# LLM-generated text detection on WP-s Claude3 Opus Source: [LLM-generated text detection on WP-s Claude3 Opus]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:05:58.843Z Evaluation of models for detecting text generated by Claude 3 Opus on the WP-s dataset split, measured using TPR at FPR 1%. 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 | LLM-generated text detection | | Dataset (including any stated split) | WP-s Claude3 Opus | | Metric | TPR @ FPR 1% | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [TPR @ FPR 1%](): Higher is better; unit: PERCENT. ## Recorded results | Method | TPR @ FPR 1% | Result date | Report paper | | --- | --- | --- | --- | | ReMoDetect | 96 | Not recorded | 68fa759c1e209131cea68f2a | | ReMoDetect | 96 | Not recorded | 68fa759c1e209131cea68f2a | | Fast-DetectGPT | 76.7 | Not recorded | 68fa759c1e209131cea68f2a | | Fast-DetectGPT | 76.7 | Not recorded | 68fa759c1e209131cea68f2a | | NPR | 55.3 | Not recorded | 68fa759c1e209131cea68f2a | | NPR | 55.3 | Not recorded | 68fa759c1e209131cea68f2a | | Log-likelihood | 54.7 | Not recorded | 68fa759c1e209131cea68f2a | | Log-likelihood | 54.7 | Not recorded | 68fa759c1e209131cea68f2a | | DetectGPT | 37.3 | Not recorded | 68fa759c1e209131cea68f2a | | DetectGPT | 37.3 | Not recorded | 68fa759c1e209131cea68f2a | | LRR | 24 | Not recorded | 68fa759c1e209131cea68f2a | | LRR | 24 | Not recorded | 68fa759c1e209131cea68f2a | | Rank | 16.7 | Not recorded | 68fa759c1e209131cea68f2a | | Rank | 16.7 | Not recorded | 68fa759c1e209131cea68f2a | | OpenAI-Detector | 8 | Not recorded | 68fa759c1e209131cea68f2a | | OpenAI-Detector | 8 | Not recorded | 68fa759c1e209131cea68f2a | | ChatGPT-Detector | 0.7 | Not recorded | 68fa759c1e209131cea68f2a | | ChatGPT-Detector | 0.7 | Not recorded | 68fa759c1e209131cea68f2a | ### ReMoDetect TPR @ FPR 1%: 96. Result ID: 6993f2c83a6c31484919b3fc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ReMoDetect TPR @ FPR 1%: 96. Result ID: 6993f2c83a6c31484919b5d5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Fast-DetectGPT TPR @ FPR 1%: 76.7. Result ID: 6993f2c83a6c31484919b3f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Fast-DetectGPT TPR @ FPR 1%: 76.7. Result ID: 6993f2c83a6c31484919b5d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### NPR TPR @ FPR 1%: 55.3. Result ID: 6993f2c83a6c31484919b3f8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### NPR TPR @ FPR 1%: 55.3. Result ID: 6993f2c83a6c31484919b5d1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Log-likelihood TPR @ FPR 1%: 54.7. Result ID: 6993f2c83a6c31484919b3f4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Log-likelihood TPR @ FPR 1%: 54.7. Result ID: 6993f2c83a6c31484919b5cd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DetectGPT TPR @ FPR 1%: 37.3. Result ID: 6993f2c83a6c31484919b3f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DetectGPT TPR @ FPR 1%: 37.3. Result ID: 6993f2c83a6c31484919b5cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LRR TPR @ FPR 1%: 24. Result ID: 6993f2c83a6c31484919b3f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LRR TPR @ FPR 1%: 24. Result ID: 6993f2c83a6c31484919b5d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Rank TPR @ FPR 1%: 16.7. Result ID: 6993f2c83a6c31484919b3f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Rank TPR @ FPR 1%: 16.7. Result ID: 6993f2c83a6c31484919b5ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### OpenAI-Detector TPR @ FPR 1%: 8. Result ID: 6993f2c83a6c31484919b3fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### OpenAI-Detector TPR @ FPR 1%: 8. Result ID: 6993f2c83a6c31484919b5d3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ChatGPT-Detector TPR @ FPR 1%: 0.7. Result ID: 6993f2c83a6c31484919b3fb. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ChatGPT-Detector TPR @ FPR 1%: 0.7. Result ID: 6993f2c83a6c31484919b5d4. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.