zai-org/GLM-5.1
摘要
GLM-5.1 是一款新一代旗舰AI模型,针对代理工程进行了优化,编码能力显著增强,在SWE-Bench Pro上达到了最先进性能,并通过扩展迭代和工具使用展示了卓越的长周期任务处理能力。
查看缓存全文
缓存时间: 2026/04/20 14:45
zai-org/GLM-5.1 · Hugging Face
来源:https://huggingface.co/zai-org/GLM-5.1
👋 加入我们的微信 (https://raw.githubusercontent.com/zai-org/GLM-5/refs/heads/main/resources/wechat.png) 或 Discord (https://discord.gg/QR7SARHRxK) 社区。📖 阅读 GLM-5.1 博客 (https://z.ai/blog/glm-5.1) 和 GLM-5 技术报告 (https://arxiv.org/abs/2602.15763)。📍 在 Z.ai API 平台 (https://docs.z.ai/guides/llm/glm-5.1) 使用 GLM-5.1 API 服务。🔜 GLM-5.1 (https://chat.z.ai/) 即将在 chat.z.ai 上线。
[论文 (https://huggingface.co/papers/2602.15763)] [GitHub (https://github.com/zai-org/GLM-5)]
引言
GLM-5.1 是我们面向智能体工程的新一代旗舰模型,相比前代在编程能力上显著增强。它在 SWE-Bench Pro 上取得了最先进的性能,并在 NL2Repo(仓库生成)和 Terminal-Bench 2.0(真实终端任务)上以大幅优势领先 GLM-5。
bench_51 (https://raw.githubusercontent.com/zai-org/GLM-5/refs/heads/main/resources/bench_51.png)
但最有意义的飞跃超越了首次通过性能。前代模型(包括 GLM-5)往往过早用尽手段:它们应用熟悉的技术快速获得初始收益,然后陷入停滞。给它们更多时间也无济于事。
相比之下,GLM-5.1 旨在更长时间内保持智能体任务的有效性。我们发现该模型能更精准地处理模糊问题,并在更长的会话中保持高效产出。它能分解复杂问题、运行实验、读取结果,并精准定位阻碍。通过反复迭代,GLM-5.1 在数百轮对话和数千次工具调用中持续优化。运行时间越长,效果越好。
基准测试
| 基准 | GLM-5.1 | GLM-5 | Qwen3.6-Plus | MiniMax M2.7 | DeepSeek-V3.2 | Kimi K2.5 | Claude Opus 4.6 | Gemini 3.1 Pro | GPT-5.4 |
|---|---|---|---|---|---|---|---|---|---|
| HLE | 31.0 | 30.5 | 28.8 | 28.0 | 25.1 | 31.5 | 36.7 | 45.0 | 39.8 |
| HLE(带工具) | 52.3 | 50.4 | 50.6 | - | 40.8 | 51.8 | 53.1* | 51.4* | 52.1* |
| AIME 2026 | 95.3 | 95.4 | 95.1 | 89.8 | 95.1 | 94.5 | 95.6 | 98.2 | 98.7 |
| HMMT Nov. 2025 | 94.0 | 96.9 | 94.6 | 81.0 | 90.2 | 91.2 | 96.3 | 94.8 | 95.8 |
| HMMT Feb. 2026 | 82.6 | 82.8 | 87.8 | 72.7 | 79.8 | 81.9 | 84.3 | 87.3 | 91.8 |
| IMO AnswerBench | 83.8 | 82.5 | 83.8 | 66.3 | 78.3 | 81.8 | 75.3 | 81.0 | 91.4 |
| GPQA-Diamond | 86.2 | 86.0 | 90.4 | 87.0 | 82.4 | 87.6 | 91.3 | 94.3 | 92.0 |
| SWE-Bench Pro | 58.4 | 55.1 | 56.6 | 56.2 | - | 53.8 | 57.3 | 54.2 | 57.7 |
| NL2Repo | 42.7 | 35.9 | 37.9 | 39.8 | - | 32.0 | 49.8 | 33.4 | 41.3 |
| Terminal-Bench 2.0(Terminus-2) | 63.5 | 56.2 | 61.6 | - | 39.3 | 50.8 | 65.4 | 68.5 | - |
| Terminal-Bench 2.0(自报告最佳) | 69.0(Claude Code) | 56.2(Claude Code) | - | - | 57.0(Claude Code) | 46.4(Claude Code) | - | - | 75.1(Codex) |
| CyberGym | 68.7 | 48.3 | - | - | 17.3 | 41.3 | 66.6 | 38.8 | 66.3 |
| BrowseComp | 68.0 | 62.0 | - | - | 51.4 | 60.6 | - | - | - |
| BrowseComp(带上下文管理) | 79.3 | 75.9 | - | - | 67.6 | 74.9 | 84.0 | 85.9 | 82.7 |
| τ3-Bench | 70.6 | 69.2 | 70.7 | 67.6 | 69.2 | 66.0 | 72.4 | 67.1 | 72.9 |
| MCP-Atlas(公开集) | 71.8 | 69.2 | 74.1 | 48.8 | 62.2 | 63.8 | 73.8 | 69.2 | 67.2 |
| Tool-Decathlon | 40.7 | 38.0 | 39.8 | 46.3 | 35.2 | 27.8 | 47.2 | 48.8 | 54.6 |
| Vending Bench 2 | $5,634.41 | $4,432.12 | $5,114.87 | - | $1,034.00 | $1,198.46 | $8,017.59 | $911.21 | $6,144.18 |
本地部署 GLM-5.1
以下开源框架支持本地部署 GLM-5.1:
- SGLang (https://github.com/sgl-project/sglang)(v0.5.10+)—— 参见 cookbook (https://cookbook.sglang.io/autoregressive/GLM/GLM-5.1)
- vLLM (https://github.com/vllm-project/vllm)(v0.19.0+)—— 参见 recipes (https://github.com/vllm-project/recipes/blob/main/GLM/GLM5.md)
- xLLM (https://github.com/jd-opensource/xllm)(v0.8.0+)—— 参见 example (https://github.com/zai-org/GLM-5/blob/main/example/ascend.md)
- Transformers (https://github.com/huggingface/transformers)(v0.5.3+)—— 参见 transformers 文档 (https://github.com/huggingface/transformers/blob/main/docs/source/en/model_doc/glm_moe_dsa.md)
- KTransformers (https://github.com/kvcache-ai/ktransformers)(v0.5.3+)—— 参见 tutorial (https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/kt-kernel/GLM-5.1-Tutorial.md)
引用
如果您的研究中使用了 GLM-5.1 或 GLM-5,请引用我们的技术报告:
@misc{glm5team2026glm5vibecodingagentic, title={GLM-5: from Vibe Coding to Agentic Engineering}, author={GLM-5-Team and : and Aohan Zeng and Xin Lv and Zhenyu Hou and Zhengxiao Du and Qinkai Zheng and Bin Chen and Da Yin and Chendi Ge and Chenghua Huang and Chengxing Xie and Chenzheng Zhu and Congfeng Yin and Cunxiang Wang and Gengzheng Pan and Hao Zeng and Haoke Zhang and Haoran Wang and Huilong Chen and Jiajie Zhang and Jian Jiao and Jiaqi Guo and Jingsen Wang and Jingzhao Du and Jinzhu Wu and Kedong Wang and Lei Li and Lin Fan and Lucen Zhong and Mingdao Liu and Mingming Zhao and Pengfan Du and Qian Dong and Rui Lu and Shuang-Li and Shulin Cao and Song Liu and Ting Jiang and Xiaodong Chen and Xiaohan Zhang and Xuancheng Huang and Xuezhen Dong and Yabo Xu and Yao Wei and Yifan An and Yilin Niu and Yitong Zhu and Yuanhao Wen and Yukuo Cen and Yushi Bai and Zhongpei Qiao and Zihan Wang and Zikang Wang and Zilin Zhu and Ziqiang Liu and Zixuan Li and Bojie Wang and Bosi Wen and Can Huang and Changpeng Cai and Chao Yu and Chen Li and Chengwei Hu and Chenhui Zhang and Dan Zhang and Daoyan Lin and Dayong Yang and Di Wang and Ding Ai and Erle Zhu and Fangzhou Yi and Feiyu Chen and Guohong Wen and Hailong Sun and Haisha Zhao and Haiyi Hu and Hanchen Zhang and Hanrui Liu and Hanyu Zhang and Hao Peng and Hao Tai and Haobo Zhang and He Liu and Hongwei Wang and Hongxi Yan and Hongyu Ge and Huan Liu and Huanpeng Chu and Jia'ni Zhao and Jiachen Wang and Jiajing Zhao and Jiamin Ren and Jiapeng Wang and Jiaxin Zhang and Jiayi Gui and Jiayue Zhao and Jijie Li and Jing An and Jing Li and Jingwei Yuan and Jinhua Du and Jinxin Liu and Junkai Zhi and Junwen Duan and Kaiyue Zhou and Kangjian Wei and Ke Wang and Keyun Luo and Laiqiang Zhang and Leigang Sha and Liang Xu and Lindong Wu and Lintao Ding and Lu Chen and Minghao Li and Nianyi Lin and Pan Ta and Qiang Zou and Rongjun Song and Ruiqi Yang and Shangqing Tu and Shangtong Yang and Shaoxiang Wu and Shengyan Zhang and Shijie Li and Shuang Li and Shuyi Fan and Wei Qin and Wei Tian and Weining Zhang and Wenbo Yu and Wenjie Liang and Xiang Kuang and Xiangmeng Cheng and Xiangyang Li and Xiaoquan Yan and Xiaowei Hu and Xiaoying Ling and Xing Fan and Xingye Xia and Xinyuan Zhang and Xinze Zhang and Xirui Pan and Xu Zou and Xunkai Zhang and Yadi Liu and Yandong Wu and Yanfu Li and Yidong Wang and Yifan Zhu and Yijun Tan and Yilin Zhou and Yiming Pan and Ying Zhang and Yinpei Su and Yipeng Geng and Yong Yan and Yonglin Tan and Yuean Bi and Yuhan Shen and Yuhao Yang and Yujiang Li and Yunan Liu and Yunqing Wang and Yuntao Li and Yurong Wu and Yutao Zhang and Yuxi Duan and Yuxuan Zhang and Zezhen Liu and Zhengtao Jiang and Zhenhe Yan and Zheyu Zhang and Zhixiang Wei and Zhuo Chen and Zhuoer Feng and Zijun Yao and Ziwei Chai and Ziyuan Wang and Zuzhou Zhang and Bin Xu and Minlie Huang and Hongning Wang and Juanzi Li and Yuxiao Dong and Jie Tang}, year={2026}, eprint={2602.15763}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2602.15763}, }
相似文章
zai-org/GLM-5.2 来了!
Z.AI 发布了 GLM-5.2,这是一款新的旗舰模型,拥有稳定的 1M token 上下文窗口,通过灵活的思考努力增强了编码能力,并通过 IndexShare 改进了架构。该模型在 MIT 开源许可证下发布。
GLM-5.2: 专为长程任务打造
Z.AI推出GLM-5.2,这是一款专为长程任务设计的旗舰模型,拥有稳定的100万token上下文、改进的编码能力以及MIT开源许可证,在与Opus 4.8和GPT-5.5等领先模型的对比中展现了竞争力。
zai-org/GLM-5
zai-org 发布 GLM-5 系列,其中 GLM-5.2 在代码基准测试中取得了开源模型最佳性能,支持 100 万 token 上下文,并采用 IndexShare 稀疏注意力机制改进架构。
GLM 5.2 是一款猛兽级模型
GLM 5.2 是一款强大的新AI模型发布,可能来自智谱AI,其性能被形容为猛兽。
zai-org/GLM-5.2-FP8
Z.AI 发布 GLM-5.2,一款旗舰级开源模型,拥有可靠的 1M token 上下文窗口,改进的编码能力,以及新的 IndexShare 稀疏注意力架构,在 1M 上下文下 FLOPs 减少了 2.9 倍。