ResearchTasksMetric-Human Agreement EvaluationMetric-Human Agreement EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedHuman-agreement n=150 (test)Spider2 M60.502Delta-Kappa (Hybrid-EX vs Baseline)7Jun 2, 2026