ResearchTasksAgent ExecutionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast Updatedtau-Bench (test)Gemini-2.5 Pro59Execution Accuracy8Mar 24, 2026CRMArena (test)Gemini-2.5 Pro49Execution Accuracy8Mar 24, 2026EnterpriseBench (test)Claude-3.5-Sonnet55Execution Accuracy8Mar 24, 2026EnterpriseArena (test)Gemini-2.5 Pro71Execution Accuracy8Mar 24, 2026