The Decoder· Matthias Bastian·· 8 d ago
The gap between open and closed AI models in cyber capabilities keeps shrinking
The gap between open and closed AI models in cyber capabilities keeps shrinking
AI summary
In the Vals AI benchmark, OpenAI's GPT-6 Sol Daybreak hits 80.8 percent of attack objectives in simulated corporate networks. Worse, the open-weight model DeepSeek V4.1 Flash reaches 72.8 percent at a tenth of the cost. Because open models can no longer be restricted, analysts say the window for defenders is shrinking fast.
Selection record
Threshold 76Media and individualsFirst 78Second 78
AdmittedSum of both 156 ≥ twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：评测开源与闭源AI模型网络攻防能力
- Why it was chosen
- Vals AI's attack-and-defence benchmark shows open models are closing in on closed frontier models on long-horizon cyberattack tasks, at a tenth of the cost.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: The Decoder · the-decoder.com