ResearchTasksCBT Conversation GenerationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedEmoLLM (test)Deepseek V3 671B0.91Bert Score20Feb 26, 2026CBT conversation evaluation datasetDeepseek V3 671B1.94Semantic Coherence10Feb 26, 2026