| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MathVista MINI | Accuracy0.878 | 90 | 5d ago | ||
| OlympiadBench | Accuracy68 | 56 | 8d ago | ||
| MathVista mini (test) | ReLaX-VL-7B | Overall Accuracy77.1 | 48 | 25d ago | |
| MathVision (test) | OpenAI-o1 | Accuracy60.3 | 47 | 18d ago | |
| LogicVista | Gemini-2.5-Pro-Thinking | Accuracy75.2 | 34 | 25d ago | |
| MathVista (test) | Qwen-VL-Max | Accuracy74.2 | 34 | 18d ago | |
| MathVerse-V | Gemini-2.5-Pro-Thinking | Accuracy81.2 | 33 | 15d ago | |
| MathVerse (test) | Accuracy (ALL)64.9 | 33 | 18d ago | ||
| DynaMath | Metis | Accuracy (DynaMath)69.2 | 28 | 4d ago | |
| MathVerse mini (test) | T-Dominant Score70.94 | 26 | 1mo ago | ||
| MathVista testmini | Score63 | 23 | 18d ago | ||
| MathVerse mini | Metis | Accuracy65.9 | 22 | 8d ago | |
| WeMath (test) | GSPO + KAWHI (Qwen3) | Accuracy72.15 | 17 | 18d ago | |
| MathVista | Vision-R1-72B* | Overall Accuracy (ALL)78.2 | 17 | 1mo ago | |
| MathVision | Naive-KD | Mean@579.5 | 16 | 18d ago | |
| MathVerse (testmini) | OpenAI-o1 | Accuracy57 | 16 | 1mo ago | |
| MathVista | Qwen2.5-VL-7B-Instruct + RFT | Pass@1 Accuracy73.8 | 15 | 4d ago | |
| MathVista | GPS Score85.1 | 15 | 1mo ago | ||
| MathVerse | Qwen2.5-VL-7B-Instruct + RFT | Pass@1 Accuracy47.2 | 14 | 4d ago | |
| DynaMath-W | Seed-1.5-thinking | Accuracy60.5 | 14 | 1mo ago | |
| MathVerse | SophiaVL-R1-7B | Average Score48.8 | 13 | 1mo ago | |
| MathVerse 1.0 (test) | Score73.01 | 12 | 3d ago | ||
| WeMath mini (test) | Accuracy72.6 | 12 | 1mo ago | ||
| MathVerse mini-vision | Score31.2 | 12 | 1mo ago | ||
| MathV | Chain of Mindset (CoM) | Pass@1 Accuracy63.16 | 12 | 1mo ago |