ResearchDatasetsScholarQA, HealthBench, ResearchQA, DeepResearchBenchScholarQA, HealthBench, ResearchQA, DeepResearchBenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsOpen-ended deep researchScholarQA, HealthBench, ResearchQA, DeepResearchBench 200-question v280.2ResearchQA Accuracy9
Open-ended deep researchScholarQA, HealthBench, ResearchQA, DeepResearchBench 200-question v280.2ResearchQA Accuracy9