Event ·Multi-source

Google 发布 Gemini 4 Carbon,安全基准超 GPT-6 Astra 与 Claude Opus 5.5

Google 发布新旗舰模型 Gemini 4 Carbon,距上一代 Gemini 4 Argon 仅两周。在 SEC-bench Pro 漏洞发现上得分 88.2%,CWE-bench 修补得分 71.0%,ExploitGym 利用得分 54.8%。GraphWalks 长上下文基准上达到 96.2%,高于 Argon 的 84.2%、GPT-6 Astra 的 71.8% 和 Claude Opus 5.5 的 66.8%。定价为每百万 token 输入 2 美元、输出 10 美元,之后将涨至 4 美元和 20 美元。因具备漏洞利用能力,首发仅面向部分网络防御者与 Fairwind Program 合作伙伴。

Current read

Google 两周内连发两代旗舰,Carbon 的漏洞发现和修补成绩直接压过 OpenAI 和 Anthropic,长上下文 96.2% 也很猛,定价还先打折,搞安全的建议盯一下。

11 sources88° AI heatLast updated 2026/10/28 17:28:52

Evidence

11 sources
Primary sourcerohanpaul_ai
View source
Related source 2TestingCatalog
View source
Related source 3@koltregaskes
View source
Related source 4Yuchen Jin
View source
Related source 5The Rundown AI
View source
Related source 7Shubham Saboo
View source
Related source 8Artificial Analysis
View source
Related source 9kimmonismus
View source
Related source 10Simon Willison’s Weblog
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Google 发布 Gemini 4 Carbon,安全基准超 GPT-6 Astra 与 Claude Opus 5.5 · 事件专题 | AITOP