# Writing flaw detection on BenchMarker Writing - In Domain, NLP Source: [Writing flaw detection on BenchMarker Writing - In Domain, NLP]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:30:50.987Z Evaluation of model performance on detecting writing flaws within the In-Domain NLP subset of the BenchMarker dataset, measured by Accuracy, F1 Score, and Cohen's Kappa. 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 | Writing flaw detection | | Dataset (including any stated split) | BenchMarker Writing - In Domain, NLP | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 27 of 27 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. - [F1 Score](): Higher is better; unit: PERCENT. - [Cohen's Kappa](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Gemini 2.5 | 81.5 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | GPT-5 | 80.8 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Claude 4.5 | 79.4 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Gemini 2.5 | 78.8 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | SAQUET | 77.4 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Command R | 76.7 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Qwen-3 | 76 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Command R+ | 75.9 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | GPT-5 | 75 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Gemma-3 | 74.7 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Gemma-3 | 74.7 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Always Not Flawed | 74.4 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | GPT-5 | 73.5 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Qwen-3 | 73.4 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Qwen-3 | 73.4 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Claude 4.5 | 71.8 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | LLaMA-3.1 | 71.2 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Qwen-3 | 70.6 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Qwen-3 | 70.5 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Qwen-3 | 69.8 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Gemini 2.5 | 68.3 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | LLaMA-3.2 | 68.3 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | LLaMA-3.1 | 63.9 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Gemma-3 | 63.1 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Random (50/50) | 50 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | LLaMA-3.2 | 46.6 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Always Flawed | 25.6 | Not recorded | 69896a28c97a0b3e3b5dc5ac | ### Gemini 2.5 Accuracy: 81.5. Result ID: 699646735698665ec48a5616. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Variant":"Pro"}. This record does not assert independent reproduction. ### GPT-5 Accuracy: 80.8. Result ID: 699646735698665ec48a5619. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Claude 4.5 Accuracy: 79.4. Result ID: 699646735698665ec48a561b. [Reporting paper]() Recorded evaluation configuration: {"Model Variant":"Sonnet"}. This record does not assert independent reproduction. ### Gemini 2.5 Accuracy: 78.8. Result ID: 699646735698665ec48a5615. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Variant":"Flash"}. This record does not assert independent reproduction. ### SAQUET Accuracy: 77.4. Result ID: 699646735698665ec48a562b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Command R Accuracy: 76.7. Result ID: 699646735698665ec48a561c. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen-3 Accuracy: 76. Result ID: 699646735698665ec48a561f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"1.7B"}. This record does not assert independent reproduction. ### Command R+ Accuracy: 75.9. Result ID: 699646735698665ec48a561d. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-5 Accuracy: 75. Result ID: 699646735698665ec48a5618. [Reporting paper]() Recorded evaluation configuration: {"Model Variant":"Mini"}. This record does not assert independent reproduction. ### Gemma-3 Accuracy: 74.7. Result ID: 699646735698665ec48a5625. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"12B"}. This record does not assert independent reproduction. ### Gemma-3 Accuracy: 74.7. Result ID: 699646735698665ec48a5626. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"27B"}. This record does not assert independent reproduction. ### Always Not Flawed Accuracy: 74.4. Result ID: 699646735698665ec48a562d. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-5 Accuracy: 73.5. Result ID: 699646735698665ec48a5617. [Reporting paper]() Recorded evaluation configuration: {"Model Variant":"Nano"}. This record does not assert independent reproduction. ### Qwen-3 Accuracy: 73.4. Result ID: 699646735698665ec48a561e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"0.6B"}. This record does not assert independent reproduction. ### Qwen-3 Accuracy: 73.4. Result ID: 699646735698665ec48a5620. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"4B"}. This record does not assert independent reproduction. ### Claude 4.5 Accuracy: 71.8. Result ID: 699646735698665ec48a561a. [Reporting paper]() Recorded evaluation configuration: {"Model Variant":"Haiku"}. This record does not assert independent reproduction. ### LLaMA-3.1 Accuracy: 71.2. Result ID: 699646735698665ec48a5629. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### Qwen-3 Accuracy: 70.6. Result ID: 699646735698665ec48a5623. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"32B"}. This record does not assert independent reproduction. ### Qwen-3 Accuracy: 70.5. Result ID: 699646735698665ec48a5622. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"14B"}. This record does not assert independent reproduction. ### Qwen-3 Accuracy: 69.8. Result ID: 699646735698665ec48a5621. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### Gemini 2.5 Accuracy: 68.3. Result ID: 699646735698665ec48a5614. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Variant":"Lite"}. This record does not assert independent reproduction. ### LLaMA-3.2 Accuracy: 68.3. Result ID: 699646735698665ec48a5628. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"3B"}. This record does not assert independent reproduction. ### LLaMA-3.1 Accuracy: 63.9. Result ID: 699646735698665ec48a562a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"70B"}. This record does not assert independent reproduction. ### Gemma-3 Accuracy: 63.1. Result ID: 699646735698665ec48a5624. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"4B"}. This record does not assert independent reproduction. ### Random (50/50) Accuracy: 50. Result ID: 699646735698665ec48a562c. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LLaMA-3.2 Accuracy: 46.6. Result ID: 699646735698665ec48a5627. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"1B"}. This record does not assert independent reproduction. ### Always Flawed Accuracy: 25.6. Result ID: 699646735698665ec48a562e. [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.