WHAT NEW IN X10.28 WED

X 上的 AI 合集档案 · 22 个合集 · 58,924 条

benchmarkIMAGE

DeepSeek V4.1 Flash 网络安全基准仅次于 GPT-6 Astra

在作者自建的 CVE 复现基准上,DeepSeek V4.1 Flash 的 pass@3 达 87.5%,仅次于 GPT-6 Astra 的 90.6%;单次召回追平 Opus 5,每个漏洞成本 2.40 美元,比 Astra 便宜 56 倍。

pilvar (Philippe Dourassov)
@pilvar2225 天前收录原推发布于 2026.10.22
DeepSeek V4.1 Flash 网络安全基准仅次于 GPT-6 Astra
pilvar (Philippe Dourassov) @pilvar222原推发布于 2026.10.22
在 X 上打开原推

Unsurprisingly, DeepSeek V4.1 Flash 1017 is mogging all other models on our cybersecurity benchmark - At pass@3, it rediscovered 87.5% of the benchmark CVEs (28/32). That ties DeepSeek V4 Pro 0813 for 2nd place, behind only GPT-6 Astra (90.6%) - Single-run recall is 70.8%, matching Opus 5 and Grok 4.7. The previous Flash was at 65.6% - Precision went from 78.9% to 86.4%, so most false positives are now gone Cost: $2.40 per CVE found. That’s 27x cheaper than Opus 5 ($64.96) and 56x cheaper than Astra ($135.23) @deepseek_ai keeps pushing the Pareto frontier 1/4 🧵

x.com/pilvar222/status/2113260594547524087采集于 2026.10.23 10:07