Unverified75% confidenceOpinionTime unknown

DeepSeek在多模态（尤其是视觉）能力上相对Gemini有所不足

1

Sources

75%

Confidence

Medium-term (~90 days)

Relevance

6/1/2026

First Seen

Valid until: 8/30/2026

Sources

Browser-Use WebUI安装配置教程：AI浏览器自动化实战

bilibilikate人不错

Related Entities

DeepSeekmodel Geminimodel

Related Claims

UnverifiedDeepSeek系列模型在视觉能力上一直存在相对短板75% similar UnverifiedDeepSeek、ChatGPT、Gemini在狭义上属于大型语言模型（LLMs），而非代表人工智能的全部65% similar UnverifiedDeepSeek Math 7B 轻量版本在奥数和高等数学领域可追平乃至超越 GPT-4、Gemini Ultra 等闭源旗舰模型65% similar UnverifiedDeepSeek 的代码生成能力不及 Codex 等顶级方案，属于够用但非顶尖水平64% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/25437

API

curl https://kongchang.com/api/v1/knowledge/claims/25437

MCP

get_claim(id=25437)