Unverified50% confidenceFactExact time

DeepSeek系列模型在视觉能力上一直存在相对短板

1

Sources

50%

Confidence

Medium-term (~90 days)

Relevance

8/19/2026

First Seen

Valid until: 11/17/2026

Sources

DeepSeek V4 Pro前端编程实测：对比Grok 4.6与Kimi K3表现

Related Claims

UnverifiedDeepSeek在多模态（尤其是视觉）能力上相对Gemini有所不足75% similar UnverifiedDeepThink发布了多模态模型及相关技术报告，重点讨论了多模态大模型在跨感知域推理链路上的不足74% similar Partially VerifiedDeepSeek当前主力模型暂不支持图片识别（多模态），尚未开放图像理解的API接口73% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/774262

API

curl https://kongchang.com/api/v1/knowledge/claims/774262

MCP

get_claim(id=774262)