Zhipu AI

GLM-5

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

zhipuai/glm-5

Context

204.8K

Output

131.1K

Released

2026-02-12

Knowledge cutoff

—

Types

InputText
OutputText

Reasoning

Supported

Tool use

Supported

Structured output

—

Attachments

—

Open weights

Supported

Provider pricing

No providers currently list this model.

Benchmarks

  • SWE-Bench Verified

    72.8 · resolved

  • SWE-Atlas Codebase QnA

    20.5 · score

  • SWE-Atlas Refactoring

    24.24 · score

  • SWE-Atlas Test Writing

    28.74 · score

From the same lab