# AI-Generated Text detection on SeqXGPT-Bench cross-genre Source: [AI-Generated Text detection on SeqXGPT-Bench cross-genre]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:58:47.732Z Evaluation of AI-generated text detection models using the SeqXGPT-Bench dataset, focusing on cross-genre text samples. 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) | SeqXGPT-Bench cross-genre | | Metric | Precision (AI) | | 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 - [Precision (AI)](): Higher is better; unit: PERCENT. - [Recall (AI)](): Higher is better; unit: PERCENT. - [Precision (Human)](): Higher is better; unit: PERCENT. - [Recall (Human)](): Higher is better; unit: PERCENT. - [F1 Score (Overall)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Precision (AI) | Result date | Report paper | | --- | --- | --- | --- | | GLTR | 96.36 | Not recorded | 68fa73e41e209131cea5eb76 | | Log-Rank | 95.58 | Not recorded | 68fa73e41e209131cea5eb76 | | Log-Likelihood | 92.6 | Not recorded | 68fa73e41e209131cea5eb76 | | RMLM | 89.9 | Not recorded | 68fa73e41e209131cea5eb76 | | RanMASK | 89.84 | Not recorded | 68fa73e41e209131cea5eb76 | | Bert | 89.82 | Not recorded | 68fa73e41e209131cea5eb76 | | ChatGPT-Detector | 86.46 | Not recorded | 68fa73e41e209131cea5eb76 | | SeqXGPT | 86.32 | Not recorded | 68fa73e41e209131cea5eb76 | | Flooding | 83.75 | Not recorded | 68fa73e41e209131cea5eb76 | | Roberta | 83.07 | Not recorded | 68fa73e41e209131cea5eb76 | | Deberta | 79.51 | Not recorded | 68fa73e41e209131cea5eb76 | | RDrop | 77.05 | Not recorded | 68fa73e41e209131cea5eb76 | | SCRN | 73.61 | Not recorded | 68fa73e41e209131cea5eb76 | | Entropy | 72.45 | Not recorded | 68fa73e41e209131cea5eb76 | ### GLTR Precision (AI): 96.36. Result ID: 699311603a6c314849137771. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cross-genre":true,"Attack":"None"}. This record does not assert independent reproduction. ### Log-Rank Precision (AI): 95.58. Result ID: 699311603a6c31484913776f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cross-genre":true,"Attack":"None"}. This record does not assert independent reproduction. ### Log-Likelihood Precision (AI): 92.6. Result ID: 699311603a6c31484913776e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cross-genre":true,"Attack":"None"}. This record does not assert independent reproduction. ### RMLM Precision (AI): 89.9. Result ID: 699311603a6c31484913777a. [Reporting paper]() Recorded evaluation configuration: {"Cross-genre":true,"Attack":"None"}. This record does not assert independent reproduction. ### RanMASK Precision (AI): 89.84. Result ID: 699311603a6c314849137779. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cross-genre":true,"Attack":"None"}. This record does not assert independent reproduction. ### Bert Precision (AI): 89.82. Result ID: 699311603a6c314849137773. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Cross-genre":true,"Attack":"None"}. This record does not assert independent reproduction. ### ChatGPT-Detector Precision (AI): 86.46. Result ID: 699311603a6c314849137776. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cross-genre":true,"Attack":"None"}. This record does not assert independent reproduction. ### SeqXGPT Precision (AI): 86.32. Result ID: 699311603a6c314849137772. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cross-genre":true,"Attack":"None"}. This record does not assert independent reproduction. ### Flooding Precision (AI): 83.75. Result ID: 699311603a6c314849137777. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cross-genre":true,"Attack":"None"}. This record does not assert independent reproduction. ### Roberta Precision (AI): 83.07. Result ID: 699311603a6c314849137774. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Cross-genre":true,"Attack":"None"}. This record does not assert independent reproduction. ### Deberta Precision (AI): 79.51. Result ID: 699311603a6c314849137775. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Cross-genre":true,"Attack":"None"}. This record does not assert independent reproduction. ### RDrop Precision (AI): 77.05. Result ID: 699311603a6c314849137778. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Cross-genre":true,"Attack":"None"}. This record does not assert independent reproduction. ### SCRN Precision (AI): 73.61. Result ID: 699311603a6c31484913777b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Cross-genre":true,"Attack":"None"}. This record does not assert independent reproduction. ### Entropy Precision (AI): 72.45. Result ID: 699311603a6c314849137770. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Cross-genre":true,"Attack":"None"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.