ResearchTasksOpen-Ended Deep ResearchFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedDeepResearch Bench Open-EndedAUQ52.09Overall Score11Feb 26, 2026ScholarQA, HealthBench, ResearchQA, DeepResearchBench 200-question v2SearchSwarm80.2ResearchQA Accuracy9Jun 9, 2026DeepConsultDualGraph64.42Win Rate9Feb 26, 2026DeepResearchGymGemini-2.5-Pro-DeepResearch90.71Clarity9Feb 26, 2026
ScholarQA, HealthBench, ResearchQA, DeepResearchBench 200-question v2SearchSwarm80.2ResearchQA Accuracy9Jun 9, 2026