Our new X account is live! Follow @wizwand_team for updates

Medical Question Answering on CV-MedMCQA (test)

0.9999AUROC

AU-probe

Updated 3d ago

Evaluation Results

Method	Links
AU-probe 2026.01		0.9999	0.1035	0.0207
AU-probe 2026.01		0.9958	0.1063	0.0388
AU-probe 2026.01		0.9911	0.2131	0.0848
AU-probe 2026.01		0.969	0.0984	0.0794
ASK4CONF 2026.01		0.719	0.1837	0.254
ASK4CONF 2026.01		0.6011	0.3665	0.3788
MSP 2026.01		0.5833	0.4297	0.4331
Mean Token Entropy 2026.01		0.5645	0.1814	0.2876
ASK4CONF 2026.01		0.5582	0.3845	0.3942
Semantic Entropy 2026.01		0.556	0.4245	0.426
RAUQ 2026.01		0.552	0.116	0.2659
SAR 2026.01		0.5441	0.0806	0.2671
Mean Token Entropy 2026.01		0.5421	0.2778	0.3433
Semantic Entropy 2026.01		0.5361	0.2102	0.3074
SAR 2026.01		0.5316	0.3164	0.3669
Semantic Entropy 2026.01		0.5308	0.2314	0.3117
MSP 2026.01		0.5303	0.4816	0.48
MSP 2026.01		0.5292	0.4797	0.4786
Semantic Entropy 2026.01		0.5233	0.4586	0.4594
RAUQ 2026.01		0.5168	0.1293	0.2791
SAR 2026.01		0.5083	0.2005	0.3117
SAR 2026.01		0.496	0.1195	0.2739
RAUQ 2026.01		0.4938	0.2563	0.3256
Mean Token Entropy 2026.01		0.4928	0.2599	0.331
Mean Token Entropy 2026.01		0.49	0.269	0.3354
MSP 2026.01		0.4846	0.4585	0.464
RAUQ 2026.01		0.4844	0.1687	0.2891
ASK4CONF 2026.01		0.4356	0.3423	0.391