| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MM-Vet | GenRecal (InternVL3.5-8B) | MM-Vet Score86.2 | 517 | 7d ago | |
| MMMU | Gemini-2.5 (Pro) | Accuracy83.89 | 208 | 7d ago | |
| WeMath | TGRL-DAPO | Accuracy72.2 | 171 | 7d ago | |
| MMMU (val) | OpenAI-o1 | Accuracy78.2 | 168 | 23d ago | |
| MathVision | InternVL2.5-38B + VRPRM | Accuracy59.41 | 162 | 7d ago | |
| LogicVista | InternVL2.5-38B + VRPRM | Accuracy84.78 | 147 | 6d ago | |
| MMMU Pro | CoT2-Meta | Accuracy85.6 | 146 | 21d ago | |
| MMStar | Masters | Accuracy82 | 143 | 2mo ago | |
| MathVerse | OpenMMReasoner-7B | Accuracy63.8 | 130 | 7d ago | |
| MMBench | AutoNPO | Accuracy90.63 | 127 | 14d ago | |
| MMBench EN V1.1 | WSVD-noQ | Accuracy80.68 | 125 | 1d ago | |
| MMBench CN | Instruct | Accuracy82 | 113 | 15d ago | |
| MMStar | LaRe | Accuracy77.1 | 78 | 7d ago | |
| DynaMath | SwimBird | Accuracy67.2 | 72 | 7d ago | |
| MathVista | Qwen3-VL-32B-Thinking | Accuracy85.9 | 72 | 1mo ago | |
| M^3CoT | DAP-ICoT | Accuracy58.7 | 70 | 2mo ago | |
| MMBench | Qwen3VL-2B-SFT | MMBench Accuracy (en)84.29 | 61 | 1d ago | |
| SEED-Bench Image | PerceptionLM-8B | Score78.6 | 60 | 1d ago | |
| M3CoT (test) | Total Acc91.61 | 55 | 6d ago | ||
| MMBench (dev) | GPT-4o | Accuracy87.6 | 47 | 3mo ago | |
| MathVista | InternVL2.5-38B + VRPRM | Accuracy83.5 | 46 | 7d ago | |
| ScienceQA | MG2-RAG | Average Accuracy97.85 | 45 | 7d ago | |
| HallusionBench | TGRL-DAPO | Accuracy0.7293 | 42 | 2mo ago | |
| MMMU | DREAM-R | Accuracy85.79 | 40 | 6d ago | |
| RealWorldQA | DREAM-R | Accuracy81.39 | 40 | 6d ago |
