ResearchDatasetsMultiArithMultiArithFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMathematical ReasoningMultiArith OOD100Base Accuracy (CA)2Arithmetic ReasoningMultiArith78.7Accuracy (format-specific prompt)2Mathematical ReasoningMultiArith96.67Initial Accuracy1Mathematical ReasoningMultiArith93.4Detection Rate1PreviousPage 2 of 2Next