ResearchDatasetsCommonsense BenchmarksFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsCommonsense ReasoningCommonsense Benchmarks (ARC-e, ARC-c, OBQA, PIQA, Hella) zero-shot60.34Average Accuracy7
Commonsense ReasoningCommonsense Benchmarks (ARC-e, ARC-c, OBQA, PIQA, Hella) zero-shot60.34Average Accuracy7