ResearchTasksMulti-turn InteractionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedAudio Multi-Challenge Text ModalityGemini-3-Flash-Preview49.21Average Pass Rate (APR)13Mar 27, 2026Audio Multi-Challenge Speech ModalityGemini-3-Flash-Preview42.7Average Pass Rate (APR)10Mar 27, 2026ALFWorldQwen2.5-72B-CodeGym82.8Accuracy10Mar 18, 2026