OpenAI launches GPT-6 Astra, its first model to cross a critical cybersecurity threshold
OpenAI launched GPT-6 Astra, its first model rated Critical for cybersecurity risk, scoring 100% on ExploitBench and finding two new zero-days.
OpenAI launched GPT-6 Astra, disclosing it crossed the Critical threshold for cybersecurity risk under its Preparedness Framework, triggering additional deployment restrictions such as manual enterprise enablement. The model scored 100% on ExploitBench (vs 78.5% for predecessor GPT-5.6 Sol) and 42.4% on ExploitGym (vs 30.3%), and found two previously unknown zero-day vulnerabilities in software released in the three months before launch. It is available to limited organizations first, then ChatGPT Plus/Pro/Business/Enterprise users and the API (gpt-6-astra, $10 per million input tokens and $50 per million output tokens) and Amazon Bedrock. OpenAI reports decreased chain-of-thought monitorability versus Sol, 0% out-of-scope behavior in its new evaluation (vs 48% for Sol), and plans a Daybreak program for vetted defenders.
- First model to cross OpenAI's Preparedness Framework 'Critical' cybersecurity threshold, triggering extra deployment restrictions.
- Scored 100% on ExploitBench (vs 78.5% for GPT-5.6 Sol) and 42.4% on ExploitGym.
- Found two previously unknown zero-day vulnerabilities during pre-launch testing on recent disclosures.
- Priced $10/$50 per million input/output tokens; available via API, ChatGPT tiers, and Amazon Bedrock.
- Chain-of-thought monitorability decreased versus predecessor; public version refuses offensive tasks like PoC generation.
- Organizations
- OpenAIGreyhound ResearchKanerika
- AI models
- GPT-6 AstraGPT-5.6 Sol
From the original article
3 min read at csoonline.com
OpenAI launched GPT-6 Astra on Thursday, disclosing that the new flagship model has crossed the “Critical” threshold for cybersecurity risk under its Preparedness Framework, a classification the company said triggers additional deployment restrictions.
csoonline.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.