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

Patient-level agreement on Closed-Weight (CW) benchmark cohort

0.831Quadratic Weighted Kappa (kw)

Assessors (A1, A2) vs consolidated output

0.61260.66930.7260.7827Jul 6, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.07
0.831
2026.07
0.773
2026.07
0.702
2026.07
0.671
2026.07
0.621