ResearchTasksGenerative Language Modeling and Problem SolvingGenerative Language Modeling and Problem SolvingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedGEN suite IFEval, AIME25, GSM8K, GPQA, HumanEval, LCBOriginal90.4IFEval Score5Apr 7, 2026