Sentence-level AI-generated text detection
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
94Average F1 Score
6
Jun 18, 2026
91.5Macro-F1
6
Jun 18, 2026
94.8Macro-F1
6
Jun 18, 2026
94.2Macro-F1
6
Jun 18, 2026
95.6Macro-F1
6
Jun 18, 2026
81.3Macro F1 Score (Pub->XD)
4
Jun 18, 2026
85.6Macro F1 (PD->PK)
4
Jun 18, 2026