QwQ-32B
Qwen- Arena score
- 1329
- Among open models
- #79of 148
- Among all on Arena
- #234
- Votes
- 25,160
Measured on QwQ-32B, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Chinese1378#64#2021.5K
- Math1359#66#2081.7K
- Applied math1356#69#2151.6K
- Spanish1352#63#195394
- English1351#78#23012.9K
- Software & IT1347#80#2347.3K
- Science1347#74#2234.5K
- Hard prompts, English1341#79#2334.6K
- Medicine & health1340#74#2241.3K
- French1338#62#198314
- Legal & government1336#74#2281.6K
- Coding1333#80#2394K
- Hard prompts1325#78#2358.8K
- Expert1323#74#2231.2K
- Business & finance1319#77#2263.5K
- Multi-turn1313#78#2403.8K
- German1313#62#197670
- Long prompts1308#80#2454.1K
- Non-English1305#76#23412.2K
- Writing & literature1301#73#2336.1K
- Russian1297#77#2392.1K
- Instructions1297#81#2447.2K
- Polish1288#64#2111.2K
- Creative writing1287#73#2363.7K
- Media & sports1279#77#2394.5K
- Excluding ties1279#79#23517.1K
- Korean1279#54#190409
- Japanese1262#53#185618
About as strong, smaller
Compare
granite-4.2-8bIBM Granite13198.8B
gemma-3-12b-itGoogle133412.2B
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM StudioMaziyarPanahi/QwQ-32B-GGUF64 builds
- MLX · Apple silicon: mlx-lm, LM Studiomlx-community/QwQ-32B-4bit29 builds
- AWQ · vLLM, SGLangQwen/QwQ-32B-AWQ6 builds
- GPTQ · vLLM, SGLangModelCloud/QwQ-32B-gptqmodel-4bit-vortex-v17 builds
Most downloaded
BenchClub runs
Not runnable yet
Runs open once a QwQ-32B 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