ResearchDatasetsT-MathT-MathFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsAdvanced ReasoningT-Math63.4Accuracy11Mathematical ReasoningT-Math (full)73Pass@16Mathematical problem solvingT-Math 4 (test)2.25Speedup1