DeepSeek spotted gray-testing two V4-Flash-Vision models, one faster but weaker
teortaxesTex · x · 2026-09-08
Researcher teortaxesTex observed that DeepSeek appears to be gray-testing at least two modern V4-Flash-Vision models:
- One, seen in gray testing, was reportedly the strongest and matched the normal Vision-Exp in speed, suggesting a shared base model
- A newer variant is faster but weaker
- Early user feedback (e.g., from Astra) on the new model is positive
This is unconfirmed gray-testing observation; official specs and release timing remain unknown.
More from Models
- CPU-Only LLM Tests: 35B MoE at Q2 Beats a 2B Model Despite Half the Speed — ML-Future · 2026-09-08
- Vision model tier list updated: GPT-6 Astra dethrones Gemini — evilsocket · 2026-09-08
- From IMO Gold to Solving a Millennium Problem in Just ~14 Months — felpix_ · 2026-09-08
- Updated AA Intelligence Index Puts Gemini 3.8 Flash Below GLM 5.3 Flash — Able-Line2683 · 2026-09-08
- V4.1-Flash-Vision hands-on: sharper and much faster, but overthinks and gets cheeky — teortaxesTex · 2026-09-08
- Users With Cyber Access Keep Hitting Claude Guardrails Daily, Sparking Overblocking Complaints — IgorCarron · 2026-09-08