Skip to content
Live
ITHome · AI·· 9 days agoSame event80

OpenAI releases cybersecurity-focused model GPT-6 Cyber, ExploitGym benchmark improvement of 51%

Brief overview

OpenAI releases cybersecurity-focused model GPT-6 Cyber, scores 48.5% in ExploitGym tests, a relative improvement of about 51% compared to GPT-5.6 Cyber's 32.1%

Same story — featured version shown《OpenAI releases GPT-6 Cyber security model》

Same story3 other outlets also reported this

  1. OpenAI News··First

    OpenAI releases GPT-6 Cyber security model

  2. The Decoder··+11 h 36 min

    OpenAI releases GPT-6 Cyber security model, capable of finding vulnerabilities and providing repair solutions

  3. ITHome · AI··+14 h 23 min·Reading now

    OpenAI releases cybersecurity-focused model GPT-6 Cyber, ExploitGym benchmark improvement of 51%

    Adds:accompanied by multiple security mechanisms

  4. 36Kr · AI··+14 h 46 min

    OpenAI has launched the cybersecurity model GPT-6 Cyber

In order of publication · later reports are added as they appear · Compared by AI from each outlet’s title and summary

Source: ITHome · AI · ithome.com

OpenAI / ChatGPTSafety & alignmentModel releases#Model releases#Safety & alignment#OpenAI