Mistral logo

Ministral 3B

3B

by Mistral

Ministral 3B is a 3B parameter model optimized for on-device and edge computing. It excels in knowledge, commonsense reasoning, and function-calling, outperforming larger models like Mistral 7B on most benchmarks. Supporting up to 128k context length, it’s ideal for orchestrating agentic workflows and specialist tasks with efficient inference.

Chat with Ministral 3B

Pricing

Input Tokens
Per 1M tokens
Free
Output Tokens
Per 1M tokens
Free
Image Processing
Per 1M tokens
$0.00/1M tokens

Supported Modalities

Input

text

Output

text

Performance Benchmarks

Intelligence Index
Overall intelligence score
10.9
Coding Index
Programming capability
5.4
Math Index
Mathematical reasoning
0.3
GPQA
Graduate-level questions
26.0%
MMLU Pro
Multitask language understanding
33.9%
HLE
Human-like evaluation
5.5%
LiveCodeBench
Real-world coding tasks
6.9%
AIME 2025
Advanced mathematics
0.3%
MATH 500
Mathematical problem solving
53.7%

Specifications

Context Length
131K tokens
Provider
Mistral
Throughput
257.474 tokens/s
Released
Oct 17, 2024
Model ID
mistralai/ministral-3b

Ready to try it?

Start chatting with Ministral 3B right now. No credit card required.

Start Chatting

More from Mistral

View all models