ResearchTasksCommonsense QAFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedCommonsense QA (ARC-E, ARC-C, HellaS, WinoG, BoolQ, OBQA, RTE, CoPa, Race) zero-shotDense81.19ARC-Easy Accuracy57May 18, 2026HellaSwagLlama 3-8B79.1Accuracy19Jun 18, 2026
Commonsense QA (ARC-E, ARC-C, HellaS, WinoG, BoolQ, OBQA, RTE, CoPa, Race) zero-shotDense81.19ARC-Easy Accuracy57May 18, 2026