Expired50% confidenceBenchmarkExact time
GLM-5.2's score on the Frontiers-WE benchmark improved from the low 30s in the previous generation to 74.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/9/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/7/2026(expired)
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's score on the Deeps-WE benchmark improved from 18 in the previous generation to 46.83% similarUnverifiedCompared to GLM 4.5, GLM 4.6 improves coding capability by 27% and reduces token consumption by 30%.69% similarUnverifiedDomestic models such as GLM5.1 have achieved scores on standard programming benchmarks like HumanEval and MBPP that are close to or even surpass some international competitors.65% similarUnverifiedIn early 2023, mainstream models' SWE-bench scores were generally below 5%; by mid-2025, top models had surpassed 70%.64% similarUnverifiedWhen GLM5's context length exceeds 200,000 tokens, a noticeable context rot problem occurs.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/403164API
curl https://kongchang.com/api/v1/knowledge/claims/403164MCP
get_claim(id=403164)