ResearchDatasetsClinician ValidationFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsLLM-as-a-judge alignmentClinician Validation Obesity cohort (R1)85.73-Way Agreement5Blinded A/B preferenceClinician Validation Spine cohort (R1)94.2Win Rate3