News · curated 4 Sep 2026
GPT-6 Astra: A new generation of intelligence
First reported openai.com
Coverage timeline
Single-source incident — first reported, latest, and curated coincide.
Why it matters
GPT-6 Astra reaching a "Critical" cyber-capability threshold and topping an exploit benchmark signals that frontier models can increasingly generate working exploits, raising the stakes for how vendors gate and defenders anticipate AI-assisted offensive capability.
OpenAI unveiled GPT-6 Astra, describing it as its "most intelligent and aligned model," which it says saturates the ExploitBench benchmark with a 100% score and reached the "Critical" cybersecurity capability threshold under its Preparedness Framework. OpenAI also reports alignment safeguards that block proof-of-concept exploit requests and reduce agentic scope-exceeding behavior (0% on an ExploitGym honeypot versus 48.2% for its prior model).