ResearchDatasetsLiveCodeBench, GPQA-Diamond, MMLULiveCodeBench, GPQA-Diamond, MMLUFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsOut-of-domain GeneralizationLiveCodeBench, GPQA-Diamond, MMLU Average55.39IPT14