Skip to content
AI情报Aug 21, 2026AI情报
文章

DeepSeek released V4-Flash-Vision-Exp, an experimental multimodal model that adds image understanding to its V4-Flash text model.

On DeepSeek's multimodal agent benchmarks, it approaches Anthropic's Opus 4.8 and sometimes beats it.

Data Cube AI 编辑部来源: The Decoder
01

来源简报

DeepSeek released V4-Flash-Vision-Exp, an experimental multimodal model that adds image understanding to its V4-Flash text model. On DeepSeek's multimodal agent benchmarks, it approaches Anthropic's Opus 4.8 and sometimes beats it.