| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Medical Question Answering | MedCalc-Bench | Accuracy35.3 | 30 | |
| Medical calculation | MedCalc-Bench | Accuracy81.4 | 15 | |
| Skill retrieval | MedCalc-Bench | nDCG@192.3 | 11 | |
| Medical Calculation | MedCalc-Bench Original (test) | Accuracy73.95 | 8 | |
| Medical Calculation | MedCalc-Bench Cleaned & restructured | Accuracy62.7 | 2 | |
| Medical Calculation | MedCalc-Bench Original (train) | Accuracy49.19 | 2 | |
| Medical Calculation | MedCalc-Bench Verified | Accuracy34.8 | 1 |