ResearchDatasetsGPQA, GSM, MATH, AIME, and IFEvalFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMulti-task Performance EvaluationGPQA-Diamond, GSM8K, MATH-500, AIME’24, and IFEval Aggregate58.72Avg Score25
Multi-task Performance EvaluationGPQA-Diamond, GSM8K, MATH-500, AIME’24, and IFEval Aggregate58.72Avg Score25