| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MATH | DeepSeek-R1 | Accuracy97.6 | 229 | 4mo ago | |
| MATH | Accuracy95.86 | 114 | 1mo ago | ||
| AIME 2024 | Accuracy100 | 113 | 2mo ago | ||
| MATH500 | Self-MoA | Accuracy93 | 96 | 1mo ago | |
| AIME 25 | Accuracy93.3 | 84 | 1mo ago | ||
| AIME 2025 | Score100 | 76 | 2mo ago | ||
| Gaokao MathQA | Qwen2.5-Math-72B | Accuracy86.3 | 60 | 4mo ago | |
| LiveMath held-out (test) | SkillOpt | Score78.4 | 59 | 2mo ago | |
| MinervaMath (test) | Confidence + AXON | Accuracy38.5 | 58 | 1mo ago | |
| AIME 2024 | Self-MoA | Top-1 Accuracy76.67 | 54 | 2mo ago | |
| AIME | MSV 64 | AIME Score1,289.8 | 52 | 4mo ago | |
| AIME 2025 | Top-1 Accuracy (%)91.67 | 46 | 2mo ago | ||
| MATH (test) | COPRO-M | Accuracy93.22 | 45 | 25d ago | |
| MATH | Accuracy95.7 | 40 | 3mo ago | ||
| AIME 25 | CoT | Average Time15.69 | 39 | 2mo ago | |
| MATH | CoT | Average Time3.94 | 39 | 2mo ago | |
| AIME 24 | CoT | Average Time15.58 | 39 | 2mo ago | |
| GSM8K (test) | Confidence + AXON | Accuracy81.5 | 30 | 1mo ago | |
| Code2Math | Accuracy Ratio98 | 30 | 4mo ago | ||
| AIME | Accuracy85 | 28 | 2mo ago | ||
| MathVerse (testmini) | Accuracy64.9 | 28 | 4mo ago | ||
| AMC 2023 | TRACE (RKL on Ey) | Accuracy (avg@k)97.81 | 27 | 1mo ago | |
| AMC | OWPO | Pass@178.36 | 27 | 2mo ago | |
| MATH-Vision (test) | Accuracy68.8 | 26 | 4mo ago | ||
| MATH 500 | Accuracy95.66 | 24 | 2mo ago |