zhipuai

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

BenchmarkScoreMetricHarness
SWE-Bench Verified72.8resolved-
SWE-Atlas Codebase QnA20.5scoreMini-SWE-Agent
SWE-Atlas Refactoring24.24scoreMini-SWE-Agent
SWE-Atlas Test Writing28.74scoreMini-SWE-Agent

Available Providers (0)

Tidak ada provider yang terdaftar untuk model ini.