ResearchDatasetsSchool of Reward Hacks and Stanford AlpacaSchool of Reward Hacks and Stanford AlpacaFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsReward-hacking detectionSchool of Reward Hacks and Stanford Alpaca (test)100F1 Score18