ResearchDatasetsMMLU, GSM8K, BBH, TriviaQA, NQMMLU, GSM8K, BBH, TriviaQA, NQFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsGeneral Language IntelligenceMMLU, GSM8K, BBH, TriviaQA, NQ latest available (test)83.54MMLU26