Primary sourcerohanpaul_ai
View sourceEvent ·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 sourcesRelated source 1Blognone
View sourceRelated source 2TestingCatalog
View sourceRelated source 3@koltregaskes
View sourceRelated source 4Yuchen Jin
View sourceRelated source 5The Rundown AI
View sourceRelated source 6IT之家
View sourceRelated source 7Shubham Saboo
View sourceRelated source 8Artificial Analysis
View sourceRelated source 9kimmonismus
View sourceRelated source 10Simon Willison’s Weblog
View sourceConflict 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.