GLM-4.5
Z.ai- Arena score
- 1430
- Among open models
- #23of 148
- Among all on Arena
- #95
- Votes
- 23,746
Measured on GLM-4.5, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Chinese1465#26#971.8K
- Medicine & health1455#19#661.4K
- Spanish1454#14#56676
- Science1445#28#943.9K
- Software & IT1441#38#1228.1K
- Legal & government1438#25#971.5K
- English1437#30#10810.1K
- Coding1434#41#1334.7K
- Expert1433#33#1131.2K
- Applied math1430#39#1201.3K
- Hard prompts, English1430#40#1304.8K
- Hard prompts1429#32#11411.1K
- Math1428#31#1081.4K
- Excluding ties1423#23#9616.9K
- Polish1422#26#1011.7K
- Business & finance1420#30#1054.2K
- Non-English1417#23#9713.6K
- French1417#41#136339
- Japanese1416#13#61774
- Multi-turn1415#36#1303.7K
- Russian1413#27#1141.6K
- Long prompts1412#36#1285.1K
- German1407#33#120535
- Media & sports1405#17#884.3K
- Instructions1404#35#1226.1K
- Writing & literature1402#28#1125.3K
- Creative writing1395#28#1123.1K
- Korean1379#25#102646
About as strong, smaller
Compare
gemma-4-26B-A4B-itGoogle143425.8B

Qwen3.8-27BQwen143727.8B

gemma-4-31B-itGoogle144331.3B

Qwen3-Next-80B-A3B-InstructQwen141781.3B
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiounsloth/GLM-4.5-GGUF11 builds
- MLX · Apple silicon: mlx-lm, LM Studiomlx-community/GLM-4.5-4bit6 builds
Most downloaded
BenchClub runs
Not runnable yet
Runs open once a GLM-4.5 build is registered.
More from Z.ai
See more
GLM-5.3-Flash6.4M321B
GLM-5.31.7M753B
GLM-4.7-Flash1.2M31.2B
GLM-51.2M754B
Other >300B models
See more
DeepSeek-V3.2DeepSeek9.9M685B
InklingThinking Machines1.4M952B
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16NVIDIA1M561B

Kimi-K3Moonshot AI765.8K2.8T