Dongfang Shuo
A Chinese web-fiction-specialized model fine-tuned from Qwen3.8 27B.
Timeline (last 90 days)
A Bilibili UP host's comparative review tested seven models with three literary creation prompts: six community fine-tuned versions based on Qwen3.8 27B (Hemingway, HumanLike Chat, Alexs WinX, DavidAU Brandings, Dongfang Shuo) and the official original Qwen3.8 27B, plus DeepSeek v4.1.
Combining the three prompts, the final ranking was: Hemingway first, HumanLike Chat second, official original Qwen3.8 27B third, DavidAU Brandings fourth, Alexs WinX fifth, DeepSeek v4.1 sixth, and Dongfang Shuo seventh.
In the second prompt (dialogue about roommates dividing a rice cooker), Hemingway ranked first, HumanLike Chat ranked second, the official original ranked third, and Dongfang Shuo ranked toward the bottom.
The UP host suggested that if using local models to assist literary creation, Hemingway and HumanLike Chat are worth trying first; DavidAU and Alexs WinX may be good at reasoning and agents but are not strong at literary creation; and Dongfang Shuo carries a relatively high risk of chaotic character relationships when writing long-form web fiction.
All Facts (4)
Combining the three prompts, the final ranking was: Hemingway first, HumanLike Chat second, official original Qwen3.8 27B third, DavidAU Brandings fourth, Alexs WinX fifth, DeepSeek v4.1 sixth, and Dongfang Shuo seventh.
50%UnverifiedIn the second prompt (dialogue about roommates dividing a rice cooker), Hemingway ranked first, HumanLike Chat ranked second, the official original ranked third, and Dongfang Shuo ranked toward the bottom.
50%UnverifiedThe UP host suggested that if using local models to assist literary creation, Hemingway and HumanLike Chat are worth trying first; DavidAU and Alexs WinX may be good at reasoning and agents but are not strong at literary creation; and Dongfang Shuo carries a relatively high risk of chaotic character relationships when writing long-form web fiction.
50%UnverifiedA Bilibili UP host's comparative review tested seven models with three literary creation prompts: six community fine-tuned versions based on Qwen3.8 27B (Hemingway, HumanLike Chat, Alexs WinX, DavidAU Brandings, Dongfang Shuo) and the official original Qwen3.8 27B, plus DeepSeek v4.1.
50%