GLM-4.7

by Zhipu AI

+
+
+
+
About

GLM-4.7, released by Zhipu AI on December 22, 2025, is a large language model with approximately 400 billion parameters from the GLM-4 family, designed for deep mathematical reasoning, multi-file software engineering, and stable agentic orchestration. It features a 200K token context window and 128K maximum output tokens, supporting extended code and analysis generation. GLM-4.7 targets advanced open-source deployments under an MIT license via Zhipu AI's Z.ai platform.

+
+
+
+
Pricing Range
Input (per 1M)$0.50 -$0.50
Output (per 1M)$0.50 -$0.50
Providers1
+
+
+
+
Timeline
ReleasedDec 22, 2025
+
+
+
+
License & Family
License
MIT
Performance Overview
Performance metrics and category breakdown

Overall Performance

3 benchmarks
Average Score
49.5%
Best Score
73.8%
High Performers (80%+)
0

Performance Metrics

Max Context Window
204.1K

Top Categories

Coding
49.5%
+
+
+
+
All Benchmark Results for GLM-4.7
Complete list of benchmark scores with detailed information
SWE Bench Verified
Coding
73.80
73.8%
Unverified
SWE-rebench
Coding
41.30
41.3%
Unverified
Terminal Bench 2.0
Coding
33.40
33.4%
Unverified