Mistral-Small-24B-Instruct-2501
Mistral AI- Arena score
- 1234
- Among open models
- #103of 148
- Among all on Arena
- #304
- Votes
- 14,681
Measured on Mistral Small 24B Instruct (2501), the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- English1256#104#3048.7K
- Software & IT1248#103#3013.5K
- Long prompts1246#99#2951.8K
- Coding1246#102#3002.1K
- Applied math1243#98#2891.4K
- Hard prompts, English1243#102#3012.4K
- Math1240#98#2881.7K
- Science1235#102#3032.6K
- Hard prompts1233#103#3013.6K
- Legal & government1219#107#312869
- Multi-turn1217#105#3112.2K
- Russian1216#104#3051.4K
- Medicine & health1216#101#294654
- Writing & literature1214#105#3153.9K
- Instructions1214#104#3025.5K
- German1211#81#256301
- Business & finance1205#105#3101.4K
- Chinese1204#105#3091.1K
- French1203#82#257142
- Expert1202#102#294754
- Non-English1198#107#3145.9K
- Creative writing1195#107#3162.4K
- Korean1188#70#230231
- Media & sports1184#106#3152.7K
- Excluding ties1129#103#3049.6K
- Japanese1111#76#253269
About as strong, smaller
Compare
granite-4.2-3bIBM Granite12923.7B
gemma-3-4b-itGoogle12914.3B

gemma-3n-E4B-itGoogle13067.8B

Molmo2-8BAi212878.7B
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM StudioMaziyarPanahi/Mistral-Small-24B-Instruct-2501-GGUF55 builds
- MLX · Apple silicon: mlx-lm, LM Studiomlx-community/Mistral-Small-24B-Instruct-2501-4bit9 builds
- AWQ · vLLM, SGLangstelterlab/Mistral-Small-24B-Instruct-2501-AWQ4 builds
- GPTQ · vLLM, SGLangfbaldassarri/mistralai_Mistral-Small-24B-Instruct-2501-autogptq-int4-gs128-asym9 builds
Most downloaded
- Mistral-Small-24B-Instruct-2501-FP8-dynamicRedHatAI · Quantization100.2K downloads
- Mistral-Small-24B-Instruct-2501-GGUFMaziyarPanahi · Quantization39.4K downloads
- Mistral-Small-24B-Instruct-2501unsloth · Fine-tune37.5K downloads
- Mistral-Small-24B-Instruct-2501-AWQstelterlab · Quantization22.6K downloads
- Mistral-Small-24B-Instruct-2501-quantized.w8a8RedHatAI · Quantization15.2K downloads
BenchClub runs
Not runnable yet
Runs open once a Mistral-Small-24B-Instruct-2501 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 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