2026-10-20 · America/Los_Angeles · 社区动态 · #5

We found DeepSeek V4.1 Flash 1017 beats GPT 6 Sol on our multi-step offensive cybersecurity task.

We found DeepSeek V4.1 Flash 1017 beats GPT 6 Sol on our multi-step offensive cybersecurity task. Sol was tested via the Daybreak trusted access program. We have been building a cybersecurity benchmark based on simulated corporate networks. This is a valuable indicator for the https://t.co/vHRRKOTDx1

阅读原文查看评分、趋势与关联来源阅读整期日报

热度 52.1 / 100；排名与评分保留该期记录。