ResearchDatasetsProMedical-BenchProMedical-BenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMedical LLM AlignmentProMedical-Bench91.5Pointwise Proficiency (S1)11Safety Veto DetectionProMedical-Bench Safety dimension (S3)91.5Precision10