ResearchTasksGeneral Language Model CapabilityFor AI assistantsMarkdownContent indexGeneral Language Model CapabilityFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMMLU, GSM8K, HumanEval, BBH CombinedVAR68.42Average Score8Mar 24, 2026