Vision model tier list updated: GPT-6 Astra dethrones Gemini

evilsocket · x · 2026-09-08

@skalskip92 updated the vision model tier list with GPT-6 Astra and Gemini 3.8 Flash, concluding that "Gemini is dethroned."

The author calls GPT-6 Astra the best "vision" model yet: it notices tiny details, draws conclusions, produces precise tight bounding boxes, reads text across contexts, has broad knowledge, and is fast—though expensive. A deep dive into its detection abilities is linked at the end.

Original post →

More from Models

Models channel →