ResearchDatasetsReasoning and Code Generation SuiteReasoning and Code Generation SuiteFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsReasoning and Code GenerationReasoning and Code Generation Suite (MATH, GSM8K, MBPP, TheoremQA, BBH) (test)54.38MATH Accuracy6
Reasoning and Code GenerationReasoning and Code Generation Suite (MATH, GSM8K, MBPP, TheoremQA, BBH) (test)54.38MATH Accuracy6