Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Confidence Calibration on SimpleQA (test)

6.8ECE

HTC

6.5888.0199.4510.881Jan 22, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
6.81475.2
2026.01
7.117.869.8
2026.01
7.51572.7
2026.01
7.718.169.1
2026.01
10.118.669.9
2026.01
1119.369.2
12.119.665.5