ResearchDatasetsGSM8K and MATHGSM8K and MATHFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMathematical ReasoningGSM8K and MATH78.4GSM8K Score38Mathematical ReasoningGSM8K and MATH500 Aggregate86.02Avg Accuracy9Arithmetic ReasoningGSM8K and MATH Average43.4Average Accuracy7