ResearchTasksMulti-turn role-playFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedICLREmoLLM96.2Success Rate (SR)12Mar 18, 2026MedDEmoLLM95.3Success Rate (SR)12Mar 18, 2026MSDEmoLLM83.2Success Rate (SR)12Mar 18, 2026EDEmoLLM92.1Success Rate (SR)12Mar 18, 2026