Staff View: :: Library Catalog

Saved in:

Bibliographic Details
Main Authors:	5 Team, Zeng, Aohan, Lv, Xin, Zheng, Qinkai, Hou, Zhenyu, Chen, Bin, Xie, Chengxing, Wang, Cunxiang, Yin, Da, Zeng, Hao, Zhang, Jiajie, Wang, Kedong, Zhong, Lucen, Liu, Mingdao, Lu, Rui, Cao, Shulin, Zhang, Xiaohan, Huang, Xuancheng, Wei, Yao, Cheng, Yean, An, Yifan, Niu, Yilin, Wen, Yuanhao, Bai, Yushi, Du, Zhengxiao, Wang, Zihan, Zhu, Zilin, Zhang, Bohan, Wen, Bosi, Wu, Bowen, Xu, Bowen, Huang, Can, Zhao, Casey, Cai, Changpeng, Yu, Chao, Li, Chen, Ge, Chendi, Huang, Chenghua, Zhang, Chenhui, Xu, Chenxi, Zhu, Chenzheng, Li, Chuang, Yin, Congfeng, Lin, Daoyan, Yang, Dayong, Jiang, Dazhi, Ai, Ding, Zhu, Erle, Wang, Fei, Pan, Gengzheng, Wang, Guo, Sun, Hailong, Li, Haitao, Li, Haiyang, Hu, Haiyi, Zhang, Hanyu, Peng, Hao, Tai, Hao, Zhang, Haoke, Wang, Haoran, Yang, Haoyu, Liu, He, Zhao, He, Liu, Hongwei, Yan, Hongxi, Liu, Huan, Chen, Huilong, Li, Ji, Zhao, Jiajing, Ren, Jiamin, Jiao, Jian, Zhao, Jiani, Yan, Jianyang, Wang, Jiaqi, Gui, Jiayi, Zhao, Jiayue, Liu, Jie, Li, Jijie, Li, Jing, Lu, Jing, Wang, Jingsen, Yuan, Jingwei, Li, Jingxuan, Du, Jingzhao, Du, Jinhua, Liu, Jinxin, Zhi, Junkai, Gao, Junli, Wang, Ke, Yang, Lekang, Xu, Liang, Fan, Lin, Wu, Lindong, Ding, Lintao, Wang, Lu, Zhang, Man, Li, Minghao, Xu, Minghuan, Zhao, Mingming, Zhai, Mingshu, Du, Pengfan, Dong, Qian, Lei, Shangde, Tu, Shangqing, Yang, Shangtong, Lu, Shaoyou, Li, Shijie, Li, Shuang, Shuang-Li, Yang, Shuxun, Yi, Sibo, Yu, Tianshu, Tian, Wei, Wang, Weihan, Yu, Wenbo, Tam, Weng Lam, Liang, Wenjie, Liu, Wentao, Wang, Xiao, Jia, Xiaohan, Gu, Xiaotao, Ling, Xiaoying, Wang, Xin, Fan, Xing, Pan, Xingru, Zhang, Xinyuan, Zhang, Xinze, Fu, Xiuqing, Zhang, Xunkai, Xu, Yabo, Wu, Yandong, Lu, Yida, Wang, Yidong, Zhou, Yilin, Pan, Yiming, Zhang, Ying, Wang, Yingli, Li, Yingru, Su, Yinpei, Geng, Yipeng, Zhu, Yitong, Yang, Yongkun, Li, Yuhang, Wu, Yuhao, Li, Yujiang, Liu, Yunan, Wang, Yunqing, Li, Yuntao, Zhang, Yuxuan, Liu, Zezhen, Yang, Zhen, Zhou, Zhengda, Qiao, Zhongpei, Feng, Zhuoer, Liu, Zhuorui, Zhang, Zichen, Yao, Zijun, Wang, Zikang, Liu, Ziqiang, Chai, Ziwei, Li, Zixuan, Zhao, Zuodong, Chen, Wenguang, Zhai, Jidong, Xu, Bin, Huang, Minlie, Wang, Hongning, Li, Juanzi, Dong, Yuxiao, Tang, Jie
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	https://arxiv.org/abs/2508.06471
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866908482545909760
author	5 Team Zeng, Aohan Lv, Xin Zheng, Qinkai Hou, Zhenyu Chen, Bin Xie, Chengxing Wang, Cunxiang Yin, Da Zeng, Hao Zhang, Jiajie Wang, Kedong Zhong, Lucen Liu, Mingdao Lu, Rui Cao, Shulin Zhang, Xiaohan Huang, Xuancheng Wei, Yao Cheng, Yean An, Yifan Niu, Yilin Wen, Yuanhao Bai, Yushi Du, Zhengxiao Wang, Zihan Zhu, Zilin Zhang, Bohan Wen, Bosi Wu, Bowen Xu, Bowen Huang, Can Zhao, Casey Cai, Changpeng Yu, Chao Li, Chen Ge, Chendi Huang, Chenghua Zhang, Chenhui Xu, Chenxi Zhu, Chenzheng Li, Chuang Yin, Congfeng Lin, Daoyan Yang, Dayong Jiang, Dazhi Ai, Ding Zhu, Erle Wang, Fei Pan, Gengzheng Wang, Guo Sun, Hailong Li, Haitao Li, Haiyang Hu, Haiyi Zhang, Hanyu Peng, Hao Tai, Hao Zhang, Haoke Wang, Haoran Yang, Haoyu Liu, He Zhao, He Liu, Hongwei Yan, Hongxi Liu, Huan Chen, Huilong Li, Ji Zhao, Jiajing Ren, Jiamin Jiao, Jian Zhao, Jiani Yan, Jianyang Wang, Jiaqi Gui, Jiayi Zhao, Jiayue Liu, Jie Li, Jijie Li, Jing Lu, Jing Wang, Jingsen Yuan, Jingwei Li, Jingxuan Du, Jingzhao Du, Jinhua Liu, Jinxin Zhi, Junkai Gao, Junli Wang, Ke Yang, Lekang Xu, Liang Fan, Lin Wu, Lindong Ding, Lintao Wang, Lu Zhang, Man Li, Minghao Xu, Minghuan Zhao, Mingming Zhai, Mingshu Du, Pengfan Dong, Qian Lei, Shangde Tu, Shangqing Yang, Shangtong Lu, Shaoyou Li, Shijie Li, Shuang Shuang-Li Yang, Shuxun Yi, Sibo Yu, Tianshu Tian, Wei Wang, Weihan Yu, Wenbo Tam, Weng Lam Liang, Wenjie Liu, Wentao Wang, Xiao Jia, Xiaohan Gu, Xiaotao Ling, Xiaoying Wang, Xin Fan, Xing Pan, Xingru Zhang, Xinyuan Zhang, Xinze Fu, Xiuqing Zhang, Xunkai Xu, Yabo Wu, Yandong Lu, Yida Wang, Yidong Zhou, Yilin Pan, Yiming Zhang, Ying Wang, Yingli Li, Yingru Su, Yinpei Geng, Yipeng Zhu, Yitong Yang, Yongkun Li, Yuhang Wu, Yuhao Li, Yujiang Liu, Yunan Wang, Yunqing Li, Yuntao Zhang, Yuxuan Liu, Zezhen Yang, Zhen Zhou, Zhengda Qiao, Zhongpei Feng, Zhuoer Liu, Zhuorui Zhang, Zichen Wang, Zihan Yao, Zijun Wang, Zikang Liu, Ziqiang Chai, Ziwei Li, Zixuan Zhao, Zuodong Chen, Wenguang Zhai, Jidong Xu, Bin Huang, Minlie Wang, Hongning Li, Juanzi Dong, Yuxiao Tang, Jie
author_facet	5 Team Zeng, Aohan Lv, Xin Zheng, Qinkai Hou, Zhenyu Chen, Bin Xie, Chengxing Wang, Cunxiang Yin, Da Zeng, Hao Zhang, Jiajie Wang, Kedong Zhong, Lucen Liu, Mingdao Lu, Rui Cao, Shulin Zhang, Xiaohan Huang, Xuancheng Wei, Yao Cheng, Yean An, Yifan Niu, Yilin Wen, Yuanhao Bai, Yushi Du, Zhengxiao Wang, Zihan Zhu, Zilin Zhang, Bohan Wen, Bosi Wu, Bowen Xu, Bowen Huang, Can Zhao, Casey Cai, Changpeng Yu, Chao Li, Chen Ge, Chendi Huang, Chenghua Zhang, Chenhui Xu, Chenxi Zhu, Chenzheng Li, Chuang Yin, Congfeng Lin, Daoyan Yang, Dayong Jiang, Dazhi Ai, Ding Zhu, Erle Wang, Fei Pan, Gengzheng Wang, Guo Sun, Hailong Li, Haitao Li, Haiyang Hu, Haiyi Zhang, Hanyu Peng, Hao Tai, Hao Zhang, Haoke Wang, Haoran Yang, Haoyu Liu, He Zhao, He Liu, Hongwei Yan, Hongxi Liu, Huan Chen, Huilong Li, Ji Zhao, Jiajing Ren, Jiamin Jiao, Jian Zhao, Jiani Yan, Jianyang Wang, Jiaqi Gui, Jiayi Zhao, Jiayue Liu, Jie Li, Jijie Li, Jing Lu, Jing Wang, Jingsen Yuan, Jingwei Li, Jingxuan Du, Jingzhao Du, Jinhua Liu, Jinxin Zhi, Junkai Gao, Junli Wang, Ke Yang, Lekang Xu, Liang Fan, Lin Wu, Lindong Ding, Lintao Wang, Lu Zhang, Man Li, Minghao Xu, Minghuan Zhao, Mingming Zhai, Mingshu Du, Pengfan Dong, Qian Lei, Shangde Tu, Shangqing Yang, Shangtong Lu, Shaoyou Li, Shijie Li, Shuang Shuang-Li Yang, Shuxun Yi, Sibo Yu, Tianshu Tian, Wei Wang, Weihan Yu, Wenbo Tam, Weng Lam Liang, Wenjie Liu, Wentao Wang, Xiao Jia, Xiaohan Gu, Xiaotao Ling, Xiaoying Wang, Xin Fan, Xing Pan, Xingru Zhang, Xinyuan Zhang, Xinze Fu, Xiuqing Zhang, Xunkai Xu, Yabo Wu, Yandong Lu, Yida Wang, Yidong Zhou, Yilin Pan, Yiming Zhang, Ying Wang, Yingli Li, Yingru Su, Yinpei Geng, Yipeng Zhu, Yitong Yang, Yongkun Li, Yuhang Wu, Yuhao Li, Yujiang Liu, Yunan Wang, Yunqing Li, Yuntao Zhang, Yuxuan Liu, Zezhen Yang, Zhen Zhou, Zhengda Qiao, Zhongpei Feng, Zhuoer Liu, Zhuorui Zhang, Zichen Wang, Zihan Yao, Zijun Wang, Zikang Liu, Ziqiang Chai, Ziwei Li, Zixuan Zhao, Zuodong Chen, Wenguang Zhai, Jidong Xu, Bin Huang, Minlie Wang, Hongning Li, Juanzi Dong, Yuxiao Tang, Jie
contents	We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that supports both thinking and direct response modes. Through multi-stage training on 23T tokens and comprehensive post-training with expert model iteration and reinforcement learning, GLM-4.5 achieves strong performance across agentic, reasoning, and coding (ARC) tasks, scoring 70.1% on TAU-Bench, 91.0% on AIME 24, and 64.2% on SWE-bench Verified. With much fewer parameters than several competitors, GLM-4.5 ranks 3rd overall among all evaluated models and 2nd on agentic benchmarks. We release both GLM-4.5 (355B parameters) and a compact version, GLM-4.5-Air (106B parameters), to advance research in reasoning and agentic AI systems. Code, models, and more information are available at https://github.com/zai-org/GLM-4.5.
format	Preprint
id	arxiv_https___arxiv_org_abs_2508_06471
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models 5 Team Zeng, Aohan Lv, Xin Zheng, Qinkai Hou, Zhenyu Chen, Bin Xie, Chengxing Wang, Cunxiang Yin, Da Zeng, Hao Zhang, Jiajie Wang, Kedong Zhong, Lucen Liu, Mingdao Lu, Rui Cao, Shulin Zhang, Xiaohan Huang, Xuancheng Wei, Yao Cheng, Yean An, Yifan Niu, Yilin Wen, Yuanhao Bai, Yushi Du, Zhengxiao Wang, Zihan Zhu, Zilin Zhang, Bohan Wen, Bosi Wu, Bowen Xu, Bowen Huang, Can Zhao, Casey Cai, Changpeng Yu, Chao Li, Chen Ge, Chendi Huang, Chenghua Zhang, Chenhui Xu, Chenxi Zhu, Chenzheng Li, Chuang Yin, Congfeng Lin, Daoyan Yang, Dayong Jiang, Dazhi Ai, Ding Zhu, Erle Wang, Fei Pan, Gengzheng Wang, Guo Sun, Hailong Li, Haitao Li, Haiyang Hu, Haiyi Zhang, Hanyu Peng, Hao Tai, Hao Zhang, Haoke Wang, Haoran Yang, Haoyu Liu, He Zhao, He Liu, Hongwei Yan, Hongxi Liu, Huan Chen, Huilong Li, Ji Zhao, Jiajing Ren, Jiamin Jiao, Jian Zhao, Jiani Yan, Jianyang Wang, Jiaqi Gui, Jiayi Zhao, Jiayue Liu, Jie Li, Jijie Li, Jing Lu, Jing Wang, Jingsen Yuan, Jingwei Li, Jingxuan Du, Jingzhao Du, Jinhua Liu, Jinxin Zhi, Junkai Gao, Junli Wang, Ke Yang, Lekang Xu, Liang Fan, Lin Wu, Lindong Ding, Lintao Wang, Lu Zhang, Man Li, Minghao Xu, Minghuan Zhao, Mingming Zhai, Mingshu Du, Pengfan Dong, Qian Lei, Shangde Tu, Shangqing Yang, Shangtong Lu, Shaoyou Li, Shijie Li, Shuang Shuang-Li Yang, Shuxun Yi, Sibo Yu, Tianshu Tian, Wei Wang, Weihan Yu, Wenbo Tam, Weng Lam Liang, Wenjie Liu, Wentao Wang, Xiao Jia, Xiaohan Gu, Xiaotao Ling, Xiaoying Wang, Xin Fan, Xing Pan, Xingru Zhang, Xinyuan Zhang, Xinze Fu, Xiuqing Zhang, Xunkai Xu, Yabo Wu, Yandong Lu, Yida Wang, Yidong Zhou, Yilin Pan, Yiming Zhang, Ying Wang, Yingli Li, Yingru Su, Yinpei Geng, Yipeng Zhu, Yitong Yang, Yongkun Li, Yuhang Wu, Yuhao Li, Yujiang Liu, Yunan Wang, Yunqing Li, Yuntao Zhang, Yuxuan Liu, Zezhen Yang, Zhen Zhou, Zhengda Qiao, Zhongpei Feng, Zhuoer Liu, Zhuorui Zhang, Zichen Wang, Zihan Yao, Zijun Wang, Zikang Liu, Ziqiang Chai, Ziwei Li, Zixuan Zhao, Zuodong Chen, Wenguang Zhai, Jidong Xu, Bin Huang, Minlie Wang, Hongning Li, Juanzi Dong, Yuxiao Tang, Jie Computation and Language We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that supports both thinking and direct response modes. Through multi-stage training on 23T tokens and comprehensive post-training with expert model iteration and reinforcement learning, GLM-4.5 achieves strong performance across agentic, reasoning, and coding (ARC) tasks, scoring 70.1% on TAU-Bench, 91.0% on AIME 24, and 64.2% on SWE-bench Verified. With much fewer parameters than several competitors, GLM-4.5 ranks 3rd overall among all evaluated models and 2nd on agentic benchmarks. We release both GLM-4.5 (355B parameters) and a compact version, GLM-4.5-Air (106B parameters), to advance research in reasoning and agentic AI systems. Code, models, and more information are available at https://github.com/zai-org/GLM-4.5.
title	GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
topic	Computation and Language
url	https://arxiv.org/abs/2508.06471

Similar Items