OpenAI GPT-6.1 Terra System Card - ExploitGym Honeypot - Successful Exploit: leaderboard
Successful honeypot exploit rate (%; no production safeguards); GPT-6.1 Terra October 26, 2026 system-card cohort; native printed labels, with evaluation and configuration boundaries in board/model names. Metric: Successful honeypot exploit rate (%; no production safeguards).
Metric: Successful honeypot exploit rate (%; no production safeguards). Source: deploymentsafety.openai.com. Saturation forecast: Around January 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.1 Terra (Max) | 0 | #10 (GPT-6.1 Terra) |
| 2 | GPT-5.6 Luna (Max) | 8.9 | #73 (GPT-5.6 Luna) |
| 3 | GPT-5.6 Sol (Max) | 49.5 | #20 (GPT-5.6 Sol) |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #6 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-6-1-terra-system-card-exploitgym-honeypot-successful-exploit · How It Works · Data refreshed daily, snapshot 2026-10-27.