OpenAI Cyber Ranges: leaderboard
OpenAI internal cyber-range suite measuring end-to-end cyber operations across realistic emulated networks.
Metric: Combined Pass Rate (%). Source: deploymentsafety.openai.com. Source: deploymentsafety.openai.com. Saturation forecast: Around January 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 93.33 | #31 |
| 2 | GPT-5.3 Codex | 80 | #69 |
| 3 | GPT-5.4 (Thinking) | 73.33 | #79 (GPT-5.4) |
| 4 | GPT-5.2 Codex | 53.33 | #95 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=openai-cyber-ranges · How It Works · Data refreshed daily, snapshot 2026-10-20.