GLM-4.5
GLM-4.5 is an open-weights AI model from Zhipu with an index score of 132 (GPT-4 = 100), rank 122 of 217.
132113–150Index score#122 of 217 models
$0.60/ $2.2Price per million tokensinput / output · via OpenRouter
131KContext windowtokens it reads at once
28 Jul 2025ReleasedReplaced by GLM-4.6
Where it sitson the frontier
o1 reached this score 8 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 7 leaderboards
The Model Indexthird-party tests, our method#122of 217 · 132
LMArena · Instruction followingfollowing detailed instructions#118of 362 · 1404LMArena · Creative writingcreative writing#124of 360 · 1372LMArena · Textoverall chat quality, judged by people#125of 362 · 1411LMArena · Mathsmaths questions in chat#120of 346 · 1411LMArena · Codingcoding questions in chat#129of 357 · 1455LMArena · Long promptslong, complex requests#123of 340 · 1417Best attop three among current models
Replaced by GLM-4.6; it no longer leads any category among current models.
Where to use itprices checked 18 Nov 2026
API providers 1 · per 1M tokens, in / out
Run it yourself
Official weightszai-org/GLM-4.5↗Host prices from OpenRouter; going direct can differ.
Facts and sources
Released28 Jul 2025
Announcementz.ai ↗
Release entryGLM-4.5
Scored asGLM-4.5
Output speed–
Hugging Facezai-org/GLM-4.5 ↗