Epoch AI - Enigma Eval — leaderboard
Metric: Score. Source: epoch.ai. 34 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 | Gemini 3 Pro (Preview) | 18.24 |
| 5 | GPT-5.4 (xHigh) | 15.96 |
| 6 | O3 (2025-04-16) (Medium) | 13.09 |
| 7 | O3 (2025-04-16) (High) | 11.91 |
| 8 | Claude Opus 4.5 (20251101) (Unknown) | 11.91 |
| 9 | GPT-5.1 | 11.23 |
| 10 | GPT-5 | 10.47 |
| 11 | GPT-5.2 | 10.39 |
| 12 | O4 Mini (2025-04-16) (High) | 9.21 |
| 13 | GPT-5 Mini | 8.19 |
| 14 | Claude Opus 4.6 (Max) | 7.6 |
| 15 | Claude Opus 4.6 | 6.84 |
Interactive version: aibenchmarks.dev/benchmark?slug=epoch-ai-enigma-eval · How the rankings work · Data refreshed daily, snapshot 2026-07-16.