ResearchTasksDeep searchFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedxBench DeepSearch-10Nanbeige4.1-3B39Score8Feb 26, 2026Xbench DeepSearchQuarkMedSearch81Score7Apr 15, 2026Average webw., hle, gaiaQwen3-8B + TEPOdense9.87Accuracy7Feb 26, 2026xbench DeepSearch (leaderboard)——Primary metric0Feb 26, 2026webw.——Primary metric0Feb 26, 2026Page 2 of 2PreviousNext