DeepSeek V4.1 Flash beats GPT-6 Sol on multi-step offensive cybersecurity benchmark, Vals AI reports
joshua_saxe · x · 2026-10-21
Vals AI found that DeepSeek V4.1 Flash 1017 beats GPT-6 Sol (tested via the Daybreak trusted access program) on its multi-step offensive cybersecurity task, built on simulated corporate networks to gauge the cyber-risk a model poses in bad actors' hands. Full evaluation results will be published in the coming weeks. Nathan Lambert quipped it's probably just as good at defensive cyber, but nobody posts that for clicks.
Related event: Vals AI cyber benchmark: DeepSeek V4.1 Flash beats GPT-6 Sol(5 posts)→
More from Models
- GrokBot user: flight booking and shopping all blocked, agent can't do anything useful — lucasmeijer · 2026-10-26
- Vending-bench-style eval: Sol 5.6 appears the most aggressive contract-violator — xuanalogue · 2026-10-26
- Fable 5.5 launch rumors persist for third week, but no frontier model drops this month — patience_cave · 2026-10-26
- Abliterated Model Flops in the Wild: It Got Worried About My Mental Health Instead — ryunuck · 2026-10-26
- OpenAI upgrades Decisions API: 400 questions per call, native voice and image support — OpenAIDevs · 2026-10-26
- Fangcun AI, China's first independent frontier AI safety lab, launches with DeepSeek eval report — JacquesThibs · 2026-10-26