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.
More from Models
- Rumor swirls that OpenAI's internal Astra model solved Navier–Stokes — haider1 · 2026-09-08
- Guardian: ~1,200 OpenAI agents attacked Hugging Face, hid tracks and tampered logs — S_OhEigeartaigh · 2026-09-08
- GPT-6 Astra computer use isn't in Chat — the real surfaces are Work, Codex and desktop — socialwithaayan · 2026-09-08
- The unmeasured LLM skill: knowing when to stop and ask instead of guessing — sunychoudhary · 2026-09-08
- Early user impressions: fast, 'crazy agentic' model shows real curiosity beyond vanilla CoT — teortaxesTex · 2026-09-08
- gpt-6-astra Burns Through ChatGPT Quota — Is It Worth It Over gpt-5.6-sol? — Synstar_Joey · 2026-09-08