Mistral: Ministral 3 14B 2512

Mistral: Ministral 3 14B 2512

mistralai · Released Dec 2, 2025 Efficient
43.5
Our Score

Performance Profile

Intelligence3.4Technical2.3Value8Content3
Intelligence 3.4/10
Technical 2.3/10
Content 3/10
Value 8/10

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language..

$0.20 / 1M
Input Price
$0.20 / 1M
Output Price
262,144 tokens
Context Window
14B Parameters

Capabilities

Tool Use Function Calling Vision

Architecture

ModalityText + Image → Text
TokenizerMistral
Parameters14B

Performance Indices

Source: Artificial Analysis

16 Intelligence Index
10.9 Coding Index
15.9 Agentic Index
30 Math Index

Benchmark Scores

Intelligence

GPQA Diamond 57.2% Graduate-level scientific reasoning
HLE 4.6% Humanity's Last Exam
MMLU Pro 69.3% Multi-task language understanding
AIME 2025 30% Competition mathematics (2025)
SciCode 23.6% Scientific computing

Technical

LiveCodeBench 35.1% Live coding evaluation
TerminalBench Hard 4.5% Agentic terminal tasks
τ²-Bench 27.2% Conversational agent benchmark

Content

IFBench 32% Instruction following
LCR 22% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does Mistral: Ministral 3 14B 2512 stack up?

Compare side-by-side with other efficient models.

Compare Models

Model Information

OpenRouter ID mistralai/ministral-14b-2512
Providermistralai
Release Date December 2, 2025
Context Length262,144 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.20 $0.000200
Output $0.20 $0.000200

Live Performance

Live endpoint metrics — refreshed every 30 minutes.

99.2%
Avg Uptime
473ms
Best Latency (TTFT)
53 tok/s
Best Throughput
2/2
Active Endpoints
Available via: Mistral, NextBit

Leaderboard Categories