# AI-generated text detection on Cross-genre AIGT Overall (test) Source: [AI-generated text detection on Cross-genre AIGT Overall (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:54:01.501Z Evaluation of AI-generated text detection models using the Cross-genre AIGT Overall test set, measured by OA, AUA, ASR, and ANQ. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | AI-generated text detection | | Dataset (including any stated split) | Cross-genre AIGT Overall (test) | | Metric | OA | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [OA](): Higher is better; unit: PERCENT. - [AUA](): Higher is better; unit: PERCENT. - [ASR](): Higher is better; unit: PERCENT. - [ANQ](): Higher is better; unit: SCALAR. ## Recorded results | Method | OA | Result date | Report paper | | --- | --- | --- | --- | | SeqXGPT | 86.75 | Not recorded | 68fa73e41e209131cea5eb76 | | Flooding | 85 | Not recorded | 68fa73e41e209131cea5eb76 | | RDrop | 84 | Not recorded | 68fa73e41e209131cea5eb76 | | DeBERTa | 83.75 | Not recorded | 68fa73e41e209131cea5eb76 | | RoBERTa | 82.5 | Not recorded | 68fa73e41e209131cea5eb76 | | SCRN | 82.5 | Not recorded | 68fa73e41e209131cea5eb76 | | Log-Rank | 81 | Not recorded | 68fa73e41e209131cea5eb76 | | Log-Likelihood | 79.75 | Not recorded | 68fa73e41e209131cea5eb76 | | RanMASK | 77 | Not recorded | 68fa73e41e209131cea5eb76 | | BERT | 76.25 | Not recorded | 68fa73e41e209131cea5eb76 | | Entropy | 75.75 | Not recorded | 68fa73e41e209131cea5eb76 | | ChatGPT-Detector | 75.75 | Not recorded | 68fa73e41e209131cea5eb76 | | RMLM | 75.25 | Not recorded | 68fa73e41e209131cea5eb76 | | GLTR | 74 | Not recorded | 68fa73e41e209131cea5eb76 | ### SeqXGPT OA: 86.75. Result ID: 699311603a6c3148491377ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Adversarial attack":"PWWS"}. This record does not assert independent reproduction. ### Flooding OA: 85. Result ID: 699311603a6c3148491377b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Adversarial attack":"PWWS"}. This record does not assert independent reproduction. ### RDrop OA: 84. Result ID: 699311603a6c3148491377b2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Adversarial attack":"PWWS"}. This record does not assert independent reproduction. ### DeBERTa OA: 83.75. Result ID: 699311603a6c3148491377af. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Adversarial attack":"PWWS"}. This record does not assert independent reproduction. ### RoBERTa OA: 82.5. Result ID: 699311603a6c3148491377ae. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Adversarial attack":"PWWS"}. This record does not assert independent reproduction. ### SCRN OA: 82.5. Result ID: 699311603a6c3148491377b5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Adversarial attack":"PWWS"}. This record does not assert independent reproduction. ### Log-Rank OA: 81. Result ID: 699311603a6c3148491377a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Adversarial attack":"PWWS"}. This record does not assert independent reproduction. ### Log-Likelihood OA: 79.75. Result ID: 699311603a6c3148491377a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Adversarial attack":"PWWS"}. This record does not assert independent reproduction. ### RanMASK OA: 77. Result ID: 699311603a6c3148491377b3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Adversarial attack":"PWWS"}. This record does not assert independent reproduction. ### BERT OA: 76.25. Result ID: 699311603a6c3148491377ad. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Adversarial attack":"PWWS"}. This record does not assert independent reproduction. ### Entropy OA: 75.75. Result ID: 699311603a6c3148491377aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Adversarial attack":"PWWS"}. This record does not assert independent reproduction. ### ChatGPT-Detector OA: 75.75. Result ID: 699311603a6c3148491377b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Adversarial attack":"PWWS"}. This record does not assert independent reproduction. ### RMLM OA: 75.25. Result ID: 699311603a6c3148491377b4. [Reporting paper]() Recorded evaluation configuration: {"Adversarial attack":"PWWS"}. This record does not assert independent reproduction. ### GLTR OA: 74. Result ID: 699311603a6c3148491377ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Adversarial attack":"PWWS"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.