ResearchTasksMedical EvaluationMedical EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedHealthBench-Hard (test)HuatuoGPT-o1-7B8.9Accuracy5May 28, 2026MediEvalGPT-4o49.3Accuracy2Feb 26, 2026