GLM-4.6
glm
Late GLM-4 workhorse for coding agents, reasoning, and structured tasks
ReasoningTool CallingOpen Weights
Context Window
205K
Max Output
131K
Temperature
Yes
Open Weights
Yes
Knowledge Cutoff
2025-04
Released
2025-09-30
Last Updated
2025-09-30
Modalities
Input:Text
→Output:Text
Benchmarks
| Benchmark | Score | Metric |
|---|---|---|
| Artificial Analysis Coding Index | 29.5 | index |
| SciCode | 38.4 | percent correct |
| Terminal-Bench Hard | 25 | success rate |
| SWE-Bench Pro | 9.67 | resolve rate |
Available Providers (0)
Tidak ada provider yang terdaftar untuk model ini.