GLM-5
glm
General GLM flagship for coding, analysis, and tool-heavy engineering workflows
ReasoningTool CallingOpen Weights
Context Window
205K
Max Output
131K
Temperature
Yes
Open Weights
Yes
Knowledge Cutoff
N/A
Released
2026-02-12
Last Updated
2026-02-12
Modalities
Input:Text
→Output:Text
Benchmarks
| Benchmark | Score | Metric | Harness |
|---|---|---|---|
| SWE-Bench Verified | 72.8 | resolved | - |
| SWE-Atlas Codebase QnA | 20.5 | score | Mini-SWE-Agent |
| SWE-Atlas Refactoring | 24.24 | score | Mini-SWE-Agent |
| SWE-Atlas Test Writing | 28.74 | score | Mini-SWE-Agent |
Available Providers (0)
Tidak ada provider yang terdaftar untuk model ini.