Qwen3-235B-A22B-Thinking-2507
Qwen- Arena score
- 1415
- Among open models
- #39of 148
- Among all on Arena
- #133
- Votes
- 8,809
Measured on Qwen3-235B-A22B-Thinking (2507), the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Chinese1482#20#74535
- Expert1463#18#73423
- Medicine & health1458#13#57506
- Applied math1436#33#105474
- Science1434#35#1211.5K
- Hard prompts, English1433#36#1241.7K
- Software & IT1431#45#1422.9K
- English1430#35#1203.9K
- Coding1425#47#1491.6K
- Hard prompts1416#43#1423.8K
- Legal & government1415#41#144532
- Math1414#41#139475
- Business & finance1413#38#1221.5K
- Multi-turn1407#44#1471.4K
- German1406#34#122210
- Excluding ties1402#39#1326.2K
- Russian1399#37#137528
- Long prompts1399#45#1521.6K
- Non-English1397#40#1414.9K
- Polish1390#37#137783
- Spanish1389#50#162185
- Writing & literature1388#35#1371.9K
- Japanese1387#25#98442
- Instructions1386#45#1532.1K
- Creative writing1384#32#1301.1K
- Korean1375#26#106204
- Media & sports1370#37#1431.5K
About as strong, smaller
Compare
gemma-4-26B-A4B-itGoogle143425.8B

Qwen3.8-27BQwen143727.8B

Qwen3.5-27BQwen140927.8B

gemma-4-31B-itGoogle144331.3B
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiounsloth/Qwen3-235B-A22B-Thinking-2507-GGUF14 builds
- MLX · Apple silicon: mlx-lm, LM Studiomlx-community/Qwen3-235B-A22B-Thinking-2507-4bit13 builds
- AWQ · vLLM, SGLangQuantTrio/Qwen3-235B-A22B-Thinking-2507-AWQ1 build
- GPTQ · vLLM, SGLangQuantTrio/Qwen3-235B-A22B-Thinking-2507-GPTQ-Int4-Int8Mix1 build
Most downloaded
- Qwen3-235B-A22B-Thinking-2507-FP8Qwen · Quantization24.1K downloads
- Qwen3-235B-A22B-Thinking-2507-4bitmlx-community · Quantization11.9K downloads
- Qwen3-235B-A22B-Thinking-2507-GGUFunsloth · Quantization3.1K downloads
- Qwen3-Nemotron-235B-A22B-GenRMnvidia · Fine-tune2.2K downloads
- AReaL-SEA-235B-A22BinclusionAI · Fine-tune2K downloads
BenchClub runs
Not runnable yet
Runs open once a Qwen3-235B-A22B-Thinking-2507 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 80–300B models
See more
DeepSeek-V4-FlashDeepSeek1.2M291B

MiniMax-M2.5MiniMax1M229B
Inkling-SmallThinking Machines1M266B
Hy3Tencent987.2K299B