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

Confidence Estimation on Chatbot Arena

0.3524Rank Correlation (RK)

Verbalized Confidence

0.2202160.2545330.288850.323167May 14, 2026
Updated 16d ago

Evaluation Results

MethodLinks
2026.05
0.352464.71
2026.05
0.342865.47
2026.05
0.340766.15
2026.05
0.337665.91
2026.05
0.295669.13
2026.05
0.281272.04
2026.05
0.270872.93
2026.05
0.269773.09
2026.05
0.265872.01
2026.05
0.257474.33
2026.05
0.225377.49