OpenAI GPT-6 Astra Launch - Internal Computer Use Safety Benchmark (with AutoReview): leaderboard
Alignment table of OpenAI's GPT-6 Astra launch post (2026-09-03): the internal computer-use safety benchmark rerun with Codex Auto-Review enabled, reporting the rate of unintended consequences. Percent, lower is better; only GPT-6 Astra and GPT-5.6 Sol have values.
Metric: Unintended-consequence rate (%). Source: openai.com. Saturation forecast: Around February 2027. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 1.8 | #6 |
| 2 | GPT-5.6 Sol | 4.3 | #22 |
No result here: #3 Claude Opus 5.5, #7 GPT-6.1 Sol, #9 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-6-astra-launch-internal-computer-use-safety-benchmark-with-autoreview · How It Works · Data refreshed daily, snapshot 2026-11-05.