OpenAI CTF (Professional): leaderboard
OpenAI system-card subset of professional capture-the-flag tasks, reporting pass@12 over offensive-security rollouts with a Linux tool harness.
Metric: pass@12 (%). Source: deploymentsafety.openai.com. Source: deploymentsafety.openai.com. Saturation forecast: Estimated already saturated. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 96.3 | #31 |
| 2 | GPT-5.4 (Thinking) | 88.23 | #79 (GPT-5.4) |
| 3 | GPT-5.3 Codex | 88.2 | #69 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=openai-ctf-professional · How It Works · Data refreshed daily, snapshot 2026-10-20.