| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MedCalc-Bench | Ens. (QwQ+DAPO/OSS) | NRR 1.5B Score0.39 | 11 | 1mo ago | |
| MedCalc-Bench Original (test) | Accuracy73.95 | 8 | 1mo ago | ||
| MedCalc-Bench Cleaned & restructured | Accuracy62.7 | 2 | 1mo ago | ||
| MedCalc-Bench Original (train) | Accuracy49.19 | 2 | 1mo ago | ||
| MedCalc Bench Company eval | Accuracy61.3 | 1 | 1mo ago | ||
| MedCalc-Bench Verified | Accuracy34.8 | 1 | 1mo ago |