# AI-generated text detection on M4GT-Bench OUTFOX (test) Source: [AI-generated text detection on M4GT-Bench OUTFOX (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:58:43.500Z Evaluation of AI-generated text detection models on the OUTFOX test split of the M4GT-Bench dataset, reporting Precision, Recall, F1, and Accuracy. 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) | M4GT-Bench OUTFOX (test) | | Metric | Precision | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. - [F1 Score](): Higher is better; unit: PERCENT. - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Precision | Result date | Report paper | | --- | --- | --- | --- | | RoBERTa | 71.71 | Not recorded | 6995478c09c33900fcd6d5da | | DependencyAI | 54.6 | Not recorded | 6995478c09c33900fcd6d5da | | XLM-R | 51.94 | Not recorded | 6995478c09c33900fcd6d5da | | Stylistic-SVM | 48.28 | Not recorded | 6995478c09c33900fcd6d5da | | NELA-SVM | 35.05 | Not recorded | 6995478c09c33900fcd6d5da | | GLTR-LR | 29.68 | Not recorded | 6995478c09c33900fcd6d5da | | GLTR-SVM | 26.93 | Not recorded | 6995478c09c33900fcd6d5da | ### RoBERTa Precision: 71.71. Result ID: 699ad87f5698665ec467eba0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"Leave-one-domain-out"}. This record does not assert independent reproduction. ### DependencyAI Precision: 54.6. Result ID: 699ad87f5698665ec467eba6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"Leave-one-domain-out"}. This record does not assert independent reproduction. ### XLM-R Precision: 51.94. Result ID: 699ad87f5698665ec467eba1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"Leave-one-domain-out"}. This record does not assert independent reproduction. ### Stylistic-SVM Precision: 48.28. Result ID: 699ad87f5698665ec467eba4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"Leave-one-domain-out"}. This record does not assert independent reproduction. ### NELA-SVM Precision: 35.05. Result ID: 699ad87f5698665ec467eba5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"Leave-one-domain-out"}. This record does not assert independent reproduction. ### GLTR-LR Precision: 29.68. Result ID: 699ad87f5698665ec467eba2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"Leave-one-domain-out"}. This record does not assert independent reproduction. ### GLTR-SVM Precision: 26.93. Result ID: 699ad87f5698665ec467eba3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"Leave-one-domain-out"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.