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

Medical Question Answering on CV-MedQA (test)

0.9998AUROC

AU-probe

Updated 3d ago

Evaluation Results

Method	Links
AU-probe 2026.01		0.9998	0.0515	0.0109
AU-probe 2026.01		0.9997	0.0379	0.0102
AU-probe 2026.01		0.9977	0.1908	0.0595
AU-probe 2026.01		0.9891	0.0411	0.0424
ASK4CONF 2026.01		0.8281	0.2429	0.2529
ASK4CONF 2026.01		0.7554	0.1259	0.2058
ASK4CONF 2026.01		0.7487	0.384	0.3726
RAUQ 2026.01		0.6405	0.1595	0.254
MSP 2026.01		0.6341	0.4277	0.428
Semantic Entropy 2026.01		0.6121	0.3329	0.3502
Mean Token Entropy 2026.01		0.5877	0.3029	0.3514
MSP 2026.01		0.5853	0.4839	0.4847
RAUQ 2026.01		0.5713	0.1913	0.2829
Semantic Entropy 2026.01		0.5601	0.4412	0.44
MSP 2026.01		0.5573	0.4865	0.485
SAR 2026.01		0.5546	0.3599	0.3882
SAR 2026.01		0.549	0.1244	0.2687
Semantic Entropy 2026.01		0.5479	0.4825	0.481
ASK4CONF 2026.01		0.5458	0.3985	0.4005
SAR 2026.01		0.5317	0.081	0.2618
Mean Token Entropy 2026.01		0.5221	0.327	0.3596
RAUQ 2026.01		0.5069	0.2487	0.3177
RAUQ 2026.01		0.4993	0.1624	0.2838
MSP 2026.01		0.4971	0.4826	0.482
SAR 2026.01		0.4865	0.2329	0.3186
Mean Token Entropy 2026.01		0.4535	0.3168	0.3399
Semantic Entropy 2026.01		0.4453	0.276	0.3493
Mean Token Entropy 2026.01		0.3169	0.3084	0.3599