DataLearner logo
MI

Mistral-Small-3.2

Chat model

Mistral-Small-3.2-24B-Instruct-2506

Release date: 2025-06-20Updated: 2025-06-27Views: 1,219
Parameters
24B
Context length
128K
Multilingual
Supported
Reasoning ability
3/5

Mistral-Small-3.2-24B-Instruct-2506 is an AI model published by MistralAI, released on 2025-06-20, for Chat model, with 24B parameters, and 128K context length, requiring about 47.04 GB storage, with a 1252.70 score on Creative Writing.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Mistral-Small-3.2

Model basics

Reasoning traces
No data
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
96K tokens
Model type
Chat model
Modality (in / out)
Text → Text
Release date
2025-06-20
Model file size
47.04 GB
MoE architecture
No
Total params / Active params
24B / Not applicable
Knowledge cutoff
No data
Mistral-Small-3.2

Open source & experience

Code license
Weights license
Apache 2.0- Commercial use permitted
GitHub repo
N/A
Mistral-Small-3.2

Official resources

Paper
N/A
DataLearnerAI blog
N/A
Mistral-Small-3.2

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$0.075/ 1M$0.200/ 1M

“—” means the modality is not billed in that direction, or the vendor has not published a price for it.

Mistral-Small-3.2

Benchmark Results

Mistral-Small-3.2 currently shows benchmark results led by MMLU (53 / 124, score 80.50), MATH (20 / 42, score 69.42), GPQA (11 / 16, score 44.22). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

General Knowledge

3 evaluations
Benchmark / mode
Score
Rank/total
MMLU
Standard Mode
80.50
53 / 124
MMLU Pro
Standard Mode
69.06
98 / 133
GPQA
Standard Mode
44.22
11 / 16

Math and Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
MATH
Standard Mode
69.42
20 / 42

General Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
46.13
247 / 270

Common Sense

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleQA
Standard Mode
12.10
39 / 47

Writing and Creative Capabilities

1 evaluations
Benchmark / mode
Score
Rank/total
Creative Writing
Standard Mode
1252.70
72 / 99
Mistral-Small-3.2

Publisher

Mistral-Small-3.2-24B-Instruct-2506

Model Overview

Mistral-Small-3.2-24B-Instruct-2506 is an AI model published by MistralAI, released on 2025-06-20, for Chat model, with 24B parameters, and 128K context length, requiring about 47.04 GB storage, with a 1252.70 score on Creative Writing.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code