ResearchTasksFeedback Evaluation AlignmentFeedback Evaluation AlignmentFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMT BenchTRACT0.494Kendall's Tau11Feb 26, 2026Vicuna BenchTRACT0.423Kendall's Tau6Feb 26, 2026FLASKPrometheus-2-7B0.405Kendall's Tau6Feb 26, 2026Feedback BenchMistral-7B-Instruct + CE (GPT-4 Score)82.4Kendall's Tau6Feb 26, 2026