NYU CTF Bench - ENiGMA: leaderboard
Metric: Challenges solved (%; 200 challenges, $3 budget). Source: arxiv.org. Saturation forecast: Estimated already saturated. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet (20240620) | 13.5 |
| 2 | GPT-4o | 9 |
| 3 | Llama 3.1 405B Instruct | 7 |
| 4 | GPT-4 Preview (1106) | 7 |
Interactive version: theaggregate.ai/benchmark?slug=nyu-ctf-bench-enigma · How It Works · Data refreshed daily, snapshot 2026-10-09.