List your company

Medical Question Answering on CV-MedMCQA (test)

0.9999AUROCAU-probe
0.4130280.5653890.717750.870111Jan 24, 2026

Evaluation results

MethodLinks
AU-probeModel=Qwen2.5-7B-Instruct2026.010.99990.10350.0207
AU-probeModel=BioMistral-7B2026.010.99580.10630.0388
AU-probeModel=Bio-Medical-Llama-3-8B2026.010.99110.21310.0848
AU-probeModel=Llama-3.1-8B-Instruct2026.010.9690.09840.0794
ASK4CONFModel=Qwen2.5-7B-Instruct2026.010.7190.18370.254
ASK4CONFModel=Llama-3.1-8B-Instruct2026.010.60110.36650.3788
MSPModel=Bio-Medical-Llama-3-8B2026.010.58330.42970.4331
Mean Token EntropyModel=Bio-Medical-Llama-3-8B2026.010.56450.18140.2876
ASK4CONFModel=Bio-Medical-Llama-3-8B2026.010.55820.38450.3942
Semantic EntropyModel=Llama-3.1-8B-Instruct2026.010.5560.42450.426
RAUQModel=Llama-3.1-8B-Instruct2026.010.5520.1160.2659
SARModel=Bio-Medical-Llama-3-8B2026.010.54410.08060.2671
Mean Token EntropyModel=Qwen2.5-7B-Instruct2026.010.54210.27780.3433
Semantic EntropyModel=BioMistral-7B2026.010.53610.21020.3074
SARModel=Qwen2.5-7B-Instruct2026.010.53160.31640.3669
Semantic EntropyModel=Bio-Medical-Llama-3-8B2026.010.53080.23140.3117
MSPModel=Qwen2.5-7B-Instruct2026.010.53030.48160.48
MSPModel=Llama-3.1-8B-Instruct2026.010.52920.47970.4786
Semantic EntropyModel=Qwen2.5-7B-Instruct2026.010.52330.45860.4594
RAUQModel=Bio-Medical-Llama-3-8B2026.010.51680.12930.2791
SARModel=Llama-3.1-8B-Instruct2026.010.50830.20050.3117
SARModel=BioMistral-7B2026.010.4960.11950.2739
RAUQModel=Qwen2.5-7B-Instruct2026.010.49380.25630.3256
Mean Token EntropyModel=BioMistral-7B2026.010.49280.25990.331
Mean Token EntropyModel=Llama-3.1-8B-Instruct2026.010.490.2690.3354
MSPModel=BioMistral-7B2026.010.48460.45850.464
RAUQModel=BioMistral-7B2026.010.48440.16870.2891
ASK4CONFModel=BioMistral-7B2026.010.43560.34230.391