ResearchTasksEventual-success trackingEventual-success trackingFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMATH-500 Level 5SBBT26.1AUROC3May 28, 2026RIMO-NSBBT0.159Brier Score2May 28, 2026AIME 2025SBBT0AUROC1May 28, 2026GSM8KSBBT11.1AUROC1May 28, 2026MATH-500 Level 1SBBT0.074Brier Score1May 28, 2026