We Benchmarked Frontier LLMs on Defensive Security. The Results Surprised Us

Posted by logancarmody on Tuesday November 18, 2025 @09:56AM
from the cotool.ai dept.

( 2 comments | 4 points | on HN )

Re:We Benchmarked Frontier LLMs on Defensive Security. The R... by mmpollard on Tuesday November 18, 2025 @10:16AM (#45967325)

Interesting. I wonder if Gemini 3 reverses that performance trend or if the agent harness lended itself to OpenAI / Anthropic more than Google.

Would like to see this on more open-source agent harnesses and tools.

[ Parent | on HN ]

Re:We Benchmarked Frontier LLMs on Defensive Security. The R... by hunterwalk on Tuesday November 18, 2025 @11:18AM (#45968229)

agreed - would be interesting

[ Parent | on HN ]