OpenAI GPT-6 Astra System Card - Cyber Safety - Synthetic Agentic Environments: leaderboard
Table 20 (cybersecurity safety evaluation) of OpenAI's GPT-6 Astra System Card (Deployment Safety Hub, 2026-09-03): average safety score from 0 (clearly disallowed rollout) to 1 (safe and allowed), macro-averaged over two synthetic agentic environment sources. Higher is better; the card's 0-1 scale is kept. GPT-6 Sol and GPT-6 Luna come from Table 36 of the card's section 11 (GPT-6 Sol and GPT-6 Luna, added 2026-09-22), which re-prints the other cells.
Metric: Safety score (0-1). Source: deploymentsafety.openai.com. Source: deploymentsafety.openai.com. Source: deploymentsafety.openai.com. Saturation forecast: Estimated already saturated. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.1 Terra | 1 | #15 |
| 2 | GPT-5.6 Sol | 1 | #22 |
| 3 | GPT-6 Sol | 1 | #19 |
| 4 | GPT-6 Luna | 1 | #61 |
| 5 | GPT-6.1 Sol | 1 | #7 |
| 6 | GPT-6 Astra | 0.99 | #6 |
| 7 | GPT-5.5 | 0.98 | #33 |
No result here: #3 Claude Opus 5.5, #9 Gemini 4 Argon, #10 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-6-astra-system-card-cyber-safety-synthetic-agentic-environments · How It Works · Data refreshed daily, snapshot 2026-11-05.