ResearchDatasetsClinicianClinicianFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsLLM-as-a-judge alignmentClinician Spine cohort (val R1)78.43-Way Agreement5Blinded A/B preferenceClinician Obesity cohort R1 (val)82.2Win Percentage3