Magica logo

Ministral 3 14B 2512 vs Ministral 3 3B 2512 (Comparative Analysis)

Loading comparison form...
Comparative Analysis: Ministral 3 14B 2512 vs. Ministral 3 3B 2512
Want to try out these models side by side?Try Magica for free

Overview

Ministral 3 3B 2512 was released 0 day before Ministral 3 14B 2512.
Ministral 3 14B 2512Ministral 3 14B 2512
Ministral 3 3B 2512Ministral 3 3B 2512
Model Provider
The organization behind this AI's development
Mistral logoMistral
Mistral logoMistral
Input Context Window
Maximum input tokens this model can process at once
262.1K
tokens
131.1K
tokens
Output Token Limit
Maximum output tokens this model can generate at once
Not specified
tokens
Not specified
tokens
Release Date
When this model first became publicly available
December 2nd, 2025
December 2nd, 2025

Capabilities & Features

Compare supported features, modalities, and advanced capabilities
Ministral 3 14B 2512
Ministral 3 3B 2512
Input Types
Supported input formats
📝Text🖼️Image
📝Text🖼️Image
Output Types
Supported output formats
📝Text
📝Text
Tokenizer
Text encoding system
MistralMistral
Key Features
Advanced capabilities
Function CallingStructured OutputReasoning ModeContent Moderation
Function CallingStructured OutputReasoning ModeContent Moderation
Open Source
Model availability
Available on HuggingFace →Available on HuggingFace →

Pricing

Ministral 3 14B 2512 is roughly 2.0x more expensive compared to Ministral 3 3B 2512 for input tokens and roughly 2.0x more expensive for output tokens.
Ministral 3 14B 2512Ministral 3 14B 2512
Ministral 3 3B 2512Ministral 3 3B 2512
Input Token Cost
Cost per million input tokens
$0.20
per million tokens
$0.10
per million tokens
Output Token Cost
Cost per million output tokens
$0.20
per million tokens
$0.10
per million tokens
Cache Read Cost
Cost to reuse cached input tokens
$0.02
per million tokens
$0.01
per million tokens

Benchmarks

Compare relevant benchmarks between Ministral 3 14B 2512 and Ministral 3 3B 2512.
Ministral 3 14B 2512Ministral 3 14B 2512
Ministral 3 3B 2512Ministral 3 3B 2512
Intelligence Index
Overall model quality across independent evaluations
11.2
(Artificial Analysis index; higher is better)
7.1
(Artificial Analysis index; higher is better)
Coding Index
Programming performance across independent evaluations
14.4
(Artificial Analysis index; higher is better)
4.8
(Artificial Analysis index; higher is better)
Agentic Index
Ability to complete multi-step agentic tasks
2.2
(Artificial Analysis index; higher is better)
1.6
(Artificial Analysis index; higher is better)
Best Design Arena Score
Highest human-preference Elo score across design arenas
1,103 Elo
(#90 in Website (44.8% win rate))
1,050 Elo
(#102 in Website (38.2% win rate))

At a Glance

Quick overview of what makes Ministral 3 14B 2512 and Ministral 3 3B 2512 unique.
Mistral logoMinistral 3 14B 2512 by Mistral understands both text and images, can use external tools and APIs, generates structured data. It can handle standard conversations with its 262.1K token context window. Very affordable at $0.20/M input and $0.20/M output tokens. Released December 2nd, 2025.
Mistral logoMinistral 3 3B 2512 by Mistral understands both text and images, can use external tools and APIs, generates structured data. It can handle standard conversations with its 131.1K token context window. Very affordable at $0.10/M input and $0.10/M output tokens. Released December 2nd, 2025.

Explore More Comparisons

Compare your models with top performers across different categories