List your company

Medical Question Answering on CV-MedExQA (test)

0.9987AUROCAU-probe
0.4853560.6186280.75190.885172Jan 24, 2026

Evaluation results

MethodLinks
AU-probeModel=Qwen2.5-7B-Instruct2026.010.99870.24880.1277
AU-probeModel=BioMistral-7B2026.010.9780.22820.1551
AU-probeModel=Bio-Medical-Llama-3-8B2026.010.95530.25160.1847
AU-probeModel=Llama-3.1-8B-Instruct2026.010.88670.18390.1793
ASK4CONFModel=Qwen2.5-7B-Instruct2026.010.70560.21840.2693
ASK4CONFModel=Llama-3.1-8B-Instruct2026.010.64970.38860.3872
MSPModel=BioMistral-7B2026.010.6410.46440.4661
SARModel=BioMistral-7B2026.010.63490.07410.2434
RAUQModel=BioMistral-7B2026.010.62740.19510.2778
Semantic EntropyModel=BioMistral-7B2026.010.61880.21680.2907
Mean Token EntropyModel=BioMistral-7B2026.010.59810.29250.3301
MSPModel=Bio-Medical-Llama-3-8B2026.010.59050.42680.4287
Mean Token EntropyModel=Bio-Medical-Llama-3-8B2026.010.58120.16190.2752
Semantic EntropyModel=Llama-3.1-8B-Instruct2026.010.57680.43690.4359
Semantic EntropyModel=Bio-Medical-Llama-3-8B2026.010.56110.26570.3206
RAUQModel=Llama-3.1-8B-Instruct2026.010.560.22460.3014
SARModel=Bio-Medical-Llama-3-8B2026.010.55720.09490.2613
ASK4CONFModel=Bio-Medical-Llama-3-8B2026.010.55460.39050.4
MSPModel=Llama-3.1-8B-Instruct2026.010.55140.47520.4737
Mean Token EntropyModel=Llama-3.1-8B-Instruct2026.010.54010.33170.3612
SARModel=Qwen2.5-7B-Instruct2026.010.53760.34220.3819
RAUQModel=Bio-Medical-Llama-3-8B2026.010.53710.13850.2763
SARModel=Llama-3.1-8B-Instruct2026.010.53640.2150.311
Semantic EntropyModel=Qwen2.5-7B-Instruct2026.010.53050.43950.4452
MSPModel=Qwen2.5-7B-Instruct2026.010.52990.42760.4359
Mean Token EntropyModel=Qwen2.5-7B-Instruct2026.010.52150.29020.3542
RAUQModel=Qwen2.5-7B-Instruct2026.010.51110.24550.3147
ASK4CONFModel=BioMistral-7B2026.010.50510.33650.3712