OpenAI GPT-5.6 System Card - GPT-Red Prompt Injection - Direct: leaderboard
GPT-Red table of OpenAI's GPT-5.6 System Card (Deployment Safety Hub, 2026-07-09), added 2026-08-03: average attack-attempt success rate of GPT-Red, OpenAI's RL-trained automated red-teamer, in direct (chat-based) instruction-hierarchy environments. Percent as printed (e.g. 0.051%), lower is better; GPT-5.6 Sol, Terra and Luna only.
Metric: Attack success rate (%). Source: deploymentsafety.openai.com. Saturation forecast: Estimated already saturated. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 0.05 | #22 |
| 2 | GPT-5.6 Terra | 0.06 | #40 |
| 3 | GPT-5.6 Luna | 0.11 | #79 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-5-6-system-card-gpt-red-prompt-injection-direct · How It Works · Data refreshed daily, snapshot 2026-11-05.