ResearchTasksMulti-agent Planning and CompositionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedTaskBench Multimedia APIs (test)AutoMAS91.12Precision1May 6, 2026TaskBench Hugging Face APIs (test)AutoMAS74.97Precision1May 6, 2026TaskBench Dailylife APIs (test)AutoMAS95.01Precision1May 6, 2026