Medical Long-form Generation on MedMCQA (test)
75.3SM ScoreAPCD
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| APCDBackbone=II-Medical-8B-1706, Decoding Strategy=APCD2026.05 | 75.3 | 76.9 | |
| Sample (top k + top p)Backbone=II-Medical-8B-1706, Decoding Strategy=Sample (top k + top p)2026.05 | 72 | 74 | |
| CSBackbone=II-Medical-8B-1706, Decoding Strategy=CS2026.05 | 71.9 | 73.8 | |
| DoLa (low)Backbone=II-Medical-8B-1706, Decoding Strategy=DoLa (low)2026.05 | 69 | 72.9 | |
| Beam SearchBackbone=II-Medical-8B-1706, Decoding Strategy=Beam Search2026.05 | 68.9 | 71.7 | |
| II-Medical-8B-1706Backbone=II-Medical-8B-1706, Decoding Strategy=Standard2026.05 | 67.9 | 71 | |
| DBSBackbone=II-Medical-8B-1706, Decoding Strategy=DBS2026.05 | 64.2 | 71.7 | |
| DoLa (high)Backbone=II-Medical-8B-1706, Decoding Strategy=DoLa (high)2026.05 | 17.4 | 17.5 |