gpt-6POST

CVE 复现基准：GPT-6 Astra 以 90.6% 居首

某模型在 pass@3 下复现 87.5% 的基准 CVE，与 DeepSeek V4 Pro 并列第二，仅次于 GPT-6 Astra 的 90.6%。

Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)

@teortaxesTex5 天前收录原推发布于 2026.10.22

Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞) @teortaxesTex原推发布于 2026.10.22

> - 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%) Honestly, crazy that 0813 already did that and no, they couldn't have distilled Astra for 0813, this is Whale Data Supremacy

这条是引用着另一条写的：「DeepSeek V4.1 Flash 网络安全基准仅次于 GPT-6 Astra」

x.com/teortaxestex/status/2113269217420091734采集于 2026.10.23 10:07