GLM 5
New
by Zhipu AI
+
+
+
+
About
GLM 5 is a large language model from Zhipu AI built for agentic tasks and tool use — designed to operate as an autonomous agent that plans multi-step tasks, calls external tools, and interacts with systems. It represents Zhipu AI's investment in the agentic AI direction, positioning GLM 5 as a foundation for enterprise applications that require AI to act through tool-calling pipelines rather than just respond with text.
+
+
+
+
Pricing Range
Input (per 1M)$0.80 -$0.80
Output (per 1M)$2.56 -$2.56
Providers1
+
+
+
+
Timeline
ReleasedFeb 11, 2026
+
+
+
+
License & Family
License
MIT
Performance Overview
Performance metrics and category breakdown
Overall Performance
3 benchmarks
Average Score
57.7%
Best Score
77.8%
High Performers (80%+)
0Performance Metrics
Max Context Window
204.1KTop Categories
Coding
60.0%
Finance
53.2%
+
+
+
+
All Benchmark Results for GLM 5
Complete list of benchmark scores with detailed information
| SWE Bench Verified | Coding | 77.80 | 77.8% | Unverified | |
| Finance Agent | Finance | 53.18 | 53.2% | Unverified | |
| SWE-rebench | Coding | 42.10 | 42.1% | Unverified |