ResearchTasksLong-horizon Mathematical ReasoningFor AI assistantsMarkdownContent indexLong-horizon Mathematical ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMATHQwen-2-72B-Instruct89.2Result Accuracy23May 29, 2026