ResearchTasksNLG EvaluationNLG EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedUSRGPT-4o0.82Spearman Correlation10Feb 26, 2026SumPubMedGPT-4o0.3Spearman Correlation10Feb 26, 2026HelpSteer2Qwen0.65Spearman Correlation10Feb 26, 2026