ResearchDatasetsReasoning DatasetsReasoning DatasetsFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMathematical ReasoningReasoning Datasets Average (MATH500, OlympiadBench, MinervaMath, GSM8K, MMLU)58.1Accuracy21ReasoningReasoning Datasets GSM8K, Math, AIME2024, HumanEval, LiveCodeBench87.23GSM8K9
Mathematical ReasoningReasoning Datasets Average (MATH500, OlympiadBench, MinervaMath, GSM8K, MMLU)58.1Accuracy21