Feed Entities Podcasts Deep Dives Developers About

[KongchangAI]

Real-time AI knowledge base. Every claim is traceable to its source, with data freshness under 24 hours.

Powered by 240+ first-hand AI sources

Knowledge

Feed
Hot Entities
Podcasts

Developers

CLI
MCP Server
REST API
About

© 2026 KongchangAI. The freshest, most accurate AI knowledge

Unverified50% confidenceBenchmarkExact time

GLM-5.2 在 Deeps-WE 基准上从上一代的18提升到46

1

Sources

50%

Confidence

Medium-term (~90 days)

Relevance

7/9/2026

First Seen

Valid until: 10/7/2026

Sources

GLM-5.2发布：开源编程能力首次逼近闭源旗舰模型

bilibili五里墩茶社6/22/2026

Related Claims

UnverifiedGLM-5.2 在 Frontiers-WE 基准上从上一代的30出头提升到7483% similar UnverifiedGLM5的上下文长度超过20万token时会出现明显的上下文腐烂问题67% similar UnverifiedGLM 4.6相较于GLM 4.5，代码能力提升27%，token消耗降低30%65% similar UnverifiedGLM5.1等国产模型在HumanEval、MBPP等标准编程基准测试上的得分已接近甚至超越部分国际竞品64% similar Unverified根据智谱公布的评测数据，GLM 5.2在多个基准上仅落后于Anthropic的Claude 4.8和OpenAI的部分顶级模型，稳居行业第二梯队63% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/403165

API

curl https://kongchang.com/api/v1/knowledge/claims/403165

MCP

get_claim(id=403165)