GLM-5.3-Flash
GLM-5.3-Flash is an open-weights AI model from Zhipu with an index score of 161 (GPT-4 = 100), rank 50 of 217.
161145–177Index score#50 of 217 models
$0.15/ $0.50Price per million tokensinput / output · via OpenRouter
1.05MContext windowtokens it reads at once
20 Aug 2026Released3 months ago
Where it sitson the frontier
GPT-5.2 reached this score 8 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 10 leaderboards
The Model Indexthird-party tests, our method#50of 217 · 161
LMArena · Mathsmaths questions in chat#10of 346 · 1505LMArena · Codingcoding questions in chat#24of 357 · 1526LMArena · Instruction followingfollowing detailed instructions#29of 362 · 1474LMArena · Textoverall chat quality, judged by people#31of 362 · 1475LMArena · Long promptslong, complex requests#44of 340 · 1480LMArena · Creative writingcreative writing#55of 360 · 1435LMArena · Visionunderstanding images#29of 145 · 1272Epoch Capabilities Indexoverall capability from many benchmarks#52of 231 · 153.8LMArena · WebDevbuilding web apps and front ends#33of 133 · 1609Best 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 38 · per 1M tokens, in / out
Run it yourself
Official weightszai-org/GLM-5.3-Flash↗Host prices from OpenRouter; going direct can differ.
Facts and sources
Released20 Aug 2026
Announcementhuggingface.co ↗
Release entryGLM-5.3-Flash
Scored asGLM-5.3-Flash
Output speed–
Hugging Facezai-org/GLM-5.3-Flash ↗