ResearchTasksMathematical and General ReasoningMathematical and General ReasoningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedGSM8k + MATH 1.0 (test)BF1694.7GSM8k Accuracy7Feb 27, 2026DeepMATH (test)BF1683.4MATH 500 Score4Feb 27, 2026