GLM-4.7Open Weight

GLM-4.7 is an AI model released by Z.ai on Monday, Dec 22 2025, 83 days after GLM-4.6. It is an open-weight model — the trained weights are available to download and run. It has a 128k token context window. Benchmark results (shown below) cover SWE-Bench Verified, Terminal-Bench 2.0, BrowseComp, Humanity's Last Exam, GPQA Diamond, and Arena Elo (Code).

Benchmarks

Coding
SWE-Bench Verified
73.8%
#19 of 36
Agentic terminal coding
Terminal-Bench 2.0
41%
#12 of 13
Web browsing
BrowseComp
52%
#17 of 17
Multidisciplinary reasoning
Humanity's Last Exam
24.8%
no tools
42.8%
with tools
no tools
#13 of 14
with tools
#17 of 17
Science
GPQA Diamond
85.7%
#26 of 46
Community preference (code)
Arena Elo (Code)
1433
#28 of 43

GLM-4.7 — frequently asked questions

When was GLM-4.7 released?
GLM-4.7 was released by Z.ai on Monday, Dec 22 2025.
Who made GLM-4.7?
GLM-4.7 was built by Z.ai. Chinese AI lab spun out of Tsinghua University (formerly Zhipu AI), building the open-weight GLM family. Rebranded internationally as Z.ai in 2025.
What benchmark scores did GLM-4.7 get?
GLM-4.7 reports 7 tracked benchmark scores — SWE-Bench Verified: 73.8%; Terminal-Bench 2.0: 41%; BrowseComp: 52%; Humanity's Last Exam (no tools): 24.8%; Humanity's Last Exam (with tools): 42.8%; GPQA Diamond: 85.7%; Arena Elo (Code): 1433. Scores are the figures published at release by Z.ai.
What is the context window of GLM-4.7?
GLM-4.7 has a context window of 128k. That is the maximum amount of input plus output the model can hold in a single request.
Is GLM-4.7 open source?
Partly. GLM-4.7 is an open-weight model: the trained weights are free to download and run locally or on your own infrastructure, but the training data and code are not fully released and the license may restrict some commercial uses. It is not open source in the strict sense.
What came before and after GLM-4.7?
Z.ai's previous tracked release was GLM-4.6 on Sep 30 2025, 83 days earlier. It was followed by GLM-5 on Feb 12 2026.

Compare GLM-4.7 with