# Long-form Writing on Creative-W.B. Source: [Long-form Writing on Creative-W.B.]() Collection index: [llms.txt]() Data updated: 2026-04-21T08:47:02.114Z Evaluation of model performance on the Creative-W.B. dataset using a generic 'Score' metric for long-form writing quality. 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 | Long-form Writing | | Dataset (including any stated split) | Creative-W.B. | | Metric | Score | | 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 - [Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Score | Result date | Report paper | | --- | --- | --- | --- | | Qwen2.5-14B-Writing-RL | 83.17 | Not recorded | 68fa792c1e209131cea7c671 | | Llama3.1-8B-Writing-RL | 82.67 | Not recorded | 68fa792c1e209131cea7c671 | | GPT-4o | 80.45 | Not recorded | 68fa792c1e209131cea7c671 | | Qwen2.5-14B-WritingBench-SFT | 79.27 | Not recorded | 68fa792c1e209131cea7c671 | | Llama3.1-8B-WritingBench-SFT | 77.7 | Not recorded | 68fa792c1e209131cea7c671 | | Qwen-Plus | 76.78 | Not recorded | 68fa792c1e209131cea7c671 | | Llama3.1-8B-Reference-SFT | 76.7 | Not recorded | 68fa792c1e209131cea7c671 | | Qwen2.5-7B-Writing-RL | 75.41 | Not recorded | 68fa792c1e209131cea7c671 | | Qwen2.5-7B-Writing-RL | 73.19 | Not recorded | 68fa792c1e209131cea7c671 | | Qwen2.5-7B-WritingBench-SFT (12k) | 70.24 | Not recorded | 68fa792c1e209131cea7c671 | | Qwen2.5-7B-WritingBench-SFT (24k) | 69.6 | Not recorded | 68fa792c1e209131cea7c671 | | Qwen2.5-7B-Reference-SFT | 68.89 | Not recorded | 68fa792c1e209131cea7c671 | | Longwriter-Zero-32B | 61.14 | Not recorded | 68fa792c1e209131cea7c671 | | Qwen2.5-14B-Instruct | 56.89 | Not recorded | 68fa792c1e209131cea7c671 | | Qwen2.5-7B-Instruct | 49.29 | Not recorded | 68fa792c1e209131cea7c671 | | Llama3.1-8B-Instruct | 48.83 | Not recorded | 68fa792c1e209131cea7c671 | | Longwriter-9B | 44.15 | Not recorded | 68fa792c1e209131cea7c671 | | Suri-7B | 18.44 | Not recorded | 68fa792c1e209131cea7c671 | ### Qwen2.5-14B-Writing-RL Score: 83.17. Result ID: 69e7397d47f34ce924cd8861. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SFT":"✓","RL":"PPO"}. This record does not assert independent reproduction. ### Llama3.1-8B-Writing-RL Score: 82.67. Result ID: 69e7397d47f34ce924cd8865. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SFT":"✓","RL":"PPO"}. This record does not assert independent reproduction. ### GPT-4o Score: 80.45. Result ID: 69e7397d47f34ce924cd8855. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SFT":"–","RL":"–"}. This record does not assert independent reproduction. ### Qwen2.5-14B-WritingBench-SFT Score: 79.27. Result ID: 69e7397d47f34ce924cd8860. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SFT":"✓","RL":"✗"}. This record does not assert independent reproduction. ### Llama3.1-8B-WritingBench-SFT Score: 77.7. Result ID: 69e7397d47f34ce924cd8863. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SFT":"✓","RL":"✗"}. This record does not assert independent reproduction. ### Qwen-Plus Score: 76.78. Result ID: 69e7397d47f34ce924cd8854. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SFT":"–","RL":"–"}. This record does not assert independent reproduction. ### Llama3.1-8B-Reference-SFT Score: 76.7. Result ID: 69e7397d47f34ce924cd8864. [Reporting paper]() Recorded evaluation configuration: {"SFT":"✓","RL":"✗"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Writing-RL Score: 75.41. Result ID: 69e7397d47f34ce924cd885e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SFT":"✓","RL":"GRPO"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Writing-RL Score: 73.19. Result ID: 69e7397d47f34ce924cd885d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SFT":"✓","RL":"PPO"}. This record does not assert independent reproduction. ### Qwen2.5-7B-WritingBench-SFT (12k) Score: 70.24. Result ID: 69e7397d47f34ce924cd885a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SFT":"✓","RL":"✗"}. This record does not assert independent reproduction. ### Qwen2.5-7B-WritingBench-SFT (24k) Score: 69.6. Result ID: 69e7397d47f34ce924cd885b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SFT":"✓","RL":"✗"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Reference-SFT Score: 68.89. Result ID: 69e7397d47f34ce924cd885c. [Reporting paper]() Recorded evaluation configuration: {"SFT":"✓","RL":"✗"}. This record does not assert independent reproduction. ### Longwriter-Zero-32B Score: 61.14. Result ID: 69e7397d47f34ce924cd8858. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SFT":"✓","RL":"GRPO"}. This record does not assert independent reproduction. ### Qwen2.5-14B-Instruct Score: 56.89. Result ID: 69e7397d47f34ce924cd885f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SFT":"✗","RL":"✗"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Score: 49.29. Result ID: 69e7397d47f34ce924cd8859. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SFT":"✗","RL":"✗"}. This record does not assert independent reproduction. ### Llama3.1-8B-Instruct Score: 48.83. Result ID: 69e7397d47f34ce924cd8862. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"SFT":"✗","RL":"✗"}. This record does not assert independent reproduction. ### Longwriter-9B Score: 44.15. Result ID: 69e7397d47f34ce924cd8857. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SFT":"✓","RL":"DPO"}. This record does not assert independent reproduction. ### Suri-7B Score: 18.44. Result ID: 69e7397d47f34ce924cd8856. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"SFT":"✓","RL":"✗"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.