#45 · Primary category： Foundation Models
GLM-4.5
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Project last updated：02/01/26
GitHub Stars
4.4K
Forks
473
Contributors
4
License
Apache-2.0
Why we included this project
Zhipu AI's GLM-4.5 line ships the actual model weights for the 4.5, 4.6, and 4.7 generations rather than wrapping them behind an API, and the repository is organized around the tasks that matter for real agent work: coding, terminal automation, tool use, and mathematical reasoning. The README is honest about where each version improved, with benchmark numbers against the prior generation, and notes that the models run inside existing agent frameworks like Claude Code, Cline, and Roo Code. For a team weighing an open-weights alternative to proprietary coding models, the per-version notes make it fairly easy to choose a release that fits your hardware and latency budget. The linked technical reports and benchmark tables let you verify the claims before spending compute.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
MiniCPM-V
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
generative-models
Generative Models by Stability AI
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities