ResearchTasksLong ReasoningLong ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedGPQAFreeKV86Pass@k24Mar 4, 2026AIME 24Full86.67Pass@k24Mar 4, 2026MATH500Full78Pass@k Rate24Mar 4, 2026