ResearchTasksMultitask Language UnderstandingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMMLU ProQwen3.5-2B66.5Score2Jun 4, 2026MMMLUHATified59.7Normalized Log Accuracy2Mar 18, 2026Page 4 of 4PreviousNext