EnigmaEval — leaderboard
EnigmaEval is a benchmark from puzzle hunts, testing AI with complex reasoning, creative problem-solving, and cross-domain knowledge synthesis.
Metric: Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 39 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 Pro (xHigh) | 23.82 |
| 2 | Gemini 3.1 Pro (Preview) | 19.76 |
| 3 | GPT-5 Pro | 18.75 |
| 4 | GPT-5.4 (xHigh) | 15.96 |
| 5 | O3 (Medium) | 13.09 |
| 6 | Claude Opus 4.5 | 11.91 |
| 7 | GPT-5.1 | 11.23 |
| 8 | GPT-5 | 10.47 |
| 9 | GPT-5.2 | 10.39 |
| 10 | O4 Mini (High) | 9.21 |
| 11 | GPT-5 Mini | 8.19 |
| 12 | Claude Opus 4.6 (Max) | 7.6 |
| 13 | Claude Opus 4.1 | 7.18 |
| 14 | O1 Pro | 6.14 |
| 15 | Claude Sonnet 4.5 | 6 |
Interactive version: theaggregate.ai/benchmark?slug=enigmaeval · How the rankings work · Data refreshed daily, snapshot 2026-07-22.