ResearchDatasetsAIME, GPQA, IFEval, LiveCodeBenchAIME, GPQA, IFEval, LiveCodeBenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsmulti-task average performanceAIME 2024, GPQA Diamond, IFEval, LiveCodeBench v673.86Average Score16