Mistral-7B-Instruct-v0.2
Mistral AIBenchClub cloud
No cloud result yet
Headline numbers come from BenchClub’s pinned cloud runner.
- Arena score
- 1090
- Among open models
- #134of 148
- Among all on Arena
- #378
- Votes
- 19,402
Measured on Mistral 7B Instruct v0.2, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- English1134#132#37012.7K
- Legal & government1099#127#360976
- Hard prompts, English1089#133#3723.7K
- Applied math1086#131#3652.2K
- Math1085#131#3652.6K
- Software & IT1083#136#3785.2K
- Coding1082#135#3743.1K
- Science1078#132#3733.3K
- Writing & literature1073#134#3854.7K
- Medicine & health1068#126#3531.1K
- Creative writing1068#132#3823K
- Hard prompts1067#136#3775.2K
- Multi-turn1062#132#3752.6K
- Long prompts1060#135#3731.6K
- Instructions1060#133#3766.7K
- Media & sports1058#132#3792.9K
- Business & finance1038#135#3751.7K
- French1037#103#295473
- Expert1036#133#359798
- Spanish1026#108#303202
- Russian1018#134#3731.2K
- Non-English1012#140#3886.7K
- Chinese1009#136#3782K
- German987#108#316564
- Excluding ties915#133#37712.7K
- Japanese878#94#288167
About as strong, smaller
Compare
granite-3.1-2b-instructIBM Granite11272.5B
gemma-2-2b-itGoogle11562.6B
granite-3.0-2b-instructIBM Granite10802.6B
Llama-3.2-3B-InstructMeta Llama11103.2B
BenchClub runs
Built on it
Top 10 among open models in#3Merges
Ways to run it
- GGUF · llama.cpp, Ollama, LM StudioTheBloke/Mistral-7B-Instruct-v0.2-GGUF74 builds
- MLX · Apple silicon: mlx-lm, LM Studiomaciejonek/Mistral-7b-Gandalf1 build
- AWQ · vLLM, SGLangTheBloke/Mistral-7B-Instruct-v0.2-AWQ8 builds
- GPTQ · vLLM, SGLangTheBloke/Mistral-7B-Instruct-v0.2-GPTQ3 builds
Most downloaded
- Mistral-7B-Instruct-v0.2-AWQTheBloke · Quantization185.1K downloads
- Mistral-7B-Instruct-v0.2-GGUFTheBloke · Quantization52.6K downloads
- Mistral-7B-Instruct-v0.2-llamafilemozilla-ai · Quantization9.5K downloads
- bigstral-12b-32kabacusai · Fine-tune9.2K downloads
- Sentiment-Analysis-7Bmicrosoft · Fine-tune3.2K downloads
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-v0.1440.8K7.2B
Other 3–9B models
See more
NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA1.9M4.0B
granite-4.1-8bIBM Granite79.4K8.8B
Molmo2-8BAi247.6K8.7B
Spark-X2.6-4BXHToken32.9K4.1B