DeepSeek launches V4-Flash-Vision-Exp, multimodal agent performance nears Opus-4.8
OwariDa · x · 2026-08-22
DeepSeek officially launched the experimental multimodal model DeepSeek-V4-Flash-Vision-Exp on its API platform: text capabilities (agents, reasoning, world knowledge) match V4-Flash, while multimodal agent benchmarks take a major leap, approaching Opus-4.8. Available via model='deepseek-v4-flash-vision-exp'; the simultaneously released DeepSeek Harness 0.1.1 supports it out of the box. The retweeter jokes that it being "strictly stronger than 0731" was because it was a blinded VLM all along.
More from Fun
- Galbot-trained humanoid robots to play tennis with celebrities at Beijing robot games — ArtificialOther · 2026-08-22
- Counter-intuitive take: The future is e-ink, not agents — martyamark · 2026-08-22
- Qwen-3.8 27B Uncensored Model Tested: Discussing Cortés Without Moral Lectures — doodlestein · 2026-08-22
- Dev gets a fully custom C+CUDA Minecraft rewrite with his favorite server built for fun — yacineMTB · 2026-08-22
- 5 agents fight for browser while I task a 6th to fix infrastructure — yacineMTB · 2026-08-22
- Meme: reject modern eye-blobs, embrace tradition (Clippy) — joonasvirtanen · 2026-08-22