GLM-5: from Vibe Coding to Agentic Engineering

GLM-5-Team; :; Aohan Zeng; Xin Lv; Zhenyu Hou; Zhengxiao Du; Qinkai Zheng; Bin Chen

cs.LGFeb 17, 2026

GLM-5: from Vibe Coding to Agentic Engineering

Authors: GLM-5-Team, :, Aohan Zeng, Xin Lv, Zhenyu Hou, Zhengxiao Du, Qinkai Zheng, Bin Chen, Da Yin, Chendi Ge, Chenghua Huang, Chengxing Xie, Chenzheng Zhu, Congfeng Yin, Cunxiang Wang, Gengzheng Pan, Hao Zeng, Haoke Zhang, Haoran Wang, Huilong Chen, Jiajie Zhang, Jian Jiao, Jiaqi Guo, Jingsen Wang, Jingzhao Du, Jinzhu Wu, Kedong Wang, Lei Li, Lin Fan, Lucen Zhong, Mingdao Liu, Mingming Zhao, Pengfan Du, Qian Dong, Rui Lu, Shuang-Li, Shulin Cao, Song Liu, Ting Jiang, Xiaodong Chen, Xiaohan Zhang, Xuancheng Huang, Xuezhen Dong, Yabo Xu, Yao Wei, Yifan An, Yilin Niu, Yitong Zhu, Yuanhao Wen, Yukuo Cen, Yushi Bai, Zhongpei Qiao, Zihan Wang, Zikang Wang, Zilin Zhu, Ziqiang Liu, Zixuan Li, Bojie Wang, Bosi Wen, Can Huang, Changpeng Cai, Chao Yu, Chen Li, Chengwei Hu, Chenhui Zhang, Dan Zhang, Daoyan Lin, Dayong Yang, Di Wang, Ding Ai, Erle Zhu, Fangzhou Yi, Feiyu Chen, Guohong Wen, Hailong Sun, Haisha Zhao, Haiyi Hu, Hanchen Zhang, Hanrui Liu, Hanyu Zhang, Hao Peng, Hao Tai, Haobo Zhang, He Liu, Hongwei Wang, Hongxi Yan, Hongyu Ge, Huan Liu, Huanpeng Chu, Jia'ni Zhao, Jiachen Wang, Jiajing Zhao, Jiamin Ren, Jiapeng Wang, Jiaxin Zhang, Jiayi Gui, Jiayue Zhao, Jijie Li, Jing An, Jing Li, Jingwei Yuan, Jinhua Du, Jinxin Liu, Junkai Zhi, Junwen Duan, Kaiyue Zhou, Kangjian Wei, Ke Wang, Keyun Luo, Laiqiang Zhang, Leigang Sha, Liang Xu, Lindong Wu, Lintao Ding, Lu Chen, Minghao Li, Nianyi Lin, Pan Ta, Qiang Zou, Rongjun Song, Ruiqi Yang, Shangqing Tu, Shangtong Yang, Shaoxiang Wu, Shengyan Zhang, Shijie Li, Shuang Li, Shuyi Fan, Wei Qin, Wei Tian, Weining Zhang, Wenbo Yu, Wenjie Liang, Xiang Kuang, Xiangmeng Cheng, Xiangyang Li, Xiaoquan Yan, Xiaowei Hu, Xiaoying Ling, Xing Fan, Xingye Xia, Xinyuan Zhang, Xinze Zhang, Xirui Pan, Xu Zou, Xunkai Zhang, Yadi Liu, Yandong Wu, Yanfu Li, Yidong Wang, Yifan Zhu, Yijun Tan, Yilin Zhou, Yiming Pan, Ying Zhang, Yinpei Su, Yipeng Geng, Yong Yan, Yonglin Tan, Yuean Bi, Yuhan Shen, Yuhao Yang, Yujiang Li, Yunan Liu, Yunqing Wang, Yuntao Li, Yurong Wu, Yutao Zhang, Yuxi Duan, Yuxuan Zhang, Zezhen Liu, Zhengtao Jiang, Zhenhe Yan, Zheyu Zhang, Zhixiang Wei, Zhuo Chen, Zhuoer Feng, Zijun Yao, Ziwei Chai, Ziyuan Wang, Zuzhou Zhang, Bin Xu, Minlie Huang, Hongning Wang, Juanzi Li, Yuxiao Dong, Jie Tang

Abstract

We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (ARC) capabilities of its predecessor, GLM-5 adopts DSA to significantly reduce training and inference costs while maintaining long-context fidelity. To advance model alignment and autonomy, we implement a new asynchronous reinforcement learning infrastructure that drastically improves post-training efficiency by decoupling generation from training. Furthermore, we propose novel asynchronous agent RL algorithms that further improve RL quality, enabling the model to learn from complex, long-horizon interactions more effectively. Through these innovations, GLM-5 achieves state-of-the-art performance on major open benchmarks. Most critically, GLM-5 demonstrates unprecedented capability in real-world coding tasks, surpassing previous baselines in handling end-to-end software engineering challenges. Code, models, and more information are available at https://github.com/zai-org/GLM-5.

Figures & tables

Figure 1: Results of GLM-5, DeepSeek-V3.2, Claude Opus 4.5, Gemini 3 Pro, and GPT-5.2 (xhigh) on 8 agentic, reasoning, and coding benchmarks: Humanity’s Last Exam, SWE-bench Verified, SWE-bench Multilingual, Terminal-Bench 2.0, BrowseComp, MCP-Atlas, $\tau^{2}$ -Bench, Vending Bench 2.

Figure 2: Artificial Analysis Intelligence Index v4.0 incorporates 10 evaluations: GDPval-AA, $\tau^{2}$ -Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity’s Last Exam, GPQA Diamond, CritPt.

Panel of Figure 3 — Figure 3: On LMArena, GLM-5 is the #1 open model in both Text Arena and Code Arena.

Panel of Figure 4 — Figure 4: Results on several long-horizon tasks. Left: Vending-Bench 2; Right: CC-Bench-V2.

Figure 5: Overall training pipeline of GLM-5.

Dataset	Hellaswag	MMLU	C-Eval	RACE	BBH	GSM8K	HumanEval
GQA-8	77.3	61.2	60.0	79.6	53.3	47.6	38.5
MLA	77.3	61.5	59.7	77.8	48.9	46.2	33.5
MLA + Muon Split	77.8	62.5	62.1	79.9	51.8	45.0	36.7
MLA-256 + Muon Split	77.4	62.0	59.9	79.6	51.3	47.5	36.6

Table 1: Evaluation results for GQA-8 and variants of MLA.

Model	Accept Length
DeepSeek-V3.2	2.55
GLM-5	2.76

Table 2: Comparison of accept lengths of DeepSeek-V3.2 and GLM-5.

	MQ-NIAH-128k	MV-NIAH-128k	SQuAD-128k	HotpotQA-128k
MLA	100.0	95.5	79.7	66.3
DSA	100.0	97.0	86.0	63.0

Table 3: Comparison of long-context benchmarks between MLA and DSA base models.

Figure 6: SFT loss curves comparison between MLA and DSA training. Results are smoothed by Running Average with a window size of 50.

	4K	8K	16K	32K	64K	128K
GLM-9B (Full Attn)	95.19	93.67	92.01	91.09	85.35	75.28
SWA Interleave	94.87	54.02	25.89	12.61	8.32	6.51
SWA Pattern	95.78	92.54	88.92	82.52	70.23	53.95

Table 4: RULER benchmark results for the GLM-9B baseline and two SWA variants without any additional training . Both SWA methods use a 1:1 ratio of full-attention to SWA layers with a 4096-token window size. The search-based SWA pattern is discovered once at 16k context length and applied uniformly across all input lengths.

	RULER (64K / 128K)	MRCR (64K / 128K)	HELMET-ICL (64K / 128K)	RepoQA (64K / 128K)
GLM-9B	85.35 / 75.28	36.53 / 35.39	77.68 / 77.36	69.00 / 65.83
SWA Interleave	65.94 / 44.93 ( $\downarrow$ 19.41 / $\downarrow$ 30.35)	30.03 / 28.83 ( $\downarrow$ 6.50 / $\downarrow$ 6.56)	75.96 / 63.52 ( $\downarrow$ 1.72 / $\downarrow$ 13.84)	50.33 / 39.33 ( $\downarrow$ 18.67 / $\downarrow$ 26.50)
SWA Pattern	83.72 / 69.59 ( $\downarrow$ 1.63 / $\downarrow$ 5.69)	35.02 / 33.58 ( $\downarrow$ 1.51 / $\downarrow$ 1.81)	76.48 / 74.60 ( $\downarrow$ 1.20 / $\downarrow$ 2.76)	62.33 / 51.17 ( $\downarrow$ 6.67 / $\downarrow$ 14.66)
GDN	76.76 / 64.00 ( $\downarrow$ 8.59 / $\downarrow$ 11.28)	31.72 / 30.22 ( $\downarrow$ 4.81 / $\downarrow$ 5.17)	76.88 / 74.84 ( $\downarrow$ 0.80 / $\downarrow$ 2.52)	65.50 / 56.17 ( $\downarrow$ 3.50 / $\downarrow$ 9.66)
SimpleGDN	81.76 / 67.03 ( $\downarrow$ 3.59 / $\downarrow$ 8.25)	33.03 / 31.27 ( $\downarrow$ 3.50 / $\downarrow$ 4.12)	79.80 / 81.84 ( $\uparrow$ 2.12 / $\uparrow$ 4.48)	65.50 / 58.50 ( $\downarrow$ 3.50 / $\downarrow$ 7.33)

Table 5: Long-context benchmark results. All efficient attention variants are continual-trained from the GLM-9B full-attention baseline. SWA pattern denotes search-based layer selection; SWA interleave denotes the fixed alternating pattern.

\Delta

@64K and

\Delta

@128K show the difference relative to the full-attention baseline at 64K and 128K context lengths, respectively.

	4K	8K	16K	32K	64K	128K
GLM-4.7-Flash	97.44	96.72	95.83	92.96	85.34	79.21
GLM-4.7-Flash + DSA warmup	97.51	96.54	95.40	90.09	84.05	71.35
GLM-4.7-Flash + DSA	96.77	96.25	96.69	93.45	87.06	78.86

Table 6: RULER benchmark results for the GLM-4.7-Flash with DSA. The warmup-only variant trains only the indexer while keeping the base model frozen, the full DSA variant jointly trains both for 150B tokens.

Figure 7: Illustration of Interleaved Thinking and Preserved Thinking.

Figure 8: Accuracy of BrowseComp with different context management strategies from GLM-4.7 (gray baselines) to GLM-5 (colored strategies).

Figure 9: Examples of reward hacking in the slides RL training. Our runtime rendering obtains grounded attribute values, making the evaluation robust to such hacking behaviors.

	GLM-5	GLM-4.7	DeepSeek -V3.2	Kimi K2.5	Claude Opus 4.5	Gemini 3 Pro	GPT-5.2 (xhigh)
Reasoning & General
HLE	30.5	24.8	25.1	31.5	28.4	37.2	35.4
HLE (w/ Tools)	50.4	42.8	40.8	51.8	43.4*	45.8*	45.5*
AIME 2026 I	92.7	92.9	92.7	92.5	93.3	90.6	-
HMMT Feb. 2025	97.9	97.1	92.5	95.4	92.9	97.3	99.4
HMMT Nov. 2025	96.9	93.5	90.2	91.1	91.7	93.0	97.1

Table 7: Comparison between GLM-5 and open-source/proprietary models. Results marked with * are from the full set of HLE. Results marked with † are evaluated on a verified version of Terminal-Bench 2.0, fixing some ambiguous instructions. The GDPval-AA Elo scores are recorded on 15th Feb., 2026. The highest score for each benchmark is bolded , and the second highest is underlined .

Category	Task	Metric	GLM-5	GLM-4.7	Claude Opus 4.5
Frontend	HTML	ISR	38.9	35.4	52.2
		CSR	76.3	64.9	82.2
	React	ISR	34.6	17.2	39.7
		CSR	71.0	49.4	70.7
	Vue	ISR	32.7	24.5	46.9
		CSR	77.1	53.8	74.3

Table 8: CC-Bench-V2 evaluation results across frontend, backend, and long-horizon tasks. BSR : Build Success Rate; ISR : Instance Success Rate; CSR : Check-item Success Rate.

Figure 10: Agent-as-a-Judge evaluation pipeline. Each generated frontend project is first built to verify static correctness. Successfully built instances are then interactively tested by an autonomous Judge Agent, which determines the functional correctness of each check item.

Model	Resolved Rate (%)	Resolved Rate SEM ( $\pm$ , %)	Pass@5 (%)
Claude Opus 4.6	52.9%	1.06%	70.8%
GPT-5.2 (xhigh)	51.7%	1.21%	58.3%
Claude Sonnet 4.5	47.1%	1.69%	60.4%
Gemini 3 Pro	46.7%	2.04%	58.3%
Claude Opus 4.5	43.8%	0.93%	58.3%
GLM-5	42.1%	1.21%	50.0%

Table 9: Performance on SWE-rebench, January 2026.

Figure 11: Performance comparison between GLM-4.7 and GLM-5 across five real-world general ability domains.

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Model	GLM-4.5	GLM-5
# Total Parameters	355B	744B
# Activated Parameters	32B	40B
# Dense Layers	3	3
# MoE Layers	89	75
# MTP Layers	1	1
Hidden Dim	5120	6144

Appendix

Table 10: Model architecture of GLM-4.5 and GLM-5. When counting parameters, for all models we include the parameters of MTP layers but not word embeddings and the output layer.

	Benchmark (Metric)	DeepSeek-V3	Kimi-K2	GLM-4.5	GLM-5
		Base	Base	Base	Base
	Architecture	MoE	MoE	MoE	MoE
	# Activated Params	37B	32B	32B	40B
	# Total Params	671B	1043B	355B	744B
English	SimpleQA (EM)	26.6	35.3	30.0	36.0
	BBH (EM)	88.4	88.7	86.2	87.4

Appendix

Table 11: Comparison among GLM-5-Base, GLM-4.5-Base and other representative open-source base models.

Category	Description	# Tasks	# Checkitems
Business Systems	Enterprise/Personal data and process management.	42	167
Web Games	Interaction and entertainment-focused games.	40	163
SVG/Canvas	Graphics rendering and interactive visualizations.	32	166
Creative Tools	Content creation and online editing tools.	28	160
Showcase Pages	Visual expression and information presentation.	27	115
Forms & Tables	Structured data entry and processing.	26	93

Appendix

Table 12: Distribution of frontend application scenarios.

Category	Description	# Tasks	# Checkitems
HTML	Vanilla HTML/CSS/JS development.	113	490
React	Component-based framework development.	58	249
Vue	Vue 3 + Vite progressive solution.	49	210

Appendix

Table 13: Statistics of technology stacks and evaluation units.

LLM Agent Training

Large language model agent training teaches models to plan, use tools, and learn from multi-step interaction with environments.

See all 585 papers

KAT-Coder-V2 Technical Report
Mar 29, 2026Fengxiang Li, Han Zhang, Haoyang Huang +43AI Coding Agents Agentic Code Generation
Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
Jul 8, 2026Zhenyu Hou, Yujiang Li, Jie Tang +1Agentic RL Asynchronous RL
Tsinghua University · Work done while ZH and YL interned at Z.AI.
IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems
Oct 22, 2026A. Jian Yang, An Huang, Bo Dan +174LLM Agent Training AI Coding Agents

Mar 29, 2026J/K move · Enter open · S save

KAT-Coder-V2 Technical Report

Fengxiang Li, Han Zhang, Haoyang Huang, Jinghui Wang+42

AI Coding Agents Agentic Code Generation LLM Agent Training RL for Code Generation

Open paper AskPDF arXiv

We present KAT-Coder-V2, an agentic coding model developed by the KwaiKAT team at Kuaishou. KAT-Coder-V2 adopts a "Specialize-then-Unify" paradigm that decomposes agentic coding into five expert domains - SWE, WebCoding, Terminal, WebSearch, and General - each undergoing independent supervised fine-tuning and reinforcement learning, before being consolidated into a single model via on-policy distillation. We develop KwaiEnv, a modular infrastructure sustaining tens of thousands of concurrent sandbox instances, and scale RL training along task complexity, intent alignment, and scaffold generalization. We further propose MCLA for stabilizing MoE RL training and Tree Training for eliminating redundant computation over tree-structured trajectories with up to 6.2x speedup. KAT-Coder-V2 achieves 79.6% on SWE-bench Verified (vs. Claude Opus 4.6 at 80.8%), 88.7 on PinchBench (surpassing GLM-5 and MiniMax M2.7), ranks first across all three frontend aesthetics scenarios, and maintains strong generalist scores on Terminal-Bench Hard (46.8) and tau^2-Bench (93.9). Our model is publicly available at https://streamlake.com/product/kat-coder.

Abstract

LLM Agent Training

Explore similar work

KAT-Coder-V2 Technical Report

Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems