Mixtral-8x22B-Instruct-v0.1
Mistral AI- Arena score
- 1162
- Among open models
- #119of 148
- Among all on Arena
- #344
- Votes
- 51,416
Measured on Mixtral 8x22B Instruct v0.1, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- English1187#119#34229.9K
- Math1184#108#3176.8K
- Applied math1179#112#3246K
- Polish1171#78#238132
- French1166#89#268767
- Coding1165#116#3378.8K
- Legal & government1165#116#3332.8K
- Hard prompts, English1163#118#3409.5K
- Writing & literature1161#116#33812.8K
- Russian1158#115#3354.9K
- Software & IT1154#121#34514.4K
- Science1151#120#3468.7K
- Spanish1150#94#276826
- Hard prompts1150#118#34014.7K
- Instructions1147#118#33918.5K
- Long prompts1144#121#3445.9K
- Creative writing1141#117#3407.4K
- German1141#91#2821.7K
- Media & sports1139#114#3357.6K
- Multi-turn1130#120#3477.8K
- Non-English1128#119#34421.5K
- Medicine & health1120#116#3362.8K
- Business & finance1118#120#3465.6K
- Chinese1116#119#3415.7K
- Expert1113#119#3332.6K
- Korean1057#82#2641.2K
- Japanese1037#82#264972
- Excluding ties1024#119#34433.7K
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 StudioMaziyarPanahi/Mixtral-8x22B-Instruct-v0.1-GGUF5 builds
- AWQ · vLLM, SGLangMaziyarPanahi/Mixtral-8x22B-Instruct-v0.1-AWQ1 build
Most downloaded
- Mixtral-8x22B-Instruct-v0.1-GGUFMaziyarPanahi · Quantization4.4K downloads
- Mixtral-8x22B-Instruct-v0.1-GGUFimpactframes · Quantization501 downloads
- mixtral-8x22b-instruct-v0.1-topo-cbp-GGUFfrankmorales2020 · Quantization421 downloads
- Mixtral-8x22B-Instruct-v0.1-i1-GGUFmradermacher · Quantization398 downloads
- Mixtral-8x22B-Instruct-v0.1-AWQMaziyarPanahi · Quantization112 downloads
BenchClub runs
Not runnable yet
Runs open once a Mixtral-8x22B-Instruct-v0.1 build is registered.
More from Mistral AI
See more
Mistral-Large-4-1T-A52B18K—

Mistral-Medium-3.5-128B14.3K128B

Mistral-Large-3-675B-Instruct-25122.8K675B

Mistral-7B-Instruct-v0.21.1M7.2B
Other 80–300B models
See more
DeepSeek-V4-FlashDeepSeek1.2M291B

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