| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MMMU, MathVision, MathVerse-VO, DynaMath, WeMath Overall | Gemini-2.0-Flash | Macro F162.3 | 18 | 3mo ago | |
| WeMath | TIM-PRM | Macro F163.9 | 18 | 3mo ago | |
| DynaMath | Gemini-2.0-Flash | Macro F166.7 | 18 | 3mo ago | |
| MathVerse VO | Gemini-2.0-Flash | Macro F162.8 | 18 | 3mo ago | |
| MathVision | Qwen3-VL | Macro F161.7 | 18 | 3mo ago | |
| MMMU | Qwen2.5-VL | Macro F159.2 | 18 | 3mo ago | |
| Hard2Verify | VerifySteer-Bi | TNR37.3 | 15 | 13d ago | |
| ProcessBench Overall | VerifySteer-Bi | F1 Score72.3 | 13 | 13d ago | |
| ProcessBench Omni-MATH | Cons@4 | TNR63.1 | 13 | 13d ago | |
| ProcessBench OlympiadBench | Cons@4 | TNR61.3 | 13 | 13d ago | |
| ProcessBench Math | Cons@4 | TNR69.5 | 13 | 13d ago | |
| ProcessBench GSM8K v1 (val) | True Negative Rate68.6 | 13 | 13d ago |