ResearchTasksGeneral AI Assistants EvaluationGeneral AI Assistants EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedGAIA n=50GPT-5 search0.594Accuracy7Feb 26, 2026GAIA text-103Tongyi-DR70.9Accuracy3Mar 10, 2026