Arena-Hard Creative Writing: leaderboard
250 creative writing prompts auto-evaluated by an ensemble of GPT-4.1 and Gemini 2.5 judges, measuring style, narrative quality, and creative expression.
Metric: Win Rate (%). Source: github.com. Saturation forecast: Estimated already saturated. 28 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O3 (2025-04-16) | 88.8 | #121 |
| 2 | Gemini 2.5 Flash | 83.9 | #245 |
| 3 | DeepSeek R1 | 77 | #251 |
| 4 | Qwen 3 235B A22B | 73.5 | #313 |
| 5 | Gemma 3 27B (IT) | 69.9 | #523 |
| 6 | GPT-4.1 | 61.5 | #248 |
| 7 | QwQ-32B | 60.9 | #421 |
| 8 | O1 (2024-12-17) (High) | 59.9 | #149 (O1 (2024-12-17)) |
| 9 | O4 Mini (2025-04-16) (High) | 58.7 | #179 (O4 Mini (2025-04-16)) |
| 10 | O1 (2024-12-17) | 56.6 | #149 |
| 11 | O4 Mini (2025-04-16) | 55.6 | #179 |
| 12 | Qwen 3 32B | 53.3 | #443 |
| 13 | GPT-4.5 (Preview) | 51.4 | #244 |
| 14 | Gemini 2.0 Flash (001) | 50 | #360 |
| 15 | O3 Mini (2025-01-31) (High) | 43 | #240 (O3 Mini (2025-01-31)) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=arena-hard-creative-writing · How It Works · Data refreshed daily, snapshot 2026-10-20.