DeepSeek V4 Flash gains vision: multimodal agent performance nears Opus 4.8
haider1 · x · 2026-08-21
DeepSeek officially launched the experimental multimodal model DeepSeek-V4-Flash-Vision-Exp, available via API as model='deepseek-v4-flash-vision-exp'. It matches V4-Flash on text (agents, reasoning, world knowledge) while making a major leap on multimodal agent benchmarks, closing in on Opus-4.8. DeepSeek Harness 0.1.1 shipped the same day with out-of-the-box support.
The retweeter's testing found it even stronger than the 0731 build on tasks that have nothing to do with vision.
Related event: DeepSeek Launches V4-Flash-Vision-Exp, Closing In on Opus 4.8(29 posts)→
More from Models
- Meta's open-weight Muse Spark Open hits Ollama with 1M-token context and Claude Code support — ollama · 2026-10-16
- 'Opus 5.5' collage demos spark claim: models have taste, no moat — yuwen_lu_ · 2026-10-16
- PrismML ships Bonsai 2 ternary models: 9B fits in 2GB for local AI — gajesh · 2026-10-16
- Apple MLX Runs 816B Muse Spark Open at 36+ Tokens/s on Four Mac Studios — andrejusb · 2026-10-16
- vLLM Ships Day-0 Support for Meta's 816B Open-Weight Muse Spark Open — woosuk_k · 2026-10-16
- Same 3 Coding Packets, Two Agents: Claude Opus 5.5 Beats Gemini 3.8 Flash on Every One — umeshonai · 2026-10-16