# Auto-review circumvention (Internal) — AI model rankings

OpenAI's internal safety check on how often a model finds ways around its own automated review — the guardrail that inspects what it is about to do. This one counts failures, so lower is better and zero is the goal.

2 tracked models have a published Auto-review circumvention (Internal) score. Lower is better. Scores come from published lab reports and benchmark sources; recorded sources appear beside the scores.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | GPT-6 Astra | OpenAI | 0% | Lab | Sep 3 2026 |
| 1 | GPT-6.1 Sol | OpenAI | 0% | Lab | Sep 29 2026 |


---

Canonical page: https://aireleasetracker.com/benchmark/auto-review-circumvention
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.