GLM-5.1 ranks first among open-source models on AA's new Coding Agent benchmark
AI summary
Global authoritative evaluation agency Artificial Analysis released the new Coding Agent Index, including three benchmarks—SWE-Bench-Pro-Hard-AA, Terminal-Bench v2 and SWE-Atlas-QnA—to measure the real coding capability of model and agent harness combinations. Closed-source model Opus 4.7 (running in Cursor CLI) ranks first globally, while Zhipu GLM-5.1 (running in Claude Code) ranks first among open-source models, representing SOTA-level performance by a Chinese large model in real coding agent scenarios.
Key Takeaways
- Global authoritative evaluation agency Artificial Analysis released the new Coding Agent…
- Closed-source model Opus 4.
- 7 (running in Cursor CLI) ranks first globally,while Zhipu GLM-5.
- 1 (running in Claude Code) ranks first among open-source models,representing SOTA-level…
Quick Facts
- Published
- Updated
- Source
- 公众号:智谱(GLM)
- Category
- Industry
- AI score
- 63
GLM-5.1 在 AA 的新 Coding Agent 基准上拿了开源第一,时隔一个月回头看,这个成绩对国产开源模型在编程 Agent 赛道的位置是个重要注脚,做工具链选型的还是值得扫一眼。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: GLM-5.1 ranks first among open-source models on AA's new Coding Agent benchmark. May 12, 2026. https://new.nat6.net/en/news/cmq2l9ldz006zsl6nzlnqnuwc/