| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MATH 500 | GUPO + SAGE | Brier Score0.0202 | 9 | 1mo ago | |
| MetaMathQA (final) | MegaTrain | Accuracy92.52 | 9 | 3mo ago | |
| MathQA | Accuracy64.55 | 8 | 2mo ago | ||
| Math QA | AGLS | Clean Accuracy46.72 | 4 | 1mo ago | |
| GSM8K (test) | CluCERT | RAvg1.16 | 4 | 5mo ago | |
| GSM8K | B1 max entropy | AUROC72.4 | 3 | 4mo ago | |
| AMC23 | Accuracy89.69 | 2 | 1mo ago |