| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MedCalc-Bench | GPT-5 | Accuracy81.4 | 15 | 22d ago | |
| MedCalc-Bench Original (test) | Accuracy73.95 | 8 | 3mo ago | ||
| MedCalc Formulas | Dynamic Workflow (ReAct) | Accuracy82 | 3 | 1d ago | |
| MedCalc-Bench Cleaned & restructured | Accuracy62.7 | 2 | 3mo ago | ||
| MedCalc-Bench Original (train) | Accuracy49.19 | 2 | 3mo ago | ||
| MedCalc Bench Company eval | Accuracy61.3 | 1 | 3mo ago | ||
| MedCalc-Bench Verified | Accuracy34.8 | 1 | 3mo ago |