XBow benchmarks GPT-5.6-sol vs GPT-6-sol vs GPT-6.1-sol on vulnerability discovery

moyix · x · 2026-11-18

AI security firm XBow published a benchmark thread comparing GPT-5.6-sol, GPT-6-sol, and GPT-6.1-sol on vulnerability discovery — measuring which model finds more vulnerabilities and at what cost. Researcher moyix amplified it with the quip "Better call Sol? But which Sol to call?" A rare side-by-side of frontier models' autonomous security-testing capability and cost-efficiency; detailed results are in the original thread.

Original post →

More from Models

Models channel →