GLM-5.1
glm
Strong GLM coding model for agentic engineering, terminals, and repository generation
ReasoningTool CallingStructured OutputOpen Weights
Context Window
200K
Max Output
131K
Temperature
Yes
Open Weights
Yes
Knowledge Cutoff
N/A
Released
2026-04-07
Last Updated
2026-04-07
Modalities
Input:Text
→Output:Text
Benchmarks
| Benchmark | Score | Metric | Harness |
|---|---|---|---|
| Artificial Analysis Coding Agent Index | 52.7 | average pass@1 | Claude Code |
| SWE-Atlas Codebase QnA | 73.2 | pass@1 | Claude Code |
| SWE-Bench Pro | 19.8 | pass@1 | Claude Code |
| Terminal-Bench | 65.1 | pass@1 | Claude Code |
Available Providers (0)
Tidak ada provider yang terdaftar untuk model ini.