ResearchTasksMath and Text ReasoningMath and Text ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedOlympiad BenchUCPO73.67PAQ14Feb 26, 2026MinervaPrompt-UC0.494PAQ14Feb 26, 2026MATH 500UCPO97.28PAQ14Feb 26, 2026AMCGRPO-UC95.06PAQ14Feb 26, 2026AIME 24UCPO86.11PAQ14Feb 26, 2026