ResearchTasksConversationalFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedBS-BenchQwen3.5-9B70Score6Jun 1, 2026MixEvalQwen3.5-9B76Score6Jun 1, 2026JetBrains pairwiseMellum 2 (RL)69.5Score6Jun 1, 2026BIRD-InteractDIA55.7Task Success Rate4Jun 18, 2026