ResearchDatasetsGSM8K, Live Code Bench, and Dolly15kGSM8K, Live Code Bench, and Dolly15kFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsData GenerationGSM8K, Live Code Bench, and Dolly15k 53K labels8.5Generation Time (hours)2