Z.ai's first natively multimodal model in the GLM-5 family, designed for efficient coding, agentic work, visual reasoning, and long-context tasks. It uses a 320B-parameter sparse mixture-of-experts architecture with 18B active parameters, hybrid linear and sparse attention, and a context window of up to one million tokens. The model weights are released under the MIT license for local deployment with frameworks including SGLang and vLLM.
No provider data available yet.
Provider mappings will appear here once they become available.
Published scores with their sources. Vendor-reported results use the vendor's own evaluation settings and are not directly comparable across vendors.
| Benchmark | Score | Source |
|---|---|---|
| Artificial Analysis Intelligence IndexGeneral · as listed on 2026-10-01 | 42 | Artificial AnalysisIndependent |