GLM-5.3
GLM-5.3 is an open-weights AI model from Zhipu with an index score of 168 (GPT-4 = 100), rank 28 of 217.
168152–184Index score#28 of 217 models
$0.070/ $1.4Price per million tokensinput / output · via OpenRouter
1.05MContext windowtokens it reads at once
14 Aug 2026Released3 months ago
Where it sitson the frontier
GPT-5.5 reached this score 4 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#28of 217 · 168
LMArena · Mathsmaths questions in chat#14of 346 · 1501LMArena · Instruction followingfollowing detailed instructions#21of 362 · 1481LMArena · Textoverall chat quality, judged by people#25of 362 · 1482LMArena · Creative writingcreative writing#27of 360 · 1456LMArena · Codingcoding questions in chat#28of 357 · 1522LMArena · Long promptslong, complex requests#27of 340 · 1488Epoch Capabilities Indexoverall capability from many benchmarks#33of 231 · 157.1LMArena · WebDevbuilding web apps and front ends#28of 133 · 1622Best attop three among current models
Not in the top three among current models on any category we track.
Where to use itprices checked 18 Nov 2026
API providers 8 of 37 · per 1M tokens, in / out
Run it yourself
Official weightszai-org/GLM-5.3↗Host prices from OpenRouter; going direct can differ.
Facts and sources
Released14 Aug 2026
Announcementz.ai ↗
Release entryGLM-5.3
Scored asGLM-5.3
Output speed–
Hugging Facezai-org/GLM-5.3 ↗