ResearchTasksMulti-turn Clinical SimulationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMIMIC-IV (test)Meissa84.4Accuracy6Mar 11, 2026MedQA Extension (test)Gemini-3-flash92.3Accuracy6Mar 11, 2026NEJM Extension OOD (test)Gemini-3-flash33.3Accuracy6Mar 11, 2026NEJM OOD (test)Meissa46.7Accuracy6Mar 11, 2026