, "Name": "MageBench", "BaseModel": "Claude-3.5-Sonnet", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 53 |
-
{"Score": 44.79, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 54 |
-
{"Score": 39.3, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 55 |
-
{"Score": 46.13, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 56 |
-
{"Score": 51.84, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 57 |
-
{"Score": 18.33, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 58 |
-
{"Score": 34.28, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 59 |
-
{"Score": 35.5, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 60 |
-
{"Score": 46.09, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 61 |
-
{"Score": 53.03, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 62 |
-
{"Score": 21.2, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 63 |
-
{"Score": 0.0, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 64 |
-
{"Score": 0.0, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 65 |
-
{"Score": 41.18, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 66 |
-
{"Score": 41.18, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 67 |
-
{"Score": 2.53, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 68 |
-
{"Score": 0.0, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 69 |
-
{"Score": 0.0, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 70 |
-
{"Score": 46.61, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 71 |
-
{"Score": 46.61, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 72 |
-
{"Score": 17.33, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 73 |
-
{"Score": 68.71, "Name": "MageBench", "BaseModel": "Human", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 74 |
-
{"Score": 94.32, "Name": "MageBench", "BaseModel": "Human", "Env.": "WebUI", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 75 |
-
{"Score": 83.63, "Name": "MageBench", "BaseModel": "Human", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "mini", "Link": "
|
| 76 |
-
{"Score": 96.85, "Name": "MageBench", "BaseModel": "Human", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 77 |
-
{"Score": 54.68, "Name": "MageBench", "BaseModel": "Human", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "mini", "Link": "
|
| 78 |
-
{"Score": 10.61, "Name": "MageBench", "BaseModel": "InternVL2-1B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 79 |
-
{"Score": 16.14, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-1.8B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 80 |
-
{"Score": 17.33, "Name": "MageBench", "BaseModel": "InternVL2-2B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 81 |
-
{"Score": 9.26, "Name": "MageBench", "BaseModel": "Qwen2-vl-2B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 82 |
-
{"Score": 2.92, "Name": "MageBench", "BaseModel": "InternVL2-4B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 83 |
-
{"Score": 1.36, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 84 |
-
{"Score": 8.08, "Name": "MageBench", "BaseModel": "Yi-VL-6B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 85 |
-
{"Score": 18.22, "Name": "MageBench", "BaseModel": "DeepSeek-VL-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 86 |
-
{"Score": 15.32, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 87 |
-
{"Score": 11.42, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 88 |
-
{"Score": 9.07, "Name": "MageBench", "BaseModel": "Llava-1.6-mistral-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 89 |
-
{"Score": 11.98, "Name": "MageBench", "BaseModel": "Qwen2-vl-7B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 90 |
-
{"Score": 16.06, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 91 |
-
{"Score": 27.43, "Name": "MageBench", "BaseModel": "InternVL2-8B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 92 |
-
{"Score": 39.22, "Name": "MageBench", "BaseModel": "Llama-3.2-11B-Vision-Instruct", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 93 |
-
{"Score": 13.3, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 94 |
-
{"Score": 31.68, "Name": "MageBench", "BaseModel": "InternVL2-26B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 95 |
-
{"Score": 1.65, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 96 |
-
{"Score": 7.21, "Name": "MageBench", "BaseModel": "Yi-VL-34B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 97 |
-
{"Score": 7.2, "Name": "MageBench", "BaseModel": "InternVL2-40B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 98 |
-
{"Score": 11.7, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 99 |
-
{"Score": 10.36, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 100 |
-
{"Score": 28.45, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 101 |
-
{"Score": 42.21, "Name": "MageBench", "BaseModel": "Llama-3.2-90B-Vision-Instruct", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 102 |
-
{"Score": 40.02, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 103 |
-
{"Score": 52.1, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 104 |
-
{"Score": 46.01, "Name": "MageBench", "BaseModel": "InternVL2-1B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 105 |
-
{"Score": 45.76, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-1.8B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 106 |
-
{"Score": 45.94, "Name": "MageBench", "BaseModel": "InternVL2-2B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 107 |
-
{"Score": 46.43, "Name": "MageBench", "BaseModel": "Qwen2-vl-2B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 108 |
-
{"Score": 46.32, "Name": "MageBench", "BaseModel": "InternVL2-4B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 109 |
-
{"Score": 46.62, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 110 |
-
{"Score": 45.6, "Name": "MageBench", "BaseModel": "DeepSeek-VL-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 111 |
-
{"Score": 46.84, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 112 |
-
{"Score": 45.6, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 113 |
-
{"Score": 46.37, "Name": "MageBench", "BaseModel": "Llava-1.6-mistral-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 114 |
-
{"Score": 46.38, "Name": "MageBench", "BaseModel": "Qwen2-vl-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 115 |
-
{"Score": 46.53, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 116 |
-
{"Score": 46.56, "Name": "MageBench", "BaseModel": "InternVL2-8B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 117 |
-
{"Score": 46.54, "Name": "MageBench", "BaseModel": "Llama-3.2-11B-Vision-Instruct", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 118 |
-
{"Score": 46.65, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 119 |
-
{"Score": 46.77, "Name": "MageBench", "BaseModel": "InternVL2-26B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 120 |
-
{"Score": 46.06, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 121 |
-
{"Score": 45.65, "Name": "MageBench", "BaseModel": "InternVL2-40B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 122 |
-
{"Score": 47.14, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 123 |
-
{"Score": 46.39, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 124 |
-
{"Score": 46.61, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 125 |
-
{"Score": 47.14, "Name": "MageBench", "BaseModel": "Llama-3.2-90B-Vision-Instruct", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 126 |
-
{"Score": 47.46, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 127 |
-
{"Score": 47.65, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 128 |
-
{"Score": 46.06, "Name": "MageBench", "BaseModel": "InternVL2-1B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 129 |
-
{"Score": 45.6, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-1.8B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 130 |
-
{"Score": 46.11, "Name": "MageBench", "BaseModel": "InternVL2-2B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 131 |
-
{"Score": 46.52, "Name": "MageBench", "BaseModel": "Qwen2-vl-2B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 132 |
-
{"Score": 46.28, "Name": "MageBench", "BaseModel": "InternVL2-4B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 133 |
-
{"Score": 46.74, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 134 |
-
{"Score": 46.64, "Name": "MageBench", "BaseModel": "DeepSeek-VL-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 135 |
-
{"Score": 46.39, "Name": "MageBench", "BaseModel": "Xcomposer-2.5-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 136 |
-
{"Score": 46.19, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 137 |
-
{"Score": 46.23, "Name": "MageBench", "BaseModel": "Llava-1.6-mistral-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 138 |
-
{"Score": 46.41, "Name": "MageBench", "BaseModel": "Qwen2-vl-7B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 139 |
-
{"Score": 46.86, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 140 |
-
{"Score": 46.35, "Name": "MageBench", "BaseModel": "InternVL2-8B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 141 |
-
{"Score": 47.33, "Name": "MageBench", "BaseModel": "Llama-3.2-11B-Vision-Instruct", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 142 |
-
{"Score": 46.53, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 143 |
-
{"Score": 46.5, "Name": "MageBench", "BaseModel": "InternVL2-26B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 144 |
-
{"Score": 46.48, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 145 |
-
{"Score": 46.82, "Name": "MageBench", "BaseModel": "InternVL2-40B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 146 |
-
{"Score": 47.84, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 147 |
-
{"Score": 46.68, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 148 |
-
{"Score": 47.09, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 149 |
-
{"Score": 48.63, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 150 |
-
{"Score": 48.33, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 151 |
-
{"Score": -2.47, "Name": "MageBench", "BaseModel": "InternVL2-1B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 152 |
-
{"Score": 2.0, "Name": "MageBench", "BaseModel": "InternVL2-2B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 153 |
-
{"Score": 0.64, "Name": "MageBench", "BaseModel": "Qwen2-vl-2B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 154 |
-
{"Score": -0.03, "Name": "MageBench", "BaseModel": "InternVL2-4B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 155 |
-
{"Score": 11.04, "Name": "MageBench", "BaseModel": "Phi-3.5-V-4.2B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 156 |
-
{"Score": -0.8, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-7B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 157 |
-
{"Score": -3.64, "Name": "MageBench", "BaseModel": "Llava-1.6-mistral-7B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 158 |
-
{"Score": 2.68, "Name": "MageBench", "BaseModel": "Qwen2-vl-7B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 159 |
-
{"Score": 3.61, "Name": "MageBench", "BaseModel": "MiniCPM-V2.6-8B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 160 |
-
{"Score": 7.9, "Name": "MageBench", "BaseModel": "InternVL2-8B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 161 |
-
{"Score": 11.58, "Name": "MageBench", "BaseModel": "Llama-3.2-11B-Vision-Instruct", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 162 |
-
{"Score": 16.59, "Name": "MageBench", "BaseModel": "LLaVA-v1.5-13B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 163 |
-
{"Score": 15.62, "Name": "MageBench", "BaseModel": "InternVL2-26B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 164 |
-
{"Score": 3.04, "Name": "MageBench", "BaseModel": "Llava-1.6-34B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 165 |
-
{"Score": 12.99, "Name": "MageBench", "BaseModel": "InternVL2-40B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 166 |
-
{"Score": 15.02, "Name": "MageBench", "BaseModel": "Qwen2-vl-72B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 167 |
-
{"Score": 18.43, "Name": "MageBench", "BaseModel": "NVLM-72B", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 168 |
-
{"Score": 8.04, "Name": "MageBench", "BaseModel": "InternVL2-76B-LLaMA3", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 169 |
-
{"Score": 8.32, "Name": "MageBench", "BaseModel": "Llama-3.2-90B-Vision-Instruct", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 170 |
-
{"Score": 17.78, "Name": "MageBench", "BaseModel": "GPT-4o", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 171 |
-
{"Score": 19.61, "Name": "MageBench", "BaseModel": "Gemini-1.5-pro", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 172 |
-
{"Score": 0.0, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 173 |
-
{"Score": 45.6, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 174 |
-
{"Score": 45.6, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 175 |
-
{"Score": 2.36, "Name": "MageBench", "BaseModel": "Idle Baseline", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 176 |
-
{"Score": 0.0, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "WebUI", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 177 |
-
{"Score": 47.4, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "Sokoban", "Target-research": "Model-Eval-Global", "Subset": "all", "Link": "
|
| 178 |
-
{"Score": 47.4, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "Sokoban", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
| 179 |
-
{"Score": 16.64, "Name": "MageBench", "BaseModel": "Random Baseline", "Env.": "Football", "Target-research": "Model-Eval-Online", "Subset": "all", "Link": "
|
|
|
|
| 1 |
+
{"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"}
|
| 2 |
+
{"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"}
|
| 3 |
+
{"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"}
|
| 4 |
+
{"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"}
|
| 5 |
+
{"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"}
|
| 6 |
+
{"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"}
|
| 7 |
+
{"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"}
|
| 8 |
+
{"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"}
|
| 9 |
+
{"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"}
|
| 10 |
+
{"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"}
|
| 11 |
+
{"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"}
|
| 12 |
+
{"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"}
|
| 13 |
+
{"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"}
|
| 14 |
+
{"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"}
|
| 15 |
+
{"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"}
|
| 16 |
+
{"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"}
|
| 17 |
+
{"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"}
|
| 18 |
+
{"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"}
|
| 19 |
+
{"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"}
|
| 20 |
+
{"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"}
|
| 21 |
+
{"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"}
|
| 22 |
+
{"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"}
|
| 23 |
+
{"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"}
|
| 24 |
+
{"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"}
|
| 25 |
+
{"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"}
|
| 26 |
+
{"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"}
|
| 27 |
+
{"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"}
|
| 28 |
+
{"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"}
|
| 29 |
+
{"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"}
|
| 30 |
+
{"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"}
|
| 31 |
+
{"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"}
|
| 32 |
+
{"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"}
|
| 33 |
+
{"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"}
|
| 34 |
+
{"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"}
|
| 35 |
+
{"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"}
|
| 36 |
+
{"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"}
|
| 37 |
+
{"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"}
|
| 38 |
+
{"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"}
|
| 39 |
+
{"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"}
|
| 40 |
+
{"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"}
|
| 41 |
+
{"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"}
|
| 42 |
+
{"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"}
|
| 43 |
+
{"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"}
|
| 44 |
+
{"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"}
|
| 45 |
+
{"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"}
|
| 46 |
+
{"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"}
|
| 47 |
+
{"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"}
|
| 48 |
+
{"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"}
|
| 49 |
+
{"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"}
|
| 50 |
+
{"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"}
|
| 51 |
+
{"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"}
|
| 52 |
+
{"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"}
|
| 53 |
+
{"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"}
|
| 54 |
+
{"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"}
|
| 55 |
+
{"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"}
|
| 56 |
+
{"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"}
|
| 57 |
+
{"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"}
|
| 58 |
+
{"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"}
|
| 59 |
+
{"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"}
|
| 60 |
+
{"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"}
|
| 61 |
+
{"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"}
|
| 62 |
+
{"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"}
|
| 63 |
+
{"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"}
|
| 64 |
+
{"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"}
|
| 65 |
+
{"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"}
|
| 66 |
+
{"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"}
|
| 67 |
+
{"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"}
|
| 68 |
+
{"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"}
|
| 69 |
+
{"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"}
|
| 70 |
+
{"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"}
|
| 71 |
+
{"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"}
|
| 72 |
+
{"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"}
|
| 73 |
+
{"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"}
|
| 74 |
+
{"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"}
|
| 75 |
+
{"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"}
|
| 76 |
+
{"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"}
|
| 77 |
+
{"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"}
|
| 78 |
+
{"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"}
|
| 79 |
+
{"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"}
|
| 80 |
+
{"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"}
|
| 81 |
+
{"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"}
|
| 82 |
+
{"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"}
|
| 83 |
+
{"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"}
|
| 84 |
+
{"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"}
|
| 85 |
+
{"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"}
|
| 86 |
+
{"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"}
|
| 87 |
+
{"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"}
|
| 88 |
+
{"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"}
|
| 89 |
+
{"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"}
|
| 90 |
+
{"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"}
|
| 91 |
+
{"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"}
|
| 92 |
+
{"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"}
|
| 93 |
+
{"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"}
|
| 94 |
+
{"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"}
|
| 95 |
+
{"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"}
|
| 96 |
+
{"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"}
|
| 97 |
+
{"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"}
|
| 98 |
+
{"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"}
|
| 99 |
+
{"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"}
|
| 100 |
+
{"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"}
|
| 101 |
+
{"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"}
|
| 102 |
+
{"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"}
|
| 103 |
+
{"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"}
|
| 104 |
+
{"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"}
|
| 105 |
+
{"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"}
|
| 106 |
+
{"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"}
|
| 107 |
+
{"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"}
|
| 108 |
+
{"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"}
|
| 109 |
+
{"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"}
|
| 110 |
+
{"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"}
|
| 111 |
+
{"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"}
|
| 112 |
+
{"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"}
|
| 113 |
+
{"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"}
|
| 114 |
+
{"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"}
|
| 115 |
+
{"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"}
|
| 116 |
+
{"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"}
|
| 117 |
+
{"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"}
|
| 118 |
+
{"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"}
|
| 119 |
+
{"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"}
|
| 120 |
+
{"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"}
|
| 121 |
+
{"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"}
|
| 122 |
+
{"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"}
|
| 123 |
+
{"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"}
|
| 124 |
+
{"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"}
|
| 125 |
+
{"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"}
|
| 126 |
+
{"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"}
|
| 127 |
+
{"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"}
|
| 128 |
+
{"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"}
|
| 129 |
+
{"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"}
|
| 130 |
+
{"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"}
|
| 131 |
+
{"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"}
|
| 132 |
+
{"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"}
|
| 133 |
+
{"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"}
|
| 134 |
+
{"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"}
|
| 135 |
+
{"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"}
|
| 136 |
+
{"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"}
|
| 137 |
+
{"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"}
|
| 138 |
+
{"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"}
|
| 139 |
+
{"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"}
|
| 140 |
+
{"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"}
|
| 141 |
+
{"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"}
|
| 142 |
+
{"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"}
|
| 143 |
+
{"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"}
|
| 144 |
+
{"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"}
|
| 145 |
+
{"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"}
|
| 146 |
+
{"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"}
|
| 147 |
+
{"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"}
|
| 148 |
+
{"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"}
|
| 149 |
+
{"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"}
|
| 150 |
+
{"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"}
|
| 151 |
+
{"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"}
|
| 152 |
+
{"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"}
|
| 153 |
+
{"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"}
|
| 154 |
+
{"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"}
|
| 155 |
+
{"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"}
|
| 156 |
+
{"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"}
|
| 157 |
+
{"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"}
|
| 158 |
+
{"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"}
|
| 159 |
+
{"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"}
|
| 160 |
+
{"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"}
|
| 161 |
+
{"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"}
|
| 162 |
+
{"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"}
|
| 163 |
+
{"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"}
|
| 164 |
+
{"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"}
|
| 165 |
+
{"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"}
|
| 166 |
+
{"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"}
|
| 167 |
+
{"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"}
|
| 168 |
+
{"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"}
|
| 169 |
+
{"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"}
|
| 170 |
+
{"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"}
|
| 171 |
+
{"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"}
|
| 172 |
+
{"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"}
|
| 173 |
+
{"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"}
|
| 174 |
+
{"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"}
|
| 175 |
+
{"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"}
|
| 176 |
+
{"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"}
|
| 177 |
+
{"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"}
|
| 178 |
+
{"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"}
|
| 179 |
+
{"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"}
|