List your company

Confidence Estimation on MedQA (test)

0.69AUROCMedConf
0.640080.653040.6660.67896Jan 22, 2026

Evaluation results

MethodLinks
MedConfType=Self-Verbalized, Model=GPT-4.12026.010.690.989
EccType=Consistency-Level, Model=GPT-4.12026.010.6670.906
CoT CEType=Self-Verbalized, Model=GPT-4.12026.010.6420.987