ResearchTasksPointwise evaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedBIGGENHuman-crafted (existing) Rubrics0.584Spearman Corr32Jun 1, 2026HelpSteer2Annotation-free Preference Learning for Rubric Generator0.464Spearman Correlation28Jun 1, 2026
HelpSteer2Annotation-free Preference Learning for Rubric Generator0.464Spearman Correlation28Jun 1, 2026