GLM-4.7
Z.ai- Arena score
- 1435
- Among open models
- #20of 148
- Among all on Arena
- #89
- Votes
- 12,153
Measured on GLM-4.7, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
Top 10 among open models in#8Medicine & health#8Japanese
CategoryScoreOpen rankArena rankVotes
- Chinese1494#15#641K
- Medicine & health1470#8#39822
- Science1457#16#682.1K
- Coding1454#27#952.5K
- Software & IT1453#27#984.1K
- English1453#14#645K
- Hard prompts, English1452#18#812.7K
- Multi-turn1446#14#741.9K
- Legal & government1444#18#84961
- Hard prompts1443#21#906.7K
- Japanese1439#8#44125
- Polish1435#18#77461
- Spanish1435#26#94342
- Long prompts1432#22#913.2K
- Excluding ties1431#19#868.4K
- French1430#34#117303
- Business & finance1430#21#832.3K
- German1426#23#95223
- Russian1424#20#941.6K
- Expert1424#41#132802
- Math1423#36#116727
- Non-English1417#22#967.2K
- Applied math1413#46#150618
- Instructions1412#26#1033.3K
- Writing & literature1411#17#922.8K
- Creative writing1402#20#951.9K
- Media & sports1401#19#942.4K
- Korean1399#15#74177
About as strong, smaller
Compare
gemma-4-26B-A4B-itGoogle143425.8B

Qwen3.8-27BQwen143727.8B

gemma-4-31B-itGoogle144331.3B

Mistral-Medium-3.5-128BMistral AI1421128B
Discussion
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiounsloth/GLM-4.7-GGUF15 builds
- MLX · Apple silicon: mlx-lm, LM Studiomlx-community/GLM-4.7-4bit7 builds
- AWQ · vLLM, SGLangQuantTrio/GLM-4.7-AWQ2 builds
- GPTQ · vLLM, SGLangJon-Nielsen/GLM-4.7-REAP-30-W4A162 builds
Most downloaded
BenchClub runs
Not runnable yet
Runs open once a GLM-4.7 build is registered.
More from Z.ai
See more
GLM-5.3-Flash6.4M321B
GLM-5.31.7M753B
GLM-51.2M754B
GLM-4.7-Flash1.2M31.2B
Other >300B models
See more
DeepSeek-V3.2DeepSeek9.6M685B
InklingThinking Machines1.5M952B
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16NVIDIA1M561B

Kimi-K3Moonshot AI768.9K2.8T