ResearchTasksMulti-Agent CollaborationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedSRDDChatDev (Llama)76.35Completeness4Apr 6, 2026MABENCH (benign)GPT-5.593.3BSR Finance CO3Jun 12, 2026