Mixtral-8x7B-Instruct-v0.1
Mistral AI- Arena score
- 1132
- Among open models
- #125of 148
- Among all on Arena
- #354
- Votes
- 73,503
Measured on Mixtral 8x7B 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
- English1168#126#35346.3K
- French1166#88#2671.3K
- Math1147#120#3399.7K
- Applied math1143#122#3418.5K
- Hard prompts, English1135#125#35113.4K
- Legal & government1132#120#3434K
- Coding1126#125#35511.8K
- Software & IT1125#127#35620.1K
- Writing & literature1123#123#35517.9K
- Science1117#125#35612.8K
- Hard prompts1115#125#35319.5K
- Multi-turn1115#122#35110.9K
- German1114#94#2872K
- Spanish1111#99#2871.1K
- Instructions1109#126#35825K
- Creative writing1109#123#35411.2K
- Media & sports1105#122#35011K
- Long prompts1103#127#3596.6K
- Medicine & health1094#122#3474.1K
- Russian1090#124#3555.2K
- Expert1087#124#3403.2K
- Business & finance1083#125#3557.1K
- Non-English1077#126#35927.2K
- Polish1072#81#243184
- Chinese1055#128#3618.3K
- Excluding ties978#125#35449K
- Korean968#91#279778
- Japanese931#90#283960
About as strong, smaller
Compare
granite-3.1-2b-instructIBM Granite11272.5B
gemma-2-2b-itGoogle11562.6B
granite-4.2-3bIBM Granite12923.7B
gemma-3-4b-itGoogle12914.3B
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM StudioTheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF25 builds
- MLX · Apple silicon: mlx-lm, LM Studiocontinuum-ai/mixtral-8x7b-instruct-compacted-conservative2 builds
- AWQ · vLLM, SGLangTheBloke/Mixtral-8x7B-Instruct-v0.1-AWQ3 builds
- GPTQ · vLLM, SGLangTheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ4 builds
Most downloaded
- Mixtral-8x7B-Instruct-v0.1-GGUFTheBloke · Quantization28.1K downloads
- Mixtral-8x7B-Instruct-v0.1RedHatAI · Fine-tune16K downloads
- GritLM-8x7BGritLM · Fine-tune9.7K downloads
- Mixtral-8x7B-Instruct-v0.1-GGUFmradermacher · Quantization4.1K downloads
- Mixtral-8x7B-Instruct-v0.1-michuggingface-mic · Fine-tune2.3K downloads
BenchClub runs
Not runnable yet
Runs open once a Mixtral-8x7B-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 40–80B models
See more
Qwen3-Coder-NextQwen347.7K79.7B

Llama-3.3-70B-InstructMeta Llama344.4K70.6B

falcon-40bTII11.6K41.8B
Jamba-v0.1AI21 Labs4.5K51.6B