LLM Creative Story Writing Win Probability
Chat & Writing · 2025-01-05
Secondary metric from Lech Mazur's Creative Story-Writing benchmark, reporting each model's estimated win probability against the evaluated pool as a 0-1 probability.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Fable 5.1 | 0.9 |
| Claude Opus 5 | 0.9 |
| Claude Opus 5.5 | 0.9 |
| GPT-6 Astra | 0.9 |
| GLM-5.3 | 0.9 |
| Claude Fable 5 | 0.9 |
| GPT-5.6 Sol | 0.8 |
| GPT-5.5 | 0.8 |
| Kimi K3 | 0.8 |
| GPT-5.4 | 0.8 |
| Muse Wonder | 0.8 |
| Opus 4.7 | 0.8 |
| Sonnet 4.6 | 0.7 |
| MiMo-V2.6-Pro | 0.7 |
| Opus 4.6 | 0.7 |
| Gemini 4 Argon | 0.6 |
| Opus 4.8 | 0.6 |
| Muse Spark 1.1 | 0.6 |
| Muse Spark 1.3 | 0.6 |
| GLM-5.2 | 0.6 |
| Grok 4.7 | 0.6 |
| GPT-5.2 | 0.6 |
| Gemini 3.8 Flash | 0.5 |
| Kimi K2.6 | 0.5 |
| Muse Spark 1.2 | 0.5 |
| MiniMax M3 | 0.5 |
| Mistral Medium 3.1 | 0.4 |
| DeepSeek V4.1 Flash | 0.4 |
| Qwen3.8 27B | 0.4 |
| MiMo-V2.5-Pro | 0.4 |
| Qwen3 Max (rolling alias) | 0.4 |
| Gemini 3.7 Flash | 0.4 |
| Qwen3.6-Max-Preview | 0.4 |
| GLM-5.1 | 0.3 |
| Kimi K2.5 | 0.3 |
| MiMo-V2-Pro | 0.3 |
| ERNIE 5.1 | 0.3 |
| Mistral Large 4 Preview | 0.3 |
| Mistral Large 3 675B Instruct 2512 | 0.3 |
| Gemma 4 31B IT | 0.2 |