GLM-5.2
GLM-5.2 is an open-weights AI model from Zhipu with an index score of 154 (GPT-4 = 100), rank 61 of 217.
154138–169Index score#61 of 217 models
$0.0070/ $6.8Price per million tokensinput / output · via OpenRouter
1.05MContext windowtokens it reads at once
16 Jun 2026ReleasedReplaced by GLM-5.3
Where it sitson the frontier
Gemini 3 Pro reached this score 7 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsevidence
Professional workevidence
Novel problemsevidence
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#61of 217 · 154
LMArena · Mathsmaths questions in chat#27of 346 · 1487LMArena · Long promptslong, complex requests#31of 340 · 1486LMArena · Creative writingcreative writing#33of 360 · 1451LMArena · Textoverall chat quality, judged by people#34of 362 · 1475LMArena · Instruction followingfollowing detailed instructions#35of 362 · 1470LMArena · Codingcoding questions in chat#43of 357 · 1515Epoch Capabilities Indexoverall capability from many benchmarks#54of 231 · 153.0LMArena · WebDevbuilding web apps and front ends#35of 133 · 1608Best attop three among current models
Where to use itprices checked 18 Nov 2026
API providers 8 of 24 · per 1M tokens, in / out
Run it yourself
Official weightszai-org/GLM-5.2↗Host prices from OpenRouter; going direct can differ.
Facts and sources
Released16 Jun 2026
Announcementz.ai ↗
Release entryGLM-5.2
Scored asGLM-5.2
Output speed–
Hugging Facezai-org/GLM-5.2 ↗