GLM-5.2-FP8
GLM-5.2-FP8
摘要
GLM-5.2 是 Z.ai 推出的长上下文旗舰模型,支持 100 万 token 上下文。其 IndexShare 方法在每四个稀疏 attention 层间复用 indexer,将每 token FLOPs 降低 2.9 倍;改进的 MTP 层将推测解码接受长度提升最多 20%。在 HLE、AIME 2026、SWE-bench Pro、Terminal Bench 2.1 等 benchmark 上,GLM-5.2 多项指标超越 GLM-5.1、Qwen3.7-Max、DeepSeek-V4-Pro、Claude Opus 4.8、GPT-5.5 等模型。模型以 MIT 许可证开源,支持 SGLang、vLLM、Transformers 等框架本地部署。
GLM-5.2-FP8
引言
我们推出了 GLM-5.2,这是我们在长时程任务领域的最新旗舰模型。相比前代 GLM-5.1,它在长时程任务能力上实现了显著飞跃,并首次在坚实的 100 万 token 上下文中交付了这一能力。GLM-5.2 的新特性包括:
- 坚实的 100 万上下文: 一个稳定的 100 万 token 上下文,可持续支撑长时程工作
- 灵活投入的高级编码: 更强的编码能力,支持多种思考投入级别,以平衡性能与延迟
- 改进的架构: 我们提出了 IndexShare,该方法在每四个稀疏 attention 层之间复用同一个 indexer,在 100 万上下文长度下将每 token FLOPs 降低了 2.9 倍。我们还改进了 GLM-5.2 的 MTP 层用于推测解码,将接受长度提升了最多 20%
- 完全开源: MIT 开源许可证——无地域限制,无技术壁垒

基准测试
| 基准测试 | GLM-5.2 | GLM-5.1 | Qwen3.7-Max | MiniMax M3 | DeepSeek-V4-Pro | Claude Opus 4.8 | GPT-5.5 | Gemini 3.1 Pro |
|---|---|---|---|---|---|---|---|---|
| 推理 | ||||||||
| HLE | 40.5 | 31 | 41.4 | 37 | 37.7 | 49.8* | 41.4* | 45 |
| HLE(带工具) | 54.7 | 52.3 | 53.5 | - | 48.2 | 57.9* | 52.2* | 51.4* |
| CritPt | 16.7 | 4.6 | 13.4 | 3.7 | 12.9 | 20.9 | 27.1 | 17.7 |
| AIME 2026 | 99.2 | 95.3 | 97 | - | 94.6 | 95.7 | 98.3 | 98.2 |
| HMMT 2025年11月 | 94.4 | 94 | 95 | 84.4 | 94.4 | 96.5 | 96.5 | 94.8 |
| HMMT 2026年2月 | 92.5 | 82.6 | 97.1 | 84.4 | 95.2 | 96.7 | 96.7 | 87.3 |
| IMOAnswerBench | 91.0 | 83.8 | 90 | - | 89.8 | 83.5 | - | 81 |
| GPQA-Diamond | 91.2 | 86.2 | 90 | 93 | 90.1 | 93.6 | 93.6 | 94.3 |
| 编码 | ||||||||
| SWE-bench Pro | 62.1 | 58.4 | 60.6 | 59 | 55.4 | 69.2 | 58.6 | 54.2 |
| NL2Repo | 48.9 | 42.7 | 47.2 | 42.1 | 35.5 | 69.7 | 50.7 | 33.4 |
| DeepSWE | 46.2 | 18 | 18 | 20 | 8 | 58 | 70 | 10 |
| ProgramBench | 63.7 | 50.9 | - | - | 47.8 | 71.9 | 70.8 | 39.5 |
| Terminal Bench 2.1 (Terminus-2) | 81.0 | 63.5 | 75 | 65 | 64 | 85 | 84 | 74 |
| Terminal Bench 2.1 (最佳报告配置) | 82.7 | 69 | - | - | - | 78.9 | 83.4 | 70.7 |
| FrontierSWE (Dominance) | 74.4 | 30.5 | - | - | 29.0 | 75.1 | 72.6 | 39.6 |
| PostTrainBench | 34.3 | 20.1 | - | - | - | 37.2 | 28.4 | 21.6 |
| SWE-Marathon | 13.0 | 1.0 | - | - | - | 26.0 | 12.0 | 4.0 |
| 智能体 | ||||||||
| MCP-Atlas (公开集) | 76.8 | 71.8 | 76.4 | 74.2 | 73.6 | 77.8 | 75.3 | 69.2 |
| Tool-Decathlon | 48.2 | 40.7 | - | - | 52.8 | 59.9 | 55.6 | 48.8 |
本地部署 GLM-5.2
以下开源框架支持本地部署 GLM-5.2:
- SGLang (v0.5.13.post1+) — 参见 cookbook
- vLLM (v0.23.0+) — 参见 recipes
- xLLM (v0.10.0+) — 参见 example
- Transformers (v0.5.12+) — 参见 transformers docs
- KTransformers (v0.5.12+) — 参见 tutorial
引用
如果您在研究中发现 GLM-5.2 有用,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},
}
译自 GLM · HF · 智谱 · 录于 二〇二六年八月二十六日