NYU CTF Bench - D-CIPHER without planner: leaderboard
Metric: Challenges solved (%; 200 challenges, $3 budget). Source: arxiv.org. Saturation forecast: Around August 2028. 2 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet (20241022) | 14 |
| 2 | GPT-4o (2024-11-20) | 9 |
Interactive version: theaggregate.ai/benchmark?slug=nyu-ctf-bench-d-cipher-without-planner · How It Works · Data refreshed daily, snapshot 2026-10-09.