ResearchTasksLLM-as-a-Judge Evaluation ConsistencyFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedRewardBenchCalibraEval83.25Kappa36Feb 26, 2026MTBenchCalibraEval71.88Kappa6Feb 26, 2026PreferenceBenchCalibraEval79.73Kappa4Feb 26, 2026