README.md

metadata

language:
  - en
  - zh
library_name: transformers
license: mit
pipeline_tag: text-generation
model-index:
  - name: GLM-4.6
    results:
      - task:
          type: evaluation
        dataset:
          name: Artificial Analysis Benchmarks
          type: artificial_analysis
        metrics:
          - name: Artificial Analysis Intelligence Index
            type: artificial_analysis_intelligence_index
            value: 44.7
          - name: Artificial Analysis Coding Index
            type: artificial_analysis_coding_index
            value: 38.7
          - name: Artificial Analysis Math Index
            type: artificial_analysis_math_index
            value: 44.3
          - name: Mmlu Pro
            type: mmlu_pro
            value: 0.784
          - name: Gpqa
            type: gpqa
            value: 0.632
          - name: Hle
            type: hle
            value: 0.052
          - name: Livecodebench
            type: livecodebench
            value: 0.561
          - name: Scicode
            type: scicode
            value: 0.331
          - name: Aime 25
            type: aime_25
            value: 0.443
          - name: Ifbench
            type: ifbench
            value: 0.367
          - name: Lcr
            type: lcr
            value: 0.263
          - name: Terminalbench Hard
            type: terminalbench_hard
            value: 0.27
          - name: Tau2
            type: tau2
            value: 0.769
        source:
          name: Artificial Analysis API
          url: https://artificialanalysis.ai

GLM-4.6

👋 Join our Discord community.
📖 Check out the GLM-4.6 technical blog, technical report(GLM-4.5), and Zhipu AI technical documentation.
📍 Use GLM-4.6 API services on Z.ai API Platform.
👉 One click to GLM-4.6.

Model Introduction

Compared with GLM-4.5, GLM-4.6 brings several key improvements:

• Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks.
• Superior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages.
• Advanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability.
• More capable agents: GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks.
• Refined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.

We evaluated GLM-4.6 across eight public benchmarks covering agents, reasoning, and coding. Results show clear gains over GLM-4.5, with GLM-4.6 also holding competitive advantages over leading domestic and international models such as DeepSeek-V3.1-Terminus and Claude Sonnet 4.

Inference

Both GLM-4.5 and GLM-4.6 use the same inference method.

you can check our github for more detail.

Recommended Evaluation Parameters

For general evaluations, we recommend using a sampling temperature of 1.0.

For code-related evaluation tasks (such as LCB), it is further recommended to set:

• top_p = 0.95
• top_k = 40

Evaluation

• For tool-integrated reasoning, please refer to this doc.
• For search benchmark, we design a specific format for searching toolcall in thinking mode to support search agent, please refer to this. for the detailed template.