ResearchDatasetsMMLU, ARC-C, GSM8K, OpenBookQA, MedQAMMLU, ARC-C, GSM8K, OpenBookQA, MedQAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsTask-Oriented Multi-Agent CommunicationMMLU, ARC-C, GSM8K, OpenBookQA, MedQA Average (test)79.03Accuracy15
Task-Oriented Multi-Agent CommunicationMMLU, ARC-C, GSM8K, OpenBookQA, MedQA Average (test)79.03Accuracy15