Skip to content
View original post on X: 👩‍💻 Paige BaileyX· 44/100AI score44/100

Gemini 4 Argon finds 74% of known vulnerabilities on depthfirst benchmark

AISummary

Google's Paige Bailey announces Gemini 4 Argon for detecting security vulnerabilities at a lower price than competitors. In depthfirst's dfbench, Gemini 4 Argon found 74% of known vulnerabilities on application and smart-contract tasks, where it rarely refused. Across all 165 tasks it scored 67.5%, second only to Mythos 5 at 69%.

Post on XView on X
@DynamicWebPaige

🔐Gemini 4 Argon for detecting security vulnerabilities, at a lower price point than competitors:

Ram@PothamRam
We tested Gemini 4 Argon on @depthfirstlabs dfbench, our benchmark for finding real vulnerabilities in code. On application and smart-contract tasks, where it rarely refused, it found 74% of known vulnerabilities, the highest recall we have measured. Across all 165 tasks it scored 67.5%, second only to Mythos 5 (69%{.
View quoted post on X

Source: 👩‍💻 Paige Bailey · x.comPublished