AI 热点

Cognition 评测 Gemini 4 Neon:FrontierCode 2.0 得分 46.2%

Cognition更新于 11月20日 07:24

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 Opu

AI 导读

Cognition 在 FrontierCode 2.0 上评测 Gemini 4 Neon,结果为 46.2%,与 Opus 5.5 相差不到 1 个百分点,成本约为后者的三分之一。其每项任务成本为 $4.38,现已可在 Devin Desktop 和 Devin CLI 中使用。

推荐理由

精选AI 评分 61

同一代码合并基准下的得分与成本数据,为比较 Gemini 4 Neon 和 Opus 5.5 提供了具体参照。

主题

标签

正文

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!

来源

Cognition