Unverified85% confidenceFactTime unknown

此前主流模型的上下文长度通常在8K到128K之间

1

Sources

85%

Confidence

Long-term

Relevance

5/31/2026

First Seen

Sources

DeepSeek V4深度解析：万亿参数开源模型碾压闭源对手

bilibili马士兵学堂

Related Claims

Unverified最新模型的上下文长度已达128K token82% similar Verified当前主流模型的上下文窗口约为128K至100万Token75% similar Partially Verified嵌入模型生成的向量通常为768维或1536维71% similar Unverified当前最先进的大语言模型已经支持128K甚至200K的上下文长度71% similar VerifiedQwen系列模型支持8K到128K不等的上下文窗口69% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/13897

API

curl https://kongchang.com/api/v1/knowledge/claims/13897

MCP

get_claim(id=13897)