ResearchTasksRole-playing agent evaluationFor AI assistantsMarkdownContent indexRole-playing agent evaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedLLM Court 5 legal scenarios 1.0 (test)Llama-3.1-8B92.5QS d BRF Score7Apr 14, 2026PersonaGymGPT-4.14.13Action Justification4May 19, 2026