ResearchTasksMulti-ability model mergingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedWizardMath (Math), Tulu-2 (Science), and WizardLM (Code) evaluation suites (test)Task Arithmetic68.4Math Accuracy7Feb 26, 2026
WizardMath (Math), Tulu-2 (Science), and WizardLM (Code) evaluation suites (test)Task Arithmetic68.4Math Accuracy7Feb 26, 2026