ResearchDatasetsMMLU, GSM8K, BBH, TriviaQA, NQFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsGeneral Language IntelligenceMMLU, GSM8K, BBH, TriviaQA, NQ latest available (test)83.54MMLU26