ResearchTasksDeepSearch Question AnsweringFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedHumanity's Last ExamAPPO14.7NS Score22Jun 11, 2026XbenchAPPO34Average Score21Jun 11, 2026General AI AssistantAPPO61.5Score (Lv.1)21Jun 11, 2026