Medical Reasoning on ICD-Bench Difficulty Level 4 1.0
71.5AccuracyOURS-14B
Evaluation Results
| Method | Links | |
|---|---|---|
| OURS-14BParameters=14B, Majority voting=true2026.01 | 71.5 | |
| QWQ-MED-3 32BParameters=32B, Majority voting=true2026.01 | 70.56 |
| Method | Links | |
|---|---|---|
| OURS-14BParameters=14B, Majority voting=true2026.01 | 71.5 | |
| QWQ-MED-3 32BParameters=32B, Majority voting=true2026.01 | 70.56 |