ResearchDatasetsFAMMAFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsNon-Arithmetic ReasoningFAMMA Non-Arithmetic (test)58.74Accuracy8Arithmetic ReasoningFAMMA Arithmetic (test)70.66Accuracy8