GLM-4.7

GLM-4.7: Zhipu AI's Flagship LLM for Agentic Coding

GLM-4.7 represents Zhipu AI's latest advancement in large language models, prioritizing agentic coding, stable multi-step reasoning, and complex workflows. Released in December 2025, it supports a 200K token context window and up to 128K output tokens, enabling robust handling of extended tasks.

Technical Specifications

• Model Type: Large Language Model (LLM)
• Developer: Z.AI (Zhipu AI)
• Context Window: 200,000 tokens
• Maximum Output Length: 128,000 tokens
• Input Modalities: Text
• Output Modalities: Text, structured responses, reasoning traces

Performance Benchmarks

GLM-4.7 leads open-source models in coding benchmarks at 128K context, achieving 73.8% on SWE-bench Verified (up 5.8% from GLM-4.6) and 84.9% on LiveCodeBench v6, surpassing Claude Sonnet 4.5. Reasoning scores include 42.8% on HLE with tools (41% gain over predecessor) and 95.7% on AIME 2025.

Key Features

GLM-4.7 excels in programming with a "think before acting" mechanism, improving multi-language code generation and terminal agent performance. It integrates function calling, structured JSON outputs, context caching, and real-time streaming for seamless developer workflows.​

Agentic Coding‍

Seamlessly writes, debugs, and deploys code across languages—ideal for terminal-based and IDE-integrated workflows.

Vibe Coding & UI Generation‍

Generates modern, aesthetically refined HTML/CSS/JS and presentation slides with accurate layout, spacing, and design sensibility.

Professional-Grade Output‍

Creates high-fidelity PPTs, posters, technical documentation, and narrative content with consistent tone and structure.

Intelligent Search & Deep Research‍

Excels at synthesizing information from long contexts, extracting insights, and generating evidence-backed summaries.

API Pricing

• Input: $0.63 / 1M tokens
• Cached Input: $0.1155 / 1M tokens
• Output: $2.31 / 1M tokens

Use Cases

GLM-4.7 powers agentic coding by autonomously handling requirement decomposition, multi-stack integration, and executable frameworks for prototypes. Developers use it for multimodal apps with real-time controls and gesture recognition, accelerating from concept to deployment.​

• Web UI and visual content creation with professional-grade aesthetics for low-code tools.
• Complex problem-solving in multi-turn chats, research, and immersive writing/role-play.
• Intelligent search consolidating cross-source data for decision support.
  

Model Comparisons

vs. GLM-4.6: GLM-4.7 boosts coding stability with 73.8% on SWE-bench Verified (up 5.8%) and 41% on Terminal Bench 2.0 (up 16.5%), plus 41% HLE gain via preserved thinking.​

vs. Claude Sonnet 4.5: Matches coding prowess at 84.9% LiveCodeBench v6 (outpacing it) and leads open-source on SWE-bench, but trails slightly in Terminal Bench; excels in tool use at 87.4% τ²-Bench.​

vs. GPT-5.1: Competitive at 84.9% LiveCodeBench v6 and 73.8% SWE-bench Verified, with superior open-source accessibility and 3x speed in real tests