ResearchDatasetsGPT-5-proFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsText DetectabilityGPT-5-pro Experiment 2 averaged over n ∈ {3, ..., 10} 2025-10-0699BERT Score5Agreement analysis of causal graph metricsGPT-5-pro Experiment 3 2025-10-060.929Pearson Correlation Coefficient4
Agreement analysis of causal graph metricsGPT-5-pro Experiment 3 2025-10-060.929Pearson Correlation Coefficient4