ResearchTasksRole-Play EvaluationRole-Play EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedCoSERClaude-4.5-Opus62.43Avg Score48Jun 26, 2026Minimax Role-Play BenchMiniMax-M2-her84.65Average Score17Feb 26, 2026