ResearchDatasetsConversational Evaluation SuiteConversational Evaluation SuiteFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsPairwise Preference EvaluationConversational Evaluation Suite AI companionship and Role-play (test)95.5Win Rate13
Pairwise Preference EvaluationConversational Evaluation Suite AI companionship and Role-play (test)95.5Win Rate13