Qwen3-VL-235B-A22B-Instruct
Qwen- Arena score
- 1420
- Among open models
- #33of 148
- Among all on Arena
- #117
- Votes
- 11,286
Measured on Qwen3-VL-235B-A22B-Instruct, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Chinese1462#33#107713
- French1450#21#81261
- Science1445#26#921.7K
- Software & IT1442#37#1204K
- Expert1442#27#95594
- Hard prompts, English1439#32#1112.5K
- Legal & government1439#23#94735
- Coding1438#38#1252.3K
- Business & finance1433#16#742.2K
- Medicine & health1431#33#110626
- English1429#37#1224.9K
- Hard prompts1428#34#1165.7K
- Spanish1428#31#105459
- Multi-turn1428#25#1061.9K
- Math1427#32#109694
- German1424#24#96279
- Applied math1421#42#134594
- Polish1419#27#102540
- Long prompts1419#30#1122.2K
- Russian1408#32#124881
- Excluding ties1407#34#1228K
- Instructions1406#31#1162.9K
- Non-English1405#33#1226.4K
- Korean1392#16#80321
- Writing & literature1392#33#1292.3K
- Japanese1385#26#99170
- Media & sports1367#38#1461.9K
- Creative writing1365#39#1501.4K
About as strong, smaller
Compare
gemma-4-26B-A4B-itGoogle143425.8B

Qwen3.8-27BQwen143727.8B

Qwen3.5-27BQwen140927.8B

gemma-4-31B-itGoogle144331.3B
Discussion
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiounsloth/Qwen3-VL-235B-A22B-Instruct-GGUF10 builds
- MLX · Apple silicon: mlx-lm, LM StudioLibraxisAI/Qwen3-VL-235B-A22B-Instruct-mlx-nvfp43 builds
- AWQ · vLLM, SGLangQuantTrio/Qwen3-VL-235B-A22B-Instruct-AWQ2 builds
Most downloaded
- Qwen3-VL-235B-A22B-Instruct-FP8Qwen · Quantization96.8K downloads
- qwen3-vl-moetiny-random · Fine-tune9.3K downloads
- Qwen3-VL-235B-A22B-Instruct-GGUFunsloth · Quantization6.5K downloads
- Qwen3-VL-235B-A22B-Instruct-NVFP4RedHatAI · Quantization3.5K downloads
- Qwen3-VL-235B-A22B-Instruct-GGUFQwen · Quantization3.1K downloads
BenchClub runs
Not runnable yet
Runs open once a Qwen3-VL-235B-A22B-Instruct 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