GLM-5.1
GLM-5.1 is an open-weights AI model from Zhipu with an index score of 151 (GPT-4 = 100), rank 66 of 217.
151134–167Index score#66 of 217 models
$1.4/ $4.4Price per million tokensinput / output · via OpenRouter
205KContext windowtokens it reads at once
7 Apr 2026ReleasedReplaced by GLM-5.2
Where it sitson the frontier
Gemini 3 Pro reached this score 5 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsevidence
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#66of 217 · 151
LMArena · Creative writingcreative writing#41of 360 · 1446LMArena · Mathsmaths questions in chat#42of 346 · 1474LMArena · Instruction followingfollowing detailed instructions#45of 362 · 1461LMArena · Long promptslong, complex requests#43of 340 · 1480LMArena · Codingcoding questions in chat#49of 357 · 1512LMArena · Textoverall chat quality, judged by people#51of 362 · 1465Epoch Capabilities Indexoverall capability from many benchmarks#67of 231 · 150.7LMArena · WebDevbuilding web apps and front ends#62of 133 · 1508Best attop three among current models
Where to use itprices checked 18 Nov 2026
API providers 8 of 11 · per 1M tokens, in / out
Run it yourself
Official weightszai-org/GLM-5.1↗Host prices from OpenRouter; going direct can differ.
Facts and sources
Released7 Apr 2026
Announcementhuggingface.co ↗
Release entryGLM-5.1
Scored asGLM-5.1
Output speed–
Hugging Facezai-org/GLM-5.1 ↗