Deepseek releases experimental Flash vision model rivaling Opus 4.8
The Decoder · rss · 2026-08-22
Deepseek has released V4-Flash-Vision-Exp, an experimental multimodal model adding image understanding to the V4-Flash text model. On internal multimodal agent benchmarks, it approaches and sometimes beats Opus 4.8.
More from Multimodal
- fal launches Worlds for real-time creation and interaction with AI-generated worlds — Scobleizer · 2026-10-16
- Gummy worms as a physics test: Gemini 4 Argon vs. Claude Opus 5.5 elasticity sims — DynamicWebPaige · 2026-10-16
- 260M-parameter looped diffusion transformer beats 6x larger baselines with 5x less compute — burkov · 2026-10-16
- Seedance 2.5 demo: stretching one second of an explosion into a 30-second shot — LudovicCreator · 2026-10-16
- Octopus Short Film Made with Grok Imagine, Upscaled via Topaz — creatoroff · 2026-10-16
- Open-sourced 61-second computing history film generated entirely by Muse Spark — sophiamyang · 2026-10-16