ResearchTasksDialogue AnnotationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedEedi (test)Sonnet 4.6 (RAG_FINETUNED_UTT)0.743Cohen's Kappa12Apr 6, 2026TalkMoves (test)Sonnet 4.6 (RAG_FINETUNED_UTT)58Cohen's Kappa12Apr 6, 2026