ResearchDatasetsMMLU, GSM8K, HumanEval, BBHFor AI assistantsMarkdownContent indexMMLU, GSM8K, HumanEval, BBHFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsGeneral Language Model CapabilityMMLU, GSM8K, HumanEval, BBH Combined68.42Average Score8