ResearchDatasetsMMLU, ARC-Challenge, and CommonsenseQAMMLU, ARC-Challenge, and CommonsenseQAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsGeneral Language ModelingMMLU, ARC-Challenge, and CommonsenseQA Aggregate64.77Average Score24