ResearchDatasetsOlympiadsOlympiadsFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMathematical ReasoningOlympiads70.22Pass@119Capability ElicitationOlympiads (test)88Elicitation Rate (U_final / U_benign)6