List your company

Medical Long-form Generation on MedQA (test)

85SMAPCD
9.39229.02148.6568.279May 10, 2026

Evaluation results

MethodLinks
APCDBackbone=II-Medical-8B-1706, Decoding Strategy=APCD2026.058586.7
CSBackbone=II-Medical-8B-1706, Decoding Strategy=CS2026.0583.485.8
Sample (top k + top p)Backbone=II-Medical-8B-1706, Decoding Strategy=Sample (top k + top p)2026.0580.185.2
Beam SearchBackbone=II-Medical-8B-1706, Decoding Strategy=Beam Search2026.0579.983.1
II-Medical-8B-1706Backbone=II-Medical-8B-1706, Decoding Strategy=Standard2026.0579.282.8
DoLa (low)Backbone=II-Medical-8B-1706, Decoding Strategy=DoLa (low)2026.0576.784.5
DBSBackbone=II-Medical-8B-1706, Decoding Strategy=DBS2026.0572.382
DoLa (high)Backbone=II-Medical-8B-1706, Decoding Strategy=DoLa (high)2026.0512.312.7