Irregular evaluates GPT-6 Astra: FrontierCyber cyber capabilities significantly improved
Assessing GPT-6 Astra: FrontierCyber Measures a Sharp Increase in Cyber Capability
Irregular, in collaboration with OpenAI, tested GPT-6 Astra using three offensive cybersecurity evaluation suites — FrontierCyber, CyScenarioBench, and Atomic Challenges — and the results show its cyber capabilities are clearly improved over GPT-5.6 Sol. On FrontierCyber, GPT-6 Astra solved 86 of 226 challenges, while GPT-5.6 Sol solved 34; Easy success rate rose from 14% to 63%, Medium from 15% to 30%, and Hard from 17% to 39%, and neither model solved any Elite challenges. During the evaluation, GPT-6 Astra discovered and exploited multiple zero-day vulnerabilities that GPT-5.6 Sol did not identify, involving widely deployed database systems, browser JavaScript engines, and mobile device SMS data; the relevant vulnerabilities are being disclosed responsibly.
第三方对 GPT-6 Astra 的进攻性网络安全评测，给出与 GPT-5.6 Sol 的分项对比和真实零日发现，可作能力阈值讨论的参照。