ResearchTasksDomain-specific agentic reasoningDomain-specific agentic reasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedTauBench V3Kimi-K2.685.8Airline Accuracy7Jun 16, 2026τ³ BankingFugu21.7Score5Jun 23, 2026