←新闻详情

Artificial Analysis更新于 10月13日 00:42

Mistral Large 4 Preview 在 Artificial Analysis Cyber Index 得分 50

Mistral Large 4 Preview scores 50 on the Artificial Analysis Cyber Index, level with GLM-5.3-Flash (50) and behind MiMo-V2.6-Pro (56). Once its weights are rele

AI 导读

Artificial Analysis 评测显示,Mistral Large 4 Preview 在 Cyber Index 上得分 50,与 GLM-5.3-Flash 持平,低于 MiMo-V2.6-Pro 的 56。权重发布后,它将在该指数上进入开源权重模型前三。其最强项是 CyberGym-E2E-AA,得分 82%,高于 MiMo-V2.6-Pro 的 79% 和 GPT-6 Luna(max)的 78%。

推荐理由

AI 评分 55

第三方评测给出 Mistral Large 4 Preview 在网络安全基准上的得分与同档模型对比,可据此了解其安全能力定位。

主题

标签

正文

当前显示原文,中文全文译文尚未就绪。

Mistral Large 4 Preview scores 50 on the Artificial Analysis Cyber Index, level with GLM-5.3-Flash (50) and behind MiMo-V2.6-Pro (56). Once its weights are released, it will rank among the top three open weights models on the Cyber Index. Its strongest result is on CyberGym-E2E-AA, where it scores 82%, ahead of MiMo-V2.6-Pro (79%) and GPT-6 Luna (max, 78%)

来源

Artificial Analysis