llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsMistral Small 3.1 24B

Mistral AI model product

Mistral Small 3.1 24B

Building upon Mistral Small 3 (2501), Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance. With 24 billion parameters, this model achieves top-tier capabilities in both text and vision tasks.

Updated Aug 10, 2026. Default version: Mistral Small 3.1 24B Instruct

Compare
LLMBoard score43.5Mistral Small 3.1 24B Instruct
Coverage100%7 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
Mistral Small 3.1 24B Instruct
Released
Mar 17, 2025
Knowledge cutoff
Unknown
Parameters
24B
Context window
N/A
Max output
N/A
Inputs
image, text
Outputs
text
Open weights
No
License
Apache 2.0

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

Mistral Small 3.1 24B Instruct category scores

Benchmark results

Published benchmark records for the scored version Mistral Small 3.1 24B Instruct.

9 rows
Columns

Show columns

TriviaQA0.851876.5%CAug 7, 2026
MBPP0.7183752.8%CAug 7, 2026
HumanEval0.9227672.0%CAug 7, 2026
SimpleQA0.1404613.3%CAug 7, 2026
MATH0.7427141.4%CAug 7, 2026
MMMU0.6476325.8%CAug 7, 2026
MMLU0.85710043.4%CAug 7, 2026
MMLU-Pro0.79612925.8%CAug 7, 2026
GPQA0.518923319.0%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

80 rows
Columns

Show columns

visioncaptioning261154.2269N/AAug 6, 2026
vision style controlcaptioning271135.0269N/AAug 6, 2026
visioncreative writing311143.5777N/AJan 9, 2026
vision style controlcreative writing321132.0777N/AJan 9, 2026
visionentity recognition421151.2246N/AAug 6, 2026
vision style controlentity recognition441126.6246N/AAug 6, 2026
visionhumor701139.2951N/AAug 6, 2026
vision style controlhumor711117.7951N/AAug 6, 2026
visionchinese771137.7713N/AAug 6, 2026
visioncreative writing vision801133.1772N/AAug 6, 2026
vision style controlchinese801137.4713N/AAug 6, 2026
vision style controlcreative writing vision801119.1772N/AAug 6, 2026
vision style controlhomework901158.5824N/AAug 6, 2026
visionhomework911155.8824N/AAug 6, 2026
visionocr981131.47,304N/AAug 6, 2026
vision style controlocr981132.77,304N/AAug 6, 2026
visiondiagram991119.71,655N/AAug 6, 2026
visionenglish991159.315,138N/AAug 6, 2026
vision style controldiagram991129.51,655N/AAug 6, 2026
visionoverall1021136.928,886N/AAug 6, 2026
vision style controlenglish1061140.915,138N/AAug 6, 2026
vision style controloverall1071127.628,886N/AAug 6, 2026
textjapanese1741212.6712N/AAug 6, 2026
text style controljapanese1761243.4712N/AAug 6, 2026
textkorean1921205.2668N/AAug 6, 2026
textspanish1931281.0703N/AAug 6, 2026
textgerman1951263.0830N/AAug 6, 2026
textpolish1981243.42,777N/AAug 6, 2026
text style controlpolish1991280.62,777N/AAug 6, 2026
textfrench2011272.5411N/AAug 6, 2026
text style controlkorean2011241.2668N/AAug 6, 2026
text style controlspanish2011305.2703N/AAug 6, 2026
text style controlgerman2021294.1830N/AAug 6, 2026
text style controlfrench2091307.1411N/AAug 6, 2026
textexpert2171259.31,645N/AAug 6, 2026
textlonger query2181299.26,297N/AAug 6, 2026
textcoding2191310.26,136N/AAug 6, 2026
texthard prompts english2231296.97,618N/AAug 6, 2026
textindustry software and it services2261302.611,085N/AAug 6, 2026
text style controlcoding2271361.96,136N/AAug 6, 2026
text style controlexpert2271303.71,645N/AAug 6, 2026
texthard prompts2291278.014,692N/AAug 6, 2026
textindustry entertainment and sports and media2291251.05,837N/AAug 6, 2026
textinstruction following2301265.08,044N/AAug 6, 2026
textrussian2311264.22,002N/AAug 6, 2026
textindustry medicine and healthcare2321264.91,953N/AAug 6, 2026
text style controlrussian2331298.52,002N/AAug 6, 2026
textindustry business and management and financial operations2341258.15,573N/AAug 6, 2026
textcreative writing2361253.04,160N/AAug 6, 2026
textindustry mathematical2361272.51,937N/AAug 6, 2026
text style controllonger query2361322.06,297N/AAug 6, 2026
text style controlhard prompts english2371335.37,618N/AAug 6, 2026
text style controlindustry entertainment and sports and media2371276.95,837N/AAug 6, 2026
textchinese2381245.51,691N/AAug 6, 2026
textindustry writing and literature and language2381269.27,114N/AAug 6, 2026
text style controlindustry software and it services2381344.011,085N/AAug 6, 2026
textenglish2391298.615,925N/AAug 6, 2026
text style controlindustry mathematical2401290.31,937N/AAug 6, 2026
text style controlinstruction following2411295.08,044N/AAug 6, 2026
textexclude ties2431204.623,696N/AAug 6, 2026
textoverall2441277.933,180N/AAug 6, 2026
textmath2441261.92,128N/AAug 6, 2026
textmulti turn2441271.15,570N/AAug 6, 2026
text style controlhard prompts2441319.014,692N/AAug 6, 2026
text style controlindustry medicine and healthcare2441315.61,953N/AAug 6, 2026
textindustry legal and government2451272.02,160N/AAug 6, 2026
textnon english2461251.017,244N/AAug 6, 2026
text style controlindustry writing and literature and language2461290.27,114N/AAug 6, 2026
text style controlmath2471277.82,128N/AAug 6, 2026
text style controlcreative writing2481270.94,160N/AAug 6, 2026
text style controlindustry business and management and financial operations2491297.35,573N/AAug 6, 2026
text style controlnon english2521278.717,244N/AAug 6, 2026
textindustry life and physical and social science2531265.95,274N/AAug 6, 2026
text style controlenglish2531321.815,925N/AAug 6, 2026
text style controlmulti turn2531291.55,570N/AAug 6, 2026
text style controlexclude ties2541240.523,696N/AAug 6, 2026
text style controloverall2561303.333,180N/AAug 6, 2026
text style controlindustry legal and government2571307.62,160N/AAug 6, 2026
text style controlchinese2591286.41,691N/AAug 6, 2026
text style controlindustry life and physical and social science2631306.05,274N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.10 input, $0.30 output per 1M via NanoGPT
Tracked offerings
3
3 rows
Columns

Show columns

NanoGPTmistral-small-31-24b-instructglobal$0.10$0.30128KAug 7, 2026
Cloudflare AI Gatewayworkers-ai/@cf/mistralai/mistral-small-3.1-24b-instructglobal$0.35$0.56128KAug 7, 2026
Cloudflare Workers AI@cf/mistralai/mistral-small-3.1-24b-instructglobal$0.351$0.555128KAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Mistral Small 3.1 24B versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

2 rows
Columns

Show columns

Mistral Small 3.1 24B BaseMar 17, 2025N/A24B128K128KNoApache 2.0
Mistral Small 3.1 24B InstructMar 17, 202543.524BN/AN/ANoApache 2.0

What is Mistral Small 3.1 24B?

A concise description based on the published model registry.

Building upon Mistral Small 3 (2501), Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance. With 24 billion parameters, this model achieves top-tier capabilities in both text and vision tasks.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

Mistral Small 3.1 24B vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

Mistral Small 3.1 24BvsDeepSeek-R1Mistral Small 3.1 24BvsQwen2.5 14BMistral Small 3.1 24BvsLlama 3.1 Nemotron 70BMistral Small 3.1 24BvsGPT-5.4-nanoMistral Small 3.1 24BvsQwen3 VL 235B A22BMistral Small 3.1 24BvsPhi 3.5 MoE

Models similar to Mistral Small 3.1 24B

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#85+5.6
MA

Mistral Small 4

Mistral AI

49.1 LLMBoard

DetailsCompare
#128-9.3
MA

Mistral Small 3 24B

Mistral AI

34.3 LLMBoard

DetailsCompare
#148-20.2
MA

Ministral 8B

Mistral AI

23.4 LLMBoard

DetailsCompare
#159-28.4
MA

Pixtral 12B

Mistral AI

15.2 LLMBoard

DetailsCompare
#103+0.2
NV

Llama 3.1 Nemotron 70B

NVIDIA

43.8 LLMBoard

DetailsCompare
#102+0.4
AC

Qwen2.5 14B

Alibaba Cloud / Qwen Team

43.9 LLMBoard

DetailsCompare

FAQ

Common questions about Mistral Small 3.1 24B.

When was Mistral Small 3.1 24B released?

Mistral Small 3.1 24B's default version was released on Mar 17, 2025.

How much does Mistral Small 3.1 24B cost?

No official standard PAYG price is currently available for Mistral Small 3.1 24B. The lowest tracked third-party offer starts at $0.10 input and $0.30 output via NanoGPT.

Who created Mistral Small 3.1 24B?

Mistral Small 3.1 24B is published under Mistral AI in the model registry.

What is the context window for Mistral Small 3.1 24B?

The current registry does not publish a context window for the default version.

Is Mistral Small 3.1 24B open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer Mistral Small 3.1 24B?

3 published provider offerings are linked to the default version.

What models should I compare Mistral Small 3.1 24B with?

Nearby ranked alternatives include DeepSeek-R1, Qwen2.5 14B, Llama 3.1 Nemotron 70B.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai