EnigmaEval
General QA · 2025-02-13
Score on puzzle-hunt reasoning tasks with multimodal clues.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-6 Astra | 69.7 |
| Gemini 4 Argon | 64.6 |
| GPT-6.1 Sol | 59.5 |
| Claude Opus 5.5 | 57.8 |
| Claude Fable 5.1 | 44.2 |
| Claude Opus 5 | 43.9 |
| Gemini 3.8 Flash | 37.2 |
| GPT-5.5 | 37.2 |
| Muse Wonder | 36.1 |
| Gemini 3.7 Flash | 33.9 |
| GPT-5.4 | 27.6 |
| Gemini 3.5 Flash | 25.4 |
| Kimi K3 | 23.6 |
| Opus 4.8 | 23.5 |
| GPT-5.6 Terra | 23.1 |
| GPT-5.6 Luna | 19.1 |
| Gemini 3 Flash Preview | 18.3 |
| Gemini 3 Pro Preview | 17.8 |
| Grok 4.5 | 17.0 |
| Muse Spark 1.1 | 16.6 |
| Opus 4.7 | 15.6 |
| Muse Spark Open | 14.7 |
| GPT-5.2 | 14.5 |
| Opus 4.5 | 12.4 |
| o3 | 11.9 |
| GPT-5.1 | 11.7 |
| GPT-5 | 10.5 |
| O4 Mini | 9.2 |
| Sonnet 4.6 | 9.1 |
| GPT-5 Mini | 8.2 |
| Grok 4 | 7.8 |
| Grok 4.20 | 7.7 |
| Opus 4.6 | 7.6 |
| GPT-5.4 Mini | 6.9 |
| Grok 4.3 | 6.1 |
| Sonnet 4.5 | 6.0 |
| o1 (source unspecified) | 5.7 |
| Gemini 2.5 Pro | 5.6 |
| Kimi K2.6 | 5.5 |
| Grok 4.1 Fast | 5.2 |