List your company

Medical Knowledge Evaluation on MMLU Med

88.1AccuracyGemini 3 Pro
68.96473.93278.983.868Dec 25, 2025Jan 11, 2026Jan 28, 2026Feb 14, 2026Mar 3, 2026Mar 20, 2026Apr 6, 2026

Evaluation results

MethodLinks
Gemini 3 ProTemperature=default2026.0488.1
Gemini 3 FlashTemperature=default2026.0487.5
MedGemma 1Model Scale=27B, Temperature=0.02026.0486.2
DOS-CPTBackbone=Qwen3-14B-Base, CPT Strategy=Distance-to-Optimum Selection2025.1282.11
LPS-CPTBackbone=Qwen3-14B-Base, CPT Strategy=Low-PPL Sampling2025.1281.85
HPS-CPTBackbone=Qwen3-14B-Base, CPT Strategy=High-PPL Sampling2025.1281.68
RS-CPTBackbone=Qwen3-14B-Base, CPT Strategy=Random Data Sampling2025.1281.62
Qwen3-14B-BaseBackbone=Qwen3-14B-Base, CPT Strategy=None2025.1281.19
Qwen3 VLModel Scale=4B, Temperature=default2026.0478.3
MedGemma 1Model Scale=4B, Temperature=0.02026.0470
MedGemma 1.5Model Scale=4B, Temperature=0.02026.0469.7