List your company

Medical Knowledge Evaluation on NEJMQA

66.14AccuracyDOS-CPT
64.673665.054365.43565.8157Dec 25, 2025

Evaluation results

MethodLinks
DOS-CPTBackbone=Qwen3-14B-Base, CPT Strategy=Distance-to-Optimum Selection2025.1266.14
RS-CPTBackbone=Qwen3-14B-Base, CPT Strategy=Random Data Sampling2025.1266.06
LPS-CPTBackbone=Qwen3-14B-Base, CPT Strategy=Low-PPL Sampling2025.1265.6
HPS-CPTBackbone=Qwen3-14B-Base, CPT Strategy=High-PPL Sampling2025.1264.79
Qwen3-14B-BaseBackbone=Qwen3-14B-Base, CPT Strategy=None2025.1264.73