ResearchTasksMulti-Turn Tool-Integrated Reasoning (TIR)Multi-Turn Tool-Integrated Reasoning (TIR)FollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMATH500OTB84.69Peak avg@32 Score6Feb 26, 2026AMC23OTB79.45Peak avg@32 Score6Feb 26, 2026AIME24OTB41.46Peak avg@32 score6Feb 26, 2026AIME25OTB28.13Peak avg@32 Score6Feb 26, 2026