ResearchTasksBest-of-N Reward EvaluationFor AI assistantsMarkdownContent indexBest-of-N Reward EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedUltraFeedback core250TEA24.323Reward Score18May 12, 2026