Vals says DeepSeek is nearing OpenAI’s most advanced cyber model
🎧 Listen to this story
Vals, a company that measures artificial intelligence capabilities, says open-weight models are catching up with the most advanced closed models on network-intrusion tasks. In two simulated scenarios, OpenAI’s most advanced cyber model, Daybreak, available only to trusted partners, completed an average of 81% of objectives across two tests; DeepSeek reached 73%, with the models tying on some tasks.
Vals says carrying out an attack cost $17 to $46 in tokens with GPT-6-Sol, compared with $2 to $3 with DeepSeek. The company says the lower cost and the ability to run open models on one’s own hardware could encourage their use by defense teams. Wired notes that the narrowing gap reduces closed models’ advantage and may limit the time gained through restricted access, although attackers still frequently use older, less capable models.
Why it matters · editorial interpretation
Vals’s evaluation suggests that the performance gap between open-weight and closed models on network-intrusion tasks may be narrowing, while lower costs and the ability to run models on one’s own hardware could make them easier for defense teams to use. The comparison also keeps restricted access relevant as an advantage for closed models, though that advantage may last for less time.
Sources
ResearchSecurity