ResearchTasksReasoning AlignmentReasoning AlignmentFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMedThink D2 N=499 (test)M3-GDP95.3HYB Score5Jun 9, 2026MedQA D1 N=500 (test)M3-GDP95.2HYB Score5Jun 9, 2026