SEAL - EnigmaEval: leaderboard
1,184 puzzle-hunt-derived challenges requiring creative multimodal problem-solving across mathematics, logic, linguistics, and cultural knowledge, with unambiguous verifiable solutions.
Metric: Score. Source: scale.com. Saturation forecast: Around 2029. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5 (High) | 39.28 | #16 (Claude Fable 5) |
| 2 | GPT-5.6 Sol (High) | 37.12 | #19 (GPT-5.6 Sol) |
| 3 | Gemini 3.1 Pro (Preview) (High) | 36.78 | #58 (Gemini 3.1 Pro (Preview)) |
| 4 | Gemini 3.5 Flash (High) | 25.41 | #60 (Gemini 3.5 Flash) |
| 5 | Claude Opus 4.8 (xHigh) | 23.51 | #37 (Claude Opus 4.8) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=seal-enigmaeval · How It Works · Data refreshed daily, snapshot 2026-10-20.