ResearchTasksCommonsense Reasoning and Knowledge Question AnsweringFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedGeneral Ability Suite (ARC, HellaSwag, PIQA, BoolQ, WinoGrande, COPA, OBQA, SciQ) various (test)FEM-SM36.4ARC-C Accuracy19Feb 27, 2026General Ability Suite ARC, HellaSwag, PIQA, BoolQ, WinoGrande, COPA, OBQA, SciQ——ARC-C AccuracyCommonsense Reasoning and Knowledge QA on ARC, HellaSwag, PIQA, BoolQ, WinoGrande, COPA, OBQA, SciQ performance trend0Feb 26, 2026
General Ability Suite (ARC, HellaSwag, PIQA, BoolQ, WinoGrande, COPA, OBQA, SciQ) various (test)FEM-SM36.4ARC-C Accuracy19Feb 27, 2026
General Ability Suite ARC, HellaSwag, PIQA, BoolQ, WinoGrande, COPA, OBQA, SciQ——ARC-C AccuracyCommonsense Reasoning and Knowledge QA on ARC, HellaSwag, PIQA, BoolQ, WinoGrande, COPA, OBQA, SciQ performance trend0Feb 26, 2026