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

Metric Correlation with Human Judgment on CT-RATE

0.622Pearson Correlation

CT-FineBench

0.090560.228530.36650.50447Apr 27, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
0.6220.3780.49
2026.04
0.5210.320.434
2026.04
0.4950.3530.479
2026.04
0.3490.2620.342
2026.04
0.170.1150.158
2026.04
0.1630.1370.171
2026.04
0.1110.0630.088