ResearchTasksDisagreement DetectionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedCEFR-SP Qwen3 labels Rater Amost20.593ROC-AUC14May 13, 2026CEFR-SP GPT-OSS-120B (Rater B)logprob label (B)55.8ROC-AUC14May 13, 2026CEFR-SP (Rater B)logprob label0.539ROC-AUC14May 13, 2026