Z.ai: GLM 5
Z.ai's GLM 5 is one of the strongest models in the database by intelligence index, with excellent coding, agentic, and instruction-following scores, tool use support, and competitive pricing — though businesses should verify API availability and compliance requirements for their region.
Assessment date: March 12, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.
Capabilities
Architecture
| Modality | Text → Text |
| Tokenizer | Other |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Evaluations
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.72 | $0.000720 |
| Output | $2.30 | $0.002300 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
