Creative Writing
Creative Writing v3 是一个用于评估大型语言模型（LLM）创意写作能力的评测基准。该基准采用混合评分系统，旨在更精确地区分不同模型，特别是顶尖模型之间的性能差异。
更新于 2026-04-22
1,481 次浏览
问题数量
32
发布机构
个人
评测类别
写作和创作
评测指标
人工评估
支持语言
英文
难度等级
中等难度
简介
用顶尖大模型来判断大模型创意写作方面的评测基准
相关资源
Creative Writing Model Score Leaderboard
Source: DataLearnerAI
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
模式说明:
normal
thinking
low
medium
high
deeper thinking
parallel_thinking
图表加载中...
Latest Creative Writing model rankings and full benchmark leaderboard
Browse the latest scores, model modes, release dates, and parameter sizes for Creative Writing.
Model release cutoff:
Creative Writing详细排名数据表格
| 排名 | 模型 | |||
|---|---|---|---|---|
| 1 | Kimi K2 Standard Mode | 88.10 | 2025-07-11 | 10000 |
| 2 | OpenAI o3 Standard Mode | 87.65 | 2025-04-16 | 未知 |
| 3 | Qwen3-235B-A22B-2507 Standard Mode | 87.50 | 2025-07-21 | 2350 |
| 4 | DeepSeek-R1-0528 Thinking Enabled | 86.25 | 2025-05-28 | 6710 |
| 5 | Qwen3-235B-A22B-Thinking-2507 Thinking Enabled | 86.10 | 2025-07-25 | 2350 |
| 6 | Qwen3-235B-A22B-Thinking Thinking Enabled | 86.10 | 2025-07-30 | 305 |
| 7 | Qwen3-30B-A3B-2507 Standard Mode | 86.00 | 2025-07-29 | 305 |
| 8 | Gemini 2.5-Pro Standard Mode | 85.85 | 2025-06-05 | 未知 |
| 9 | Qwen3-Next Standard Mode | 85.30 | 2025-09-11 | 800 |
| 10 | GPT-4o(2025-03-27) Standard Mode | 84.90 | 2025-03-27 | 未知 |
| 11 | DeepSeek-R1 Standard Mode | 84.60 | 2025-01-20 | 6710 |
| 12 | Qwen3-235B-A22B Thinking Enabled | 84.60 | 2025-04-28 | 2350 |
| 13 | Claude Opus 4 Standard Mode | 83.75 | 2025-05-23 | 未知 |
| 14 | Claude Sonnet 4 Standard Mode | 83.05 | 2025-05-23 | 未知 |
| 15 | DeepSeek-V3 Standard Mode | 81.60 | 2024-12-26 | 6810 |
| 16 | DeepSeek-V3-0324 Standard Mode | 81.60 | 2025-03-24 | 6710 |
| 17 | Qwen3-32B Thinking Enabled | 81.00 | 2025-04-28 | 320 |
| 18 | Qwen3-235B-A22B Standard Mode | 80.40 | 2025-04-28 | 2350 |
| 19 | Qwen3-32B Standard Mode | 78.30 | 2025-04-28 | 320 |
| 20 | Claude 3.5 Sonnet New Standard Mode | 78.15 | 2024-10-22 | 未知 |
| 21 | Qwen3-8B Thinking Enabled | 75.00 | 2025-04-28 | 80 |
| 22 | Qwen3-30B-A3B Standard Mode | 68.10 | 2025-04-28 | 305 |
| 23 | Qwen3-8B Standard Mode | 64.50 | 2025-04-28 | 80 |