ResearchDatasetsMATH, GPQA, MMLU, GSM8K, ARCMATH, GPQA, MMLU, GSM8K, ARCFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsGeneral ReasoningMATH-500, GPQA-D, MMLU-P, GSM8K, ARC-C Aggregate85.41Average Score18