2026-10-20 · America/Los_Angeles · 社区动态 · #18

Vals AI found DeepSeek V4.1 Flash 1017 beats GPT 6 Sol on their multi-step offensive cybersecurity task. Sol was tested via the Daybreak trusted access program.

From Vals AI on 𝕏: https://x.com/ValsAI/status/2112471082397778083

热度 45.8 / 100；排名与评分保留该期记录。