Google 发布 Gemini 4 Carbon，登顶 Artificial Analysis V5 榜单
精选理由
Google 新模型 Gemini 4 Carbon 登顶 Artificial Analysis V5，主打网络安全场景，三个安全基准成绩都公开了，搞安全的可以试试。
Google 宣布推出 Gemini 4 Carbon，在 Artificial Analysis V5 排名中拿下第一。该模型首先面向网络安全防御人员开放。在安全基准上，它在 SEC-bench Pro 漏洞发现任务拿到 88.2%，ExploitGym 漏洞利用任务拿到 54.8%，CWE-bench 补丁任务拿到 71.0%。官方称其在编程和智能体任务上也有明显提升。
原文 · TestingCatalog
BREAKING 🔥: Google announced Gemini 4 Carbon, a new SOTA model that takes the top spot on Artificial Analysis V5 ranking!
> Gemini 4 Carbon is iolling out to cyber defenders first.
> It shows significant gains across coding and agentic tasks as well as across key capabilities critical for cybersecurity defense, landing a firm lead in SEC-bench Pro (88.2%) for finding vulnerabilities, ExploitGym (54.8%) for exploitation, and CWE-bench (71.0%) for patching
It needs testing! 👀
