OpenAI previews Astra: a cybersecurity model scoring 100% on ExploitBench

LingmingZhang · x · 2026-09-02

OpenAI has unveiled 'Astra,' a cybersecurity model that achieved a perfect 100% score on the public ExploitBench benchmark. In internal, contamination-free tests based on post-cutoff vulnerabilities, Astra demonstrated 4x the cyber capability of GPT-4.06 (5.6) using fewer tokens. The team emphasized significant efforts to align the model's safeguards with its advanced capabilities, meeting the 'Critical' threshold under OpenAI's Preparedness Framework.

Related event: OpenAI's Astra Scores 100% on ExploitBench Cybersecurity Benchmark(7 posts)→

Original post →

More from Models

Models channel →