GLM-4.7
GLM-4.7 is an open-weights AI model from Zhipu with an index score of 140 (GPT-4 = 100), rank 100 of 217.
140123–157Index score#100 of 217 models
$0.40/ $1.75Price per million tokensinput / output · via OpenRouter
205KContext windowtokens it reads at once
22 Dec 2025ReleasedReplaced by GLM-5
Where it sitson the frontier
Gemini 2.5 Pro reached this score 9 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsno evidence yet
Professional workevidence
Novel problemsno evidence yet
Long tasksno evidence yet
Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.
What others sayrank on 9 leaderboards
The Model Indexthird-party tests, our method#100of 217 · 140
LMArena · Long promptslong, complex requests#77of 340 · 1451LMArena · Textoverall chat quality, judged by people#82of 362 · 1441LMArena · Creative writingcreative writing#84of 360 · 1406LMArena · Instruction followingfollowing detailed instructions#88of 362 · 1426LMArena · Codingcoding questions in chat#91of 357 · 1484LMArena · Mathsmaths questions in chat#96of 346 · 1427Epoch Capabilities Indexoverall capability from many benchmarks#104of 231 · 143.4LMArena · WebDevbuilding web apps and front ends#79of 133 · 1436Best attop three among current models
Replaced by GLM-5; it no longer leads any category among current models.
Where to use itprices checked 18 Nov 2026
API providers 5 · per 1M tokens, in / out
Run it yourself
Official weightszai-org/GLM-4.7↗Host prices from OpenRouter; going direct can differ.
Facts and sources
Released22 Dec 2025
Announcementhuggingface.co ↗
Release entryGLM-4.7
Scored asGLM-4.7
Output speed–
Hugging Facezai-org/GLM-4.7 ↗