Medical Reasoning on ICD-Bench Difficulty Level 2 1.0
85.63AccuracyOURS-14B
Evaluation results
| Method | Links | |
|---|---|---|
| OURS-14BParameters=14B, Majority voting=true2026.01 | 85.63 | |
| QWQ-MED-3 32BParameters=32B, Majority voting=true2026.01 | 83.79 |
| Method | Links | |
|---|---|---|
| OURS-14BParameters=14B, Majority voting=true2026.01 | 85.63 | |
| QWQ-MED-3 32BParameters=32B, Majority voting=true2026.01 | 83.79 |