ResearchDatasetsPE-FDPE-FDFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsPreference EstimationPE-FD=6 (test)56.91Average Outcome Reward9Preference EstimationPE-FD=8 (test)61.28Average Outcome Reward9