ResearchDatasetsORZ57KORZ57KFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMathematical ReasoningORZ57K evaluation suite MATH, Minerva, Olympiad Bench, AMC, AIME (test)37.1Final Test Accuracy2
Mathematical ReasoningORZ57K evaluation suite MATH, Minerva, Olympiad Bench, AMC, AIME (test)37.1Final Test Accuracy2