ResearchTasksGrade-school reasoningGrade-school reasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedGSM8K AugCoT-SFT59.7Accuracy15Jun 30, 2026GSM HardSFT-CoT53.4Pass@1 Success Rate9Feb 26, 2026