ResearchDatasetsTask AverageTask AverageFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsReinforcement LearningTask Average HC, Ant, Hop, Walk v57,282Mean Episodic Return17Mathematical ReasoningTask-average AIME24, AIME25, AMC23, MATH500, Minerva (test)40.7Pass@18