ResearchTasksTranslator-call mode selectionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMMLU ProX LiteLUAR76.45Macro F112Jun 2, 2026PolyMath HighLUAR73.74Macro F112Jun 2, 2026PolyMath MediumLUAR75.22Macro F112Jun 2, 2026PolyMath LowLUAR87.64Macro F1 Score12Jun 2, 2026