ResearchDatasetsAggregate of BenchmarksAggregate of BenchmarksFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsReward ModelingAggregate of 7 benchmarks (HelpSteer3, Reward Bench V2, SCAN-HPD, HREF, LitBench, WQ_Arena, WPB)74.56Overall Accuracy45
Reward ModelingAggregate of 7 benchmarks (HelpSteer3, Reward Bench V2, SCAN-HPD, HREF, LitBench, WQ_Arena, WPB)74.56Overall Accuracy45