Medical Reasoning on ICD-Bench Difficulty Level 1 1.0
0.9675AccuracyQWQ-MED-3 32B
Evaluation Results
| Method | Links | |
|---|---|---|
| QWQ-MED-3 32BParameters=32B, Majority voting=true2026.01 | 0.9675 | |
| OURS-14BParameters=14B, Majority voting=true2026.01 | 0.9423 |
| Method | Links | |
|---|---|---|
| QWQ-MED-3 32BParameters=32B, Majority voting=true2026.01 | 0.9675 | |
| OURS-14BParameters=14B, Majority voting=true2026.01 | 0.9423 |