Skip to main content

Mistral Small 3.2

MistralMistralOpen WeightApache 2.0 · Commercial OK

Description

Mistral-Small-3.2-24B-Instruct-2506 is a minor update of Mistral-Small-3.1-24B-Instruct-2503.

Release Date
2025-06-20
Parameters
23.6B
Context Length
128K
Modalities
image, text

Capability Radar

26
general
27
coding
40
reasoning
33
scienceest.
36
agents
90
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Code Ranking359
21.0
AA
General Ranking346
32.0
AA
Math Reasoning218
41.0
AA
Multimodal Ranking5
92.0
LS
Science350
33.0
AA

Benchmark Scores (LLM Stats)

Biology

GPQA46.1%SR

Code

HumanEval Plus92.9%SR
MBPP Plus78.3%SR

Communication

Wild Bench65.3%SR

Creativity

Arena Hard43.1%SR

Factuality

SimpleQA12.1%SR

Finance

MMLU80.5%SR
MMLU-Pro69.1%SR

General

IF84.8%SR
MMMU62.5%SR

Image To Text

DocVQA94.9%SR

Math

MATH69.4%SR
MathVista67.1%SR

Multimodal

AI2D92.9%SR
ChartQA87.4%SR

AA Evaluation Indices

Math Index
27.0
Intelligence Index
9.1
Math 500
0.9
Mmlu Pro
0.7
Gpqa
0.5
Ifbench
0.3
Aime
0.3
Tau2
0.3
Livecodebench
0.3
Aime 25
0.3
Scicode
0.3
Lcr
0.2
Terminalbench Hard
0.1
Hle
0.0

LLM Stats Category Scores

Image To Text
90
Multimodal
80
Vision
80
Language
70
Legal
70
Math
70
Finance
70
Healthcare
70
Communication
70
Reasoning
60
Physics
50
General
50
Biology
50
Chemistry
50
Creativity
40
Writing
40
Factuality
10

Pricing

Input Price$0.087 / 1M tokens
Output Price$0.25 / 1M tokens
Blended Price (3:1)$0.128 / 1M tokens

Speed

Tokens/sec143.9
Time to First Token0.48s
Time to Answer0.48s

Provider Price Ranking

Provider Price Ranking

3 providers

Cheapest: MistralMost Expensive: Regolo AI
ProviderInputOutput
1MistralPRIMARY
$0.087
$0.25
2LLM Gateway
$0.1
$0.3
3Regolo AI
$0.5
$2.2

Compare pricing across different API providers for this model.

External Sources