ResearchTasksCommonsense Reasoning and KnowledgeCommonsense Reasoning and KnowledgeFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedlm-eval ARC-C, BoolQ, Lambada, PIQA, WinograndeFP1653.58ARC-C Accuracy8Mar 31, 2026