| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MM-Vet | GenRecal (InternVL3.5-8B) | MM-Vet Score86.2 | 551 | 22d ago | |
| MMMU | Gemini-2.5 (Pro) | Accuracy83.89 | 220 | 22d ago | |
| WeMath | Accuracy78 | 199 | 25d ago | ||
| MMBench | AutoNPO | Accuracy90.63 | 180 | 25d ago | |
| LogicVista | InternVL2.5-38B + VRPRM | Accuracy84.78 | 172 | 22d ago | |
| MMMU Pro | CoT2-Meta | Accuracy85.6 | 171 | 24d ago | |
| MMMU (val) | OpenAI-o1 | Accuracy78.2 | 168 | 2mo ago | |
| MathVision | InternVL2.5-38B + VRPRM | Accuracy59.41 | 162 | 1mo ago | |
| MMStar | Masters | Accuracy82 | 143 | 3mo ago | |
| MathVerse | PAPOG | Accuracy68.5 | 138 | 1mo ago | |
| MMBench EN V1.1 | WSVD-noQ | Accuracy80.68 | 125 | 1mo ago | |
| MMBench CN | Instruct | Accuracy82 | 119 | 1mo ago | |
| MMStar | TVI-CoT | Accuracy79.2 | 102 | 18d ago | |
| MathVista | Qwen3-VL-32B-Thinking | Accuracy85.9 | 89 | 29d ago | |
| MMMU | Accuracy72.9 | 77 | 24d ago | ||
| DynaMath | SwimBird | Accuracy67.2 | 77 | 1mo ago | |
| M^3CoT | DAP-ICoT | Accuracy58.7 | 70 | 4mo ago | |
| MMBench | Qwen3VL-2B-SFT | MMBench Accuracy (en)84.29 | 65 | 24d ago | |
| SEED-Bench Image | PerceptionLM-8B | Score78.6 | 60 | 1mo ago | |
| SEED-BENCH | C-RADIOv4-H | Accuracy78.1 | 59 | 18d ago | |
| M3CoT (test) | Total Acc91.61 | 55 | 1mo ago | ||
| MathVista | InternVL2.5-38B + VRPRM | Accuracy83.5 | 50 | 22d ago | |
| MMBench (dev) | GPT-4o | Accuracy87.6 | 47 | 4mo ago | |
| ScienceQA | MG2-RAG | Average Accuracy97.85 | 45 | 1mo ago | |
| MMMU (test) | GPT-4o | Accuracy64.7 | 43 | 25d ago |
