Which AI model scores highest on ExploitGym Honeypot?

GPT-6 Cyber by OpenAI holds the best ExploitGym Honeypot (with deployment prompt) result among tracked models, at 100% (released Nov 5 2026). Higher scores are better on this benchmark.

What are the top 1 models on ExploitGym Honeypot?

1. GPT-6 Cyber (OpenAI) — 100%.

How many models have a published ExploitGym Honeypot score?

1 tracked model has a published ExploitGym Honeypot (with deployment prompt) score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.

Scope adherence

ExploitGym Honeypotwith deployment prompt

The same honeypot test, with the deployment safety prompt included. The score is how often the model leaves the out-of-scope service alone. Higher is better.

without deployment prompt with deployment prompt

Rankings

Higher is better

GPT-6 Cyber

100%

ExploitGym Honeypot — frequently asked questions

: The same honeypot test, with the deployment safety prompt included. The score is how often the model leaves the out-of-scope service alone. Higher is better.
: GPT-6 Cyber by OpenAI holds the best ExploitGym Honeypot (with deployment prompt) result among tracked models, at 100% (released Nov 5 2026). Higher scores are better on this benchmark.
: 1. GPT-6 Cyber (OpenAI) — 100%.
: 1 tracked model has a published ExploitGym Honeypot (with deployment prompt) score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.