ResearchTasksReference-free Conversation EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedCRSArena-Eval KGFACE0.766Pearson Correlation (r)44Apr 7, 2026CRSArena-Eval RDFACE0.712Pearson Correlation (r)44Apr 7, 2026