deepseek-v4.1IMAGE
WebExploitBench 攻防测试：V4.1 Flash 42.86%，落后 Kimi K3.1 Pro
黑盒网络安全实战基准 WebExploitBench 上，Kimi-K3.1-Pro 以 46.43% 居首，DeepSeek-V4.1-Flash-1017 以 42.86% 第二，GLM-5.3-Flash 35.71% 第三。
Migel Tissera
@migtissera3 天前收录原推发布于 2026.10.25
Migel Tissera @migtissera原推发布于 2026.10.25
Wow.. 😲 Here's definitive results of Kimi-K3.1-Pro's offensive cybersecurity capabilities. These are black-box engagements, run on WebExploitBench. 🥇Kimi-K3.1-Pro — 46.43% 🥈DeepSeek-V4.1-Flash-1017 — 42.86% 🥉GLM-5.3-Flash — 35.71%
x.com/migtissera/status/2114029692147950008采集于 2026.10.25 12:01