# Text Generation on Wikipedia Biographies (test) Source: [Text Generation on Wikipedia Biographies (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:40:40.787Z Evaluation of text generation performance on the test split of the Wikipedia Biographies dataset, measured using δ-P, δ-R, and δ-PR metrics. 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 | Text Generation | | Dataset (including any stated split) | Wikipedia Biographies (test) | | Metric | Delta Precision (δ-P) | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [Delta Precision (δ-P)](): Higher is better; unit: SCALAR. - [Delta Recall (δ-R)](): Higher is better; unit: SCALAR. - [Delta Precision-Recall (δ-PR)](): Higher is better; unit: SCALAR. ## Recorded results | Method | Delta Precision (δ-P) | Result date | Report paper | | --- | --- | --- | --- | | Pretrained | 25.37 | Not recorded | 698abc31c97a0b3e3b5de48e | | Conditional | 24.31 | Not recorded | 698abc31c97a0b3e3b5de48e | | Conditional | 24.16 | Not recorded | 698abc31c97a0b3e3b5de48e | | Conditional | 23.17 | Not recorded | 698abc31c97a0b3e3b5de48e | | RW | 22.88 | Not recorded | 698abc31c97a0b3e3b5de48e | | Pretrained | 22.3 | Not recorded | 698abc31c97a0b3e3b5de48e | | MinMax | 22.27 | Not recorded | 698abc31c97a0b3e3b5de48e | | MinMax | 21.65 | Not recorded | 698abc31c97a0b3e3b5de48e | | RW | 21.29 | Not recorded | 698abc31c97a0b3e3b5de48e | | Pretrained | 21.18 | Not recorded | 698abc31c97a0b3e3b5de48e | | RW | 20.91 | Not recorded | 698abc31c97a0b3e3b5de48e | | Pretrained | 20.9 | Not recorded | 698abc31c97a0b3e3b5de48e | | RW | 19.67 | Not recorded | 698abc31c97a0b3e3b5de48e | | MinMax | 19.55 | Not recorded | 698abc31c97a0b3e3b5de48e | | MinMax | 19.13 | Not recorded | 698abc31c97a0b3e3b5de48e | | Conditional | 19.09 | Not recorded | 698abc31c97a0b3e3b5de48e | ### Pretrained Delta Precision (δ-P): 25.37. Result ID: 6998d5a85698665ec4396e33. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA-3.2-Chat 3B"}. This record does not assert independent reproduction. ### Conditional Delta Precision (δ-P): 24.31. Result ID: 6998d5a85698665ec4396e34. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaMA-3.2-Chat 3B"}. This record does not assert independent reproduction. ### Conditional Delta Precision (δ-P): 24.16. Result ID: 6998d5a85698665ec4396e3c. [Reporting paper]() Recorded evaluation configuration: {"Model":"Gemma-3 4B (it)"}. This record does not assert independent reproduction. ### Conditional Delta Precision (δ-P): 23.17. Result ID: 6998d5a85698665ec4396e38. [Reporting paper]() Recorded evaluation configuration: {"Model":"Gemma-3 4B (pt)"}. This record does not assert independent reproduction. ### RW Delta Precision (δ-P): 22.88. Result ID: 6998d5a85698665ec4396e35. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA-3.2-Chat 3B"}. This record does not assert independent reproduction. ### Pretrained Delta Precision (δ-P): 22.3. Result ID: 6998d5a85698665ec4396e3b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemma-3 4B (it)"}. This record does not assert independent reproduction. ### MinMax Delta Precision (δ-P): 22.27. Result ID: 6998d5a85698665ec4396e36. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA-3.2-Chat 3B"}. This record does not assert independent reproduction. ### MinMax Delta Precision (δ-P): 21.65. Result ID: 6998d5a85698665ec4396e3e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemma-3 4B (it)"}. This record does not assert independent reproduction. ### RW Delta Precision (δ-P): 21.29. Result ID: 6998d5a85698665ec4396e31. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA-3.2-Chat 1B"}. This record does not assert independent reproduction. ### Pretrained Delta Precision (δ-P): 21.18. Result ID: 6998d5a85698665ec4396e2f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA-3.2-Chat 1B"}. This record does not assert independent reproduction. ### RW Delta Precision (δ-P): 20.91. Result ID: 6998d5a85698665ec4396e3d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemma-3 4B (it)"}. This record does not assert independent reproduction. ### Pretrained Delta Precision (δ-P): 20.9. Result ID: 6998d5a85698665ec4396e37. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemma-3 4B (pt)"}. This record does not assert independent reproduction. ### RW Delta Precision (δ-P): 19.67. Result ID: 6998d5a85698665ec4396e39. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemma-3 4B (pt)"}. This record does not assert independent reproduction. ### MinMax Delta Precision (δ-P): 19.55. Result ID: 6998d5a85698665ec4396e32. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LLaMA-3.2-Chat 1B"}. This record does not assert independent reproduction. ### MinMax Delta Precision (δ-P): 19.13. Result ID: 6998d5a85698665ec4396e3a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemma-3 4B (pt)"}. This record does not assert independent reproduction. ### Conditional Delta Precision (δ-P): 19.09. Result ID: 6998d5a85698665ec4396e30. [Reporting paper]() Recorded evaluation configuration: {"Model":"LLaMA-3.2-Chat 1B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.