Mistral-Small-3.2-24B-Instruct-2506
Mistral AIBenchClub cloud
No cloud result yet
Headline numbers come from BenchClub’s pinned cloud runner.
- Arena score
- 1338
- Among open models
- #73of 148
- Among all on Arena
- #223
- Votes
- 17,431
Measured on Mistral Small 3.2 (2506), the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Coding1363#73#2203.3K
- Software & IT1361#75#2235.9K
- English1358#74#2227.5K
- Hard prompts, English1357#72#2203.4K
- Applied math1352#71#218990
- Spanish1346#66#201420
- Medicine & health1346#69#2171.1K
- Multi-turn1343#66#2123K
- Math1342#72#2211K
- Legal & government1340#72#2221.1K
- Chinese1340#75#2271.1K
- German1340#57#186427
- Science1339#76#2282.9K
- French1336#63#199227
- Hard prompts1335#74#2257.7K
- Long prompts1326#70#2243.4K
- Business & finance1325#75#2212.9K
- Russian1324#71#2201.2K
- Polish1317#55#1931.7K
- Non-English1315#74#2269.9K
- Writing & literature1310#68#2243.8K
- Instructions1309#75#2304.4K
- Creative writing1304#68#2222.1K
- Media & sports1304#66#2163.1K
- Excluding ties1292#73#22312.2K
- Expert1291#83#240855
- Japanese1275#49#178519
- Korean1256#60#201362
BenchClub runs
No runs yet
Be the first to benchmark Mistral-Small-3.2-24B-Instruct-2506 on your own hardware.
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiounsloth/Mistral-Small-3.2-24B-Instruct-2506-GGUF26 builds
- MLX · Apple silicon: mlx-lm, LM Studiolmstudio-community/Mistral-Small-3.2-24B-Instruct-2506-MLX-6bit25 builds
- GPTQ · vLLM, SGLanggratex/mistral-small-3.2-24b-Instruct-GPTQ-W4A161 build
Most downloaded
- Mistral-Small-3.2-24B-Instruct-2506-GGUFunsloth · Quantization137.7K downloads
- Cydonia-24B-v4.3-GGUFTheDrummer · Quantization134.1K downloads
- mistralai_Mistral-Small-3.2-24B-Instruct-2506-GGUFbartowski · Quantization52.7K downloads
- Mistral-Small-3.2-24B-Instruct-2506-GGUFlmstudio-community · Quantization24.5K downloads
- Mistral-Small-3.2-24B-Instruct-2506-MLX-6bitlmstudio-community · Quantization19.7K 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-Instruct-v0.21.1M7.2B
Other 20–40B models
See more
Qwen3.8-27BQwen6.9M27.8B

gemma-4-31B-itGoogle6.3M31.3B
Ornith-1.0-35BOrnith1.4M35.1B
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA1.3M31.6B