Model Releases

UK AISI evaluates OpenAI GPT-5.5 cyberattack capabilities: 71.4% pass rate on Expert tasks

Original title:Our evaluation of OpenAI's GPT-5.5 cyber capabilities

AI summary

The UK AI Security Institute released an evaluation of the cybersecurity capabilities of an early version of OpenAI GPT-5.5. GPT-5.5 achieved an average pass rate of 71.4% on Expert-level CTF tasks, exceeding Claude Mythos Preview's 68.6%, and completed the 32-step enterprise network attack simulation The Last Ones end-to-end in 2 of 10 attempts, becoming the second model to do so.

Key Takeaways

  • The UK AI Security Institute released an evaluation of the cybersecurity capabilities of an early…
  • 5 achieved an average pass rate of 71.
  • 4% on Expert-level CTF tasks,exceeding Claude Mythos Preview's 68.
  • 6%,and completed the 32-step enterprise network attack simulation The Last Ones end-to-end in 2 of…

Quick Facts

Published
Updated
Source
英国 AI Security Institute:Blog(网页)
Category
Model Releases
AI score
77
Read the original Read the full article at the original source
Why it matters

英国 AISI 公布了对 GPT-5.5 网络攻击能力的独立评测数据,并给出与 Claude Mythos Preview 的直接对比和任务细节。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: UK AISI evaluates OpenAI GPT-5.5 cyberattack capabilities: 71.4% pass rate on Expert tasks. April 30, 2026. https://new.nat6.net/en/news/r4s12yyiywbsig4bskufb7iwx/

View all →