ResearchTasksPatient-level agreementFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedOpen-Weight (OW) cohort (full)Gemma vs Qwen0.953Quadratic Weighted Kappa (kw)9Jul 7, 2026Closed-Weight (CW) benchmark cohortAssessors (A1, A2) vs consolidated output0.831Quadratic Weighted Kappa (kw)5Jul 7, 2026
Closed-Weight (CW) benchmark cohortAssessors (A1, A2) vs consolidated output0.831Quadratic Weighted Kappa (kw)5Jul 7, 2026