ResearchTasksMassively Multitask Language UnderstandingMassively Multitask Language UnderstandingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAfriMMLU (test)Llama-3.1-70B-Instruct34.2Accuracy (Xho)7Mar 24, 2026MMLU-proGPT-543Performance5Feb 26, 2026