OpenAI GPT-5.6 System Card - Prompt Injection - Search and Function Calling: leaderboard
Metric: Prompt-injection robustness rate (%). Source: deploymentsafety.openai.com. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Terra | 94.6 |
| 2 | GPT-5.6 Sol | 91 |
| 3 | GPT-5.6 Luna | 89.7 |
| 4 | GPT-5.4 (Thinking) | 69.7 |
| 5 | GPT-5.2 (Thinking) | 56.8 |
| 6 | GPT-5.1 (Thinking) | 42.3 |
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-5-6-system-card-prompt-injection-search-and-function-calling · How It Works · Data refreshed daily, snapshot 2026-09-19.