Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Patient-level agreement on Closed-Weight (CW) benchmark cohort
Loading...
0.831
Quadratic Weighted Kappa (kw)
Assessors (A1, A2) vs consolidated output
0.6126
0.6693
0.726
0.7827
Jul 6, 2026
Quadratic Weighted Kappa (kw)
Updated 18d ago
Evaluation Results
Method
Method
Links
Quadratic Weighted Kappa (kw)
Assessors (A1, A2) vs consolidated output
Context=CW internal pi...
2026.07
0.831
CW MOSAIC
Comparison Reference=O...
2026.07
0.773
CW MOSAIC
Comparison Reference=C...
2026.07
0.702
CW MOSAIC
Comparison Reference=Y...
2026.07
0.671
GPT-4o vs DeepSeek
Context=CW inter-asses...
2026.07
0.621
Feedback
Search any
task
Search any
task