模型58

Cognition 在 FrontierCode 2.0 上评测 Gemini 4 Neon

原标题:We’ve evaluated Gemini 4 Neon on FrontierCode 2.0, our benchmark that measures whether you should merge the PR, and found that it scores ...

Cognition@cognition发布时间 (北京时间)

Cognition 用其 FrontierCode 2.0 基准评测 Gemini 4 Neon,该基准衡量模型给出的 PR 是否值得合并,结果显示其得分与 Opus 5.5 相差不到 1 分,成本约为后者的三分之一。Gemini 4 Neon 得分为 46.2%,单任务成本 4.38 美元,是 Gemini 系列中表现最强的模型。该模型现已在 Devin Desktop 和 Devin CLI 中可用。

中文译文尚未完成,先为你展示原文。

We’ve evaluated Gemini 4 Neon on FrontierCode 2.0, our benchmark that measures whether you should merge the PR, and found that it scores within one point of Opus 5.5 at about a third of the cost.

It is the strongest of the Gemini model series with a score of 46.2% and a cost of $4.38 per task.

Gemini 4 Neon is now available to use in Devin Desktop and Devin CLI!

Google / GeminiAI 编码评测基准#评测/基准#编码#Google