Artificial Analysis· @ArtificialAnlys · X·· 2 小时前AI 评分39
AI 导读
Mistral Large 4(high)在 Artificial Analysis Cyber Index 上得分 51,在现有开源权重模型中排名第三,仅次于 DeepSeek V4.1 Flash 1017(max,57)和 MiMo-V2.6-Pro(56)。它在 CyberGym-E2E-AA 上与两者持平或更优(79% 对 76% 和 79%),但在 DeepsecBench-AA(15% 对 25% 和 26%)和 CWE-Bench-AA(58% 对 69% 和 63%)上落后。
正文
Mistral Large 4 (high) scores 51 on the Artificial Analysis Cyber Index, third among current open weights models behind DeepSeek V4.1 Flash 1017 (max, 57) and MiMo-V2.6-Pro (56). It matches or beats both on CyberGym-E2E-AA (79% vs. 76% and 79%), but trails them on DeepsecBench-AA (15% vs. 25% and 26%) and CWE-Bench-AA (58% vs. 69% and 63%)
来源:Artificial Analysis · x.com