ResearchTasksAgentic Question AnsweringFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedAMABenchDCI-Lite32.2A-ALF Score10Jun 4, 2026AirQAGemini-2.5-Pro51.85SGL Score7Mar 31, 2026BrowseComp-Plus document corpusGPT-5.274.7Recall4Jun 23, 2026