OpenAI's Astra achieves 100% success rate on ExploitBench vulnerability tests

JiaweiLiu_ · x · 2026-09-02

Tests show that OpenAI's new model, Astra, achieved a 100% Automated Cybersecurity Exploit (ACE) success rate against all 41 CVEs in ExploitBench. To rule out contamination, an internal port using only V8 CVEs from the past 3 months was created. Astra still demonstrated a major capability increase over GPT-4o (5.6) while using significantly fewer tokens. OpenAI previously stated that Astra has reached the 'Critical' threshold under its Preparedness Framework.

Related event: OpenAI's Astra Hits 100% on ExploitBench, Far Outpacing GPT-5.6(6 posts)→

Original post →

More from Models

Models channel →