QwQ-32B-Preview
Qwen- Arena score
- 1162
- Among open models
- #120of 148
- Among all on Arena
- #345
- Votes
- 3,231
Measured on QwQ-32B-Preview, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Applied math1222#102#302422
- Chinese1218#98#300206
- Math1213#103#303480
- English1184#121#3441.8K
- Hard prompts, English1171#115#336519
- Long prompts1167#115#334475
- Hard prompts1162#116#336852
- Instructions1156#116#3351.3K
- Coding1155#119#343566
- Software & IT1154#120#344824
- Science1154#119#343583
- Legal & government1143#118#338214
- Multi-turn1141#118#343487
- Writing & literature1139#120#347855
- Expert1134#115#325232
- Creative writing1134#119#343454
- Non-English1130#118#3421.4K
- Media & sports1114#120#346540
- Russian1114#119#344527
- Business & finance1098#123#351374
- Excluding ties1022#120#3452.2K
About as strong, smaller
Compare
gemma-2-2b-itGoogle11562.6B
granite-4.2-3bIBM Granite12923.7B
gemma-3-4b-itGoogle12914.3B

gemma-3n-E4B-itGoogle13067.8B
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiobartowski/QwQ-32B-Preview-GGUF36 builds
- MLX · Apple silicon: mlx-lm, LM Studiomlx-community/Qwen_QwQ-32B-Preview_MLX-8bit31 builds
- AWQ · vLLM, SGLangKirillR/QwQ-32B-Preview-AWQ3 builds
- GPTQ · vLLM, SGLangModelCloud/QwQ-32B-Preview-gguf-vortex-v15 builds
Most downloaded
BenchClub runs
Not runnable yet
Runs open once a QwQ-32B-Preview build is registered.
More from Qwen
See more
Qwen3.8-27B6.9M27.8B

Qwen3.5-27B1.7M27.8B

Qwen3.5-35B-A3B1.4M36.0B

Qwen3.5-122B-A10B775.1K125B
Other 20–40B models
See more
gemma-4-31B-itGoogle6.3M31.3B
Ornith-1.0-35BOrnith1.4M35.1B
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA1.3M31.6B
GLM-4.7-FlashZ.ai1.2M31.2B