ResearchTasksRole-Playing Evaluation (Conversational-Naturalness)For AI assistantsMarkdownContent indexRole-Playing Evaluation (Conversational-Naturalness)FollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedCNEBM65Win Rate9May 7, 2026