WHAT NEW IN X11.03 TUE

X 上的 AI 合集档案 · 22 个合集 · 66,612 条

gpt-6IMAGE

Mistral Large 4 网络安全基准超过 GPT-6 Astra

帖称 Mistral Large 4 在安全类基准上胜过 Opus 5.5 与 Astra,主因是后两者约四成安全任务被自家过滤器拦下。

Cline
@cline27 天前收录原推发布于 2026.10.07
Mistral Large 4 网络安全基准超过 GPT-6 Astra
Cline @cline原推发布于 2026.10.07
在 X 上打开原推

Mistral Large 4 beats Opus 5.5 and GPT-6 Astra on cybersecurity benchmarks, largely because it refuses far fewer security tasks. Meanwhile Opus and Astra had ~40% of tasks blocked by their own safety filters.

x.com/cline/status/2107561157787824347采集于 2026.10.07 10:10