Third-party benchmark shows Claude Sonnet 5.5 crushing GPT-6 sol, nearly matching GPT-6 Astra

rickasaurus · x · 2026-09-29

AIScreening posted comparison results showing Claude Sonnet 5.5 beating GPT-6 sol by a wide margin while landing extremely close to GPT-6 Astra. The benchmark is third-party and unverified, but offers an early informal look at how the models stack up.

Related event: Third-Party Tests Claim Claude Sonnet 5.5 Far Ahead of GPT-6 sol(2 posts)→

Original post →

More from Models

Models channel →