Expired60% confidenceFactTime unknown
Domestic 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.
1
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 8/29/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedGLM 5.2 is a high-performance open-source model that reportedly achieves performance close to or even surpassing Opus 4.8 at one-sixth of the price.73% similarUnverifiedOn professional code benchmarks such as HumanEval, the performance of top models has approached or even surpassed average human-level performance.72% similarUnverifiedAccording to benchmark data published by Zhipu, GLM 5.2 trails only Anthropic's Claude 4.8 and certain top-tier OpenAI models across multiple benchmarks, firmly placing it in the industry's second tier.68% similarUnverified斯坦福HAI研究所2023年报告显示，最新LLM在HumanEval等代码基准测试中正确率已超过85%，远超2021年的不足50%67% similarUnverifiedOn mainstream evaluations such as MMLU, HumanEval, and GSM8K, the score gaps among leading large models are often only a few percentage points.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/13490API
curl https://kongchang.com/api/v1/knowledge/claims/13490MCP
get_claim(id=13490)