CresOWLve: leaderboard
Creative problem-solving on CresOWLve (2026), 2,061 expert-written puzzles from the quiz game What? Where? When?, each needing several real-world facts from different domains joined by a non-obvious creative connection, answered zero-shot in the English version. Accuracy judged by GPT-4o against the reference answer, its explanation and accepted alternatives, in percent; higher is better.
Metric: Accuracy (%) judged by GPT-4o against the reference answer, its explanation and accepted alternatives, English version, on the 2,061 creative questions of CresOWLve (expert-written What? Where? When? puzzles that need several real-world facts joined by a creative leap), zero-shot; non-thinking models with chain-of-thought prompting, thinking models at the stated effort; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 14 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 76.03 | #99 | |
| 2 | GPT-5.4 | Medium | 53.47 | #135 |
| 3 | Gemini 3 Flash | Medium | 52.16 | #175 |
| 4 | GLM-5 | 37.17 | #269 | |
| 5 | Qwen 3.5 397B A17B | 31.25 | #264 | |
| 6 | DeepSeek V3.2 | Thinking | 25.47 | #419 |
| 7 | GPT-4.1 | 24.99 | #505 | |
| 8 | Qwen 3 235B A22B 2507 Instruct | 20.82 | #616 | |
| 9 | Qwen 3 235B A22B 2507 (Thinking) | 20.82 | #466 | |
| 10 | Mistral Large 3 | 17.61 | #832 | |
| 11 | GPT-4.1 Mini | 13.78 | #789 | |
| 12 | Llama 3.3 70B Instruct | 10.14 | #1385 | |
| 13 | Command A | 9.07 | #1296 | |
| 14 | OLMo-2-0325-32B-Instruct | 5.29 | #2841 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=cresowlve · How It Works · Data refreshed daily, snapshot 2026-11-21.