Qwen3-Next-80B-A3B-Instruct
Qwen- Arena score
- 1417
- Among open models
- #38of 148
- Among all on Arena
- #128
- Votes
- 22,689
Measured on Qwen3-Next-80B-A3B-Instruct, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Chinese1460#35#1111.7K
- Medicine & health1456#15#621.2K
- Software & IT1447#32#1088K
- Coding1440#36#1214.8K
- Math1440#22#831.2K
- Spanish1435#27#95684
- Science1435#33#1163.5K
- Applied math1435#35#1091.1K
- Hard prompts, English1431#38#1275.2K
- Legal & government1431#28#1071.4K
- Hard prompts1428#35#11912K
- Business & finance1422#29#1034.3K
- English1422#44#1359.7K
- Expert1417#46#1441.1K
- German1417#28#107490
- Multi-turn1415#35#1294K
- French1413#43#141384
- Non-English1407#31#11412.9K
- Excluding ties1404#37#12616K
- Russian1404#35#1301.6K
- Long prompts1403#42#1475.4K
- Polish1398#36#1311K
- Japanese1396#20#88318
- Instructions1389#44#1476.4K
- Korean1363#30#121522
- Writing & literature1355#54#1805K
- Media & sports1349#51#1734.2K
- Creative writing1333#57#1913K
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-Next-80B-A3B-Instruct-GGUF26 builds
- MLX · Apple silicon: mlx-lm, LM Studiolmstudio-community/Qwen3-Next-80B-A3B-Instruct-MLX-4bit19 builds
- AWQ · vLLM, SGLangTheHouseOfTheDude/Qwen3-Next-80B-A3B-Instruct_Compressed-Tensors1 build
- GPTQ · vLLM, SGLangjart25/Qwen3-Next-80B-A3B-Instruct-Int4-GPTQ1 build
Most downloaded
- Qwen3-Next-80B-A3B-Instruct-GGUFunsloth · Quantization139.1K downloads
- Qwen_Qwen3-Next-80B-A3B-Instruct-GGUFbartowski · Quantization27.2K downloads
- Qwen3-Next-80B-A3B-Instruct-FP8Qwen · Quantization25.6K downloads
- qwen3-next-moetiny-random · Fine-tune10.2K downloads
- Qwen3-Next-80B-A3B-Instruct-MLX-4bitlmstudio-community · Quantization9.5K downloads
BenchClub runs
Not runnable yet
Runs open once a Qwen3-Next-80B-A3B-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