ResearchTasksMulti-turn Dialogue ReasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMuTual (test)FOCAL REASONER84.6MRR19Jun 4, 2026MultiChallengeTableLong32.97Accuracy4Mar 24, 2026MuTual+PathReasoner81.49R@13Feb 26, 2026MuTualPathReasoner88.93R@13Feb 26, 2026Dream (val)PathReasoner85.05Accuracy3Feb 26, 2026