ResearchTasksAgentic TasksFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedTau2 RetailGPT-5.1 (Medium)78.1Score10Feb 26, 2026Tau2 AirlineGPT-5.1 (Medium)64Score10Feb 26, 2026AgentQwen3.6-Plus99.1MTP Acceptance Rate5Jun 11, 2026FramesDebate70.45Accuracy5Mar 10, 2026BrowseCompMAS-ZERO9.45Accuracy5Mar 10, 2026