ResearchTasksReasoning (Aggregated)Reasoning (Aggregated)FollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAverage Math500 AIME24 AIME25 GPQALatent-GRPO41.72Pass@15May 1, 2026