Mistral Small 3.1 24B
Mar 2025
Mistral Small 3.1 24BCompare inon
Benchmarks of Mistral Small 3.1 24B18
BenchmarkByScoreRank
Knowledge1
Multimodal1
Writing16
No benchmark matches
Rankingconfiguration unstated?
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperGLM 5.3 FlashunstatedOpenwins 72%-41%$0.15 / $0.50Memory (4-bit): 14 GB → 193 GB+5
BetterGPT-5 Minihighwins 58%+71%$0.053
OpenGemma 4 31Bunstatedwins 70%-60%$0.10 / $0.34Memory (4-bit): 14 GB → 19 GB
CheaperHy3unstatedOpenwins 71%-43%$0.13 / $0.53Memory (4-bit): 14 GB → 179 GB+1CheaperGPT-6 Lunamaxwins 69%-50%$0.068Function calling only with none · Chat Completions+3ModelScoreCostPer taskWhat changes
GLM 5.3 FlashunstatedOpenwins 72%-41%$0.15 / $0.50Memory (4-bit): 14 GB → 193 GB+5Hy3unstatedOpenwins 71%-43%$0.13 / $0.53Memory (4-bit): 14 GB → 179 GB+1Gemma 4 31BunstatedOpenwins 70%-60%$0.10 / $0.34Memory (4-bit): 14 GB → 19 GBGPT-6 Lunamaxwins 69%-50%$0.068Function calling only with none · Chat Completions+3Gemma 4 26B A4BunstatedOpenwins 68%-35%$0.15 / $0.60Memory (4-bit): 14 GB → 15 GBModelScoreCostPer taskWhat changes
GPT-5 Minihighwins 58%+71%$0.053GPT-6 Lunamaxwins 69%-50%$0.068Function calling only with none · Chat Completions+3GPT-5.6 Lunaxhighwins 69%+12%$0.085GPT-5.6 Terraxhighwins 71%+1,019%$0.63Prompts with >272K input tokensGPT-6.1 Solmaxwins 75%+895%$0.72Remove unsupported parameters+5ModelScoreCostPer taskWhat changes
Gemma 4 31BunstatedOpenwins 70%-60%$0.10 / $0.34Memory (4-bit): 14 GB → 19 GBGemma 4 26B A4BunstatedOpenwins 68%-35%$0.15 / $0.60Memory (4-bit): 14 GB → 15 GB
Qwen3.8 27BunstatedOpenwins 63%+138%$0.42 / $2.55Memory (4-bit): 14 GB → 17 GB+5
Muse Glimmer 30BunstatedOpenwins 63%+24%$0.30 / $1.10Memory (4-bit): 14 GB → 18 GBQwen 3.5 27BunstatedOpenwins 62%+105%$0.30 / $2.40Memory (4-bit): 14 GB → 17 GBModelScoreCostPer taskWhat changes
Mistral Medium 3.5unstatedOpenwins 68%—$1.50 / $7.50Memory (4-bit): 14 GB → 77 GBMistral Large 3unstatedOpenwins 65%—$0.50 / $1.50Memory (4-bit): not verifiedMistral Large 4unstatedwins 64%—$1.36 / $4.18Infinite whitespace stream+4Mistral Largeunstatedsame—$2 / $6No image inputMistral Small 3unstatedOpenwins 44%—$0.05 / $0.08Context: 128K → 32K+1Mixtral 8x22B InstructunstatedOpenwins 39%—$2 / $6Context: 128K → 66K+2Mixtral 8x7B Instruct v0.1Openwins 35%—$0.54 / $0.54Context: 128K → 33K+2Mistral 7B Instruct v0.2Openwins 28%—$0.055 / $0.055Context: 128K → 33K+2All Mistral models →Run it yourself
estimateFits on✗ 8 GB (phone, laptop)✓ 16 GB · compressed✓ 24 GB GPU · compressed✓ 48 GB GPU · 8-bit✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use
History
2 versionsBenchmarks
all categoriesChat & Knowledge
Arena Text · overall1,303#154
Arena Text · Chinese1,252.6#148
Arena Text · English1,294.6#153
Arena Text · French1,272.6#125
Arena Text · German1,266.1#121
Arena Text · instruction following1,263.1#145
Arena Text · Japanese1,207.7#106
Arena Text · Korean1,206.9#118
Arena Text · non-English1,254.6#148
Arena Text · Polish1,241.6#125
Arena Text · Russian1,263.3#144
Arena Text · Spanish1,283.6#129
EQ-Bench 3783.6#46
Arena Text · overall · full cohort1,277.1#151
Writing & Language
Arena Text · creative writing1,270#148
EQ-Bench Creative Writing v3760.9#85
Arena Text · creative writing · full cohort1,252.2#144
Vision & Documents
Arena Vision · overall1,136.5#77
FAQ
How much does Mistral Small 3.1 24B cost?›
$0.35 per 1M input tokens and $0.56 per 1M output tokens (cheapest host: Cloudflare).
Is Mistral Small 3.1 24B free to use?›
There is no free API; the cheapest paid price is $0.35 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Mistral Small 3.1 24B, and what is it best at?›
#154 of 196 in Chat & Knowledge, #148 of 195 in Writing & Language, #77 of 88 in Vision & Documents.
Is Mistral Small 3.1 24B better than Gemma 3 4B?›
On Arena Text · creative writing, Mistral Small 3.1 24B scores 1,270 vs 1,275 — about the same.
How can I use Mistral Small 3.1 24B?›
Through the API of Cloudflare.
What is the context window of Mistral Small 3.1 24B?›
128K tokens, with up to 102K output tokens.
When was Mistral Small 3.1 24B released? Is there a newer version?›
Released 2025-03-11. It is the current version in its line.
Is Mistral Small 3.1 24B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Mistral Small 3.1 24B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Mistral Small 3.1 24B read images?›
It accepts text and images as input.
What is Mistral Small 3.1 24B?›
Mistral Small 3.1 24B is an open-weights language model from Mistral, released Mar 2025.
What are the best alternatives to Mistral Small 3.1 24B?›
GLM 5.3 Flash (cheaper), GPT-5 Mini (better), Gemma 4 31B (open weights).