Medical Reasoning on ICD-Bench Difficulty Level 5 1.0
59.05AccuracyOURS-14B
Evaluation Results
| Method | Links | |
|---|---|---|
| OURS-14BParameters=14B, Majority voting=true2026.01 | 59.05 | |
| QWQ-MED-3 32BParameters=32B, Majority voting=true2026.01 | 49.69 |
Loading the SOTA2 catalog…