| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| GSM8K | BERT-Judge | Accuracy0.988 | 248 | 1mo ago | |
| MATH-500 | GLM-4.7-Flash-T | Accuracy99.2 | 126 | 29d ago | |
| AIME24 | DSMoE | Accuracy77.3 | 57 | 1mo ago | |
| GSM8K | Pass@196.51 | 47 | 3mo ago | ||
| GSM8K 5-shot | UltraMix-190k | Score82.7 | 46 | 4mo ago | |
| Minerva | COSE | Accuracy89.16 | 40 | 1mo ago | |
| MATH500 | AIPO | Score99.32 | 39 | 2mo ago | |
| Math (test) | OPCD | Accuracy80.9 | 36 | 4mo ago | |
| AMC23 | MPO+ | Score78.3 | 33 | 1mo ago | |
| OlympiadBench | Score77.59 | 31 | 3mo ago | ||
| GSM8K (test) | TextGrad-M | Mean@494.04 | 28 | 25d ago | |
| GSM-Plus | Qwen3.5-9B | Score90.7 | 28 | 1mo ago | |
| MATH | DSR | Score39.66 | 27 | 2mo ago | |
| AIME 2025 | VP2O | Accuracy (%)69.9 | 26 | 1mo ago | |
| AIME 2025 | ePF | Top-1 Score28.83 | 26 | 3mo ago | |
| MATH 500 | MATH 500 Score96.6 | 25 | 1mo ago | ||
| MATH 500 | Accuracy92.7 | 25 | 1mo ago | ||
| iGSM | Accuracy100 | 25 | 2mo ago | ||
| AIME 25 | Score (%)61.11 | 23 | 1mo ago | ||
| GSM8K | GSM8K Math Score94.01 | 22 | 1mo ago | ||
| CMATH | LLaDA2.0-flash | Score96.9 | 22 | 2mo ago | |
| Math | IGDS | pass@861.1 | 21 | 2mo ago | |
| LiC Math | Concat Score92.9 | 21 | 3mo ago | ||
| IMO-ANSWERBENCH | Seed2.0 Pro | Score89.3 | 18 | 23d ago | |
| AIME 24 | Projected | AVG@3274.38 | 16 | 18d ago |