ResearchTasksLanguage understanding and knowledgeLanguage understanding and knowledgeFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedKnowledge Evaluation Suite MMLU & C-EVALQwen2.5-7B + Inf-1M72.2MMLU16Feb 26, 2026MMLU-ProEvo 8B57.2Accuracy16Mar 10, 2026