AI Models Find a Zero-Day Flaw for as Little as $4.24
Xint.io found that three of seven tested AI models discovered a privately reported Google V8 zero-day, CVE-2026-102321, according to ZDNET. GPT 6 Sol found it in 13 minutes for $4.24, while GPT 5.6 Sol required 44 minutes and $22; Claude Opus 5 succeeded on its first attempt at a reported cost of $43.40. DeepSeek and Z.ai models failed, and earlier models had missed the same flaw after 25 hours and $350 of scanning.
Xint.io’s findings suggest that scoped vulnerability research with frontier models is becoming substantially faster and cheaper, while also showing that success depends on the model and prompt guidance.

ZDNET’s key takeaways
- As AI advances, so does its ability to find zero-day vulnerabilities.
- Only three of seven AI models found a privately reported Google V8 bug.
- Finding a zero-day now costs as little as $4. Can defenders keep up?
Trending Now
I tried Claude Sheets on 3 tasks – and it saved me hours of work in 10 minutes 11/15/2026
#Xint.io#GPT 6 Sol#GPT 5.6 Sol#Claude Opus 5#Google V8#CVE-2026-102321#OpenAI#Anthropic#DeepSeek#Z.ai#Google Vulnerability Reward Program