ResearchTasksMathMathFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMath MediumGPT-20.006Baseline Score1Apr 10, 2026Math EasyGPT-22.56Baseline Score1Apr 10, 2026Math 1000 samples (test)Base Model75Accuracy1Feb 26, 2026PreviousPage 5 of 5Next