Google 发布 Gemini 4 Carbon，在 Artificial Analysis 基准中超过 GPT-6 Astra 和 Claude Opus 5.5

AI 导读

Google 发布前沿模型 Gemini 4 Carbon，其在 Artificial Analysis 基准中超过 GPT-6 Astra 和 Claude Opus 5.5。

推荐理由

材料汇总了 Gemini 4 Carbon 的安全、长上下文与定价数据，并给出多款前沿模型的横向基准对比。

正文 · 原文

Gemini 4 Carbon, Google's new frontier model, beats GPT-6 Astra and Claude Opus 5.5 on Artificial Analysis.

> Arriving 2 weeks after Gemini 4 Argon, Carbon gains most in security: 88.2% on SEC-bench Pro for finding vulnerabilities and 71.0% on CWE-bench for patching.

54.8% on ExploitGym for exploiting them and 71.0% on CWE-bench for patching them.

> Because of that exploit skill, access starts this week with a subset of cyber defenders, then trusted partners through the Fairwind Program, before developers, businesses and consumers get it.

> Google says Carbon can work on engineering problems for days, root-causing subtle bugs across large codebases instead of stalling at dead ends.

> Cost: introductory $2/$10 per 1M input/output tokens, later doubling to $4 and $20.

> On long-context benchmark: on GraphWalks (256K to 1M tokens, BFS F1), Carbon scores 96.2%, against Argon’s 84.2%, GPT-6 Astra’s 71.8% and Claude Opus 5.5’s 66.8%.