{"name":"GLM-5: Flagship Models for Long-Horizon Agentic Engineering","description":"GLM-5 is a series of flagship models, including GLM-5.2, GLM-5.1, and GLM-5, developed by zai-org for complex systems engineering and long-horizon agentic tasks. These models offer advanced coding capabilities, impressive context lengths, and state-of-the-art performance on various benchmarks. They are designed to sustain effective problem-solving over extended sessions through iterative reasoning and strategy revision.","github":"https://github.com/zai-org/GLM-5","url":"https://osrepos.com/repo/zai-org-glm-5","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/zai-org-glm-5","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/zai-org-glm-5.md","json":"https://osrepos.com/repo/zai-org-glm-5.json","topics":["agentic-ai","coding","llm","long-horizon","AI","Machine Learning","Deep Learning","Language Model"],"keywords":["agentic-ai","coding","llm","long-horizon","AI","Machine Learning","Deep Learning","Language Model"],"stars":null,"summary":"GLM-5 is a series of flagship models, including GLM-5.2, GLM-5.1, and GLM-5, developed by zai-org for complex systems engineering and long-horizon agentic tasks. These models offer advanced coding capabilities, impressive context lengths, and state-of-the-art performance on various benchmarks. They are designed to sustain effective problem-solving over extended sessions through iterative reasoning and strategy revision.","content":"## Introduction\n\nThe GLM-5 series, developed by zai-org, represents a significant advancement in large language models tailored for complex systems engineering and long-horizon agentic tasks. This repository showcases GLM-5, GLM-5.1, and the latest GLM-5.2, each building upon its predecessor with enhanced capabilities.\n\n### GLM-5.2\n\nGLM-5.2 is the latest flagship model, making a substantial leap in long-horizon task capability with a solid 1M-token context. Its new features include robust 1M context stability, advanced coding with flexible effort levels, and an improved architecture featuring IndexShare, which reduces per-token FLOPs by 2.9x at 1M context length. GLM-5.2 demonstrates state-of-the-art performance on coding benchmarks, outperforming other open-source models and closing the gap with frontier closed-source models.\n\n### GLM-5.1\n\nGLM-5.1 is designed for agentic engineering, offering significantly stronger coding capabilities. It achieves state-of-the-art performance on SWE-Bench Pro and excels in real-world terminal tasks. A key innovation of GLM-5.1 is its ability to remain effective over much longer horizons, handling ambiguous problems with better judgment and sustaining productivity through iterative reasoning, experimentation, and strategy revision over hundreds of rounds.\n\n### GLM-5\n\nGLM-5 targets complex systems engineering and long-horizon agentic tasks. It scales significantly from GLM-4.5, increasing parameters and pre-training data. It integrates DeepSeek Sparse Attention (DSA) to reduce deployment costs while maintaining long-context capacity. GLM-5 also leverages `slime`, a novel asynchronous RL infrastructure, to improve training throughput and efficiency, leading to best-in-class performance among open-source models across reasoning, coding, and agentic tasks.\n\n## Installation\n\nThe GLM-5 series models are available for download and local deployment. You can access the models through Hugging Face and ModelScope.\n\nTo serve GLM-5 series models locally, several frameworks are supported:\n\n*   [SGLang](https://github.com/sgl-project/sglang) (v0.5.13.post1+), see [cookbook](https://cookbook.sglang.io/autoregressive/GLM/GLM-5.2)\n*   [vLLM](https://github.com/vllm-project/vllm) (v0.23.0+), see [recipes](https://recipes.vllm.ai/zai-org/GLM-5.2)\n*   [Transformers](https://github.com/huggingface/transformers) (v0.5.12+), see [transformers docs](https://github.com/huggingface/transformers/blob/main/docs/source/en/model_doc/glm_moe_dsa.md)\n*   [KTransformers](https://github.com/kvcache-ai/ktransformers) (v0.5.12+), see [tutorial](https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/kt-kernel/GLM-5.2-Tutorial.md)\n*   For deployment on the `Ascend NPU` platform, inference frameworks such as vLLM-Ascend, xLLM, and SGLang are supported, see [here](example/ascend.md).\n\n## Examples\n\nGLM-5 models support controlling the thinking budget through the `reasoning_effort` parameter. This parameter accepts two levels: `max` (default) and `high`. If `reasoning_effort` is unset or set to any value other than `high`, the model runs at `Max`. To use the `High` level, you must explicitly pass `reasoning_effort=\"high\"`. Thinking can be turned off entirely by setting `enable_thinking=false`.\n\n## Why Use GLM-5?\n\nThe GLM-5 series offers compelling advantages for developers and researchers working with advanced AI:\n\n*   **Exceptional Long-Horizon Capability**: GLM-5.2 provides a stable 1M-token context, enabling sustained work on complex, long-duration tasks.\n*   **State-of-the-Art Agentic Engineering**: GLM-5.1 and GLM-5 excel in agentic tasks, demonstrating superior problem-solving, iterative reasoning, and strategic revision over extended sessions.\n*   **Advanced Coding Performance**: The models achieve leading scores on standard coding benchmarks like Terminal-Bench and SWE-bench Pro.\n*   **Efficient Deployment**: Features like DeepSeek Sparse Attention in GLM-5 reduce deployment costs while preserving long-context capacity.\n*   **Strong Benchmark Results**: Consistent top performance across a wide range of academic and real-world benchmarks, including Vending Bench 2, showcasing robust planning and resource management.\n\n## Links\n\n*   **GitHub Repository**: [zai-org/GLM-5](https://github.com/zai-org/GLM-5 \"zai-org/GLM-5\")\n*   **GLM-5.2 Blog**: [Read the GLM-5.2 blog](https://z.ai/blog/glm-5.2 \"Read the GLM-5.2 blog\")\n*   **GLM-5 Technical Report**: [arXiv:2602.15763](https://arxiv.org/abs/2602.15763 \"arXiv:2602.15763\")\n*   **Z.ai API Platform**: [Use GLM-5.2 API services](https://docs.z.ai/guides/llm/glm-5.2 \"Use GLM-5.2 API services\")\n*   **Try GLM-5.2 at Z.ai**: [Visit z.ai](https://z.ai \"Visit z.ai\")\n*   **Hugging Face**: [zai-org/GLM-5.2](https://huggingface.co/zai-org/GLM-5.2 \"zai-org/GLM-5.2\"), [zai-org/GLM-5.1](https://huggingface.co/zai-org/GLM-5.1 \"zai-org/GLM-5.1\"), [zai-org/GLM-5](https://huggingface.co/zai-org/GLM-5 \"zai-org/GLM-5\")\n*   **ModelScope**: [ZhipuAI/GLM-5.2](https://modelscope.cn/models/ZhipuAI/GLM-5.2 \"ZhipuAI/GLM-5.2\"), [ZhipuAI/GLM-5.1](https://modelscope.cn/models/ZhipuAI/GLM-5.1 \"ZhipuAI/GLM-5.1\"), [ZhipuAI/GLM-5](https://modelscope.cn/models/ZhipuAI/GLM-5 \"ZhipuAI/GLM-5\")","metrics":{"detailViews":4,"githubClicks":1},"dates":{"published":null,"modified":"2026-06-18T07:47:52.000Z"}}