ResearchTasksAlpacaEval 2.0AlpacaEval 2.0FollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedUltraFeedbackSSPO30LC42Feb 26, 2026DSP BusinessSSPO17.9LC28Feb 26, 2026UltraMedical PreferenceSSPO17.7LC28Feb 26, 2026