LLM-generated text detection
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
98.7AUROC
9
Feb 26, 2026
0.964AUROC
9
Feb 26, 2026
99.8AUROC
9
Feb 26, 2026
99.8AUROC
9
Feb 26, 2026
0.963AUROC
9
Feb 26, 2026
99.35GPT-4 Performance Score
8
Feb 26, 2026
0.868ROC AUC
8
Feb 26, 2026
0.891ROC AUC
8
Feb 26, 2026
0.893ROC AUC
8
Feb 26, 2026
0.917ROC AUC
8
Feb 26, 2026
0.907ROC AUC
8
Feb 26, 2026
89.12GPT-4 Score
8
Feb 26, 2026
99.94GPT-4 Score
8
Feb 26, 2026
1ROC AUC
8
Feb 26, 2026
99.92ROC AUC
8
Feb 26, 2026
1ROC AUC
8
Feb 26, 2026
100ROC AUC
8
Feb 26, 2026
100ROC AUC
8
Feb 26, 2026
100ROC AUC
8
Feb 26, 2026
100ROC AUC
8
Feb 26, 2026
0.746AUROC
8
Feb 26, 2026
0.805AUROC
8
Feb 26, 2026
0.823AUROC
8
Feb 26, 2026
80.99AUROC
8
Feb 26, 2026
0.975AUROC
8
Feb 26, 2026