| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Medical | MedCalc | Accuracy57.4 | 25 | |
| Property Inference Defense | MedCalc QA | Generation Attack MAE0.013 | 6 | |
| Property Inference Defense | MedCalc CC | Generation Attack MAE0.0104 | 6 | |
| QA | MedCalc | MAE0.0157 | 5 | |
| CC | MedCalc | MAE0.0066 | 5 | |
| Medical Calculation | MedCalc Bench Company eval | Accuracy61.3 | 1 |