NOUMENOpen app
NOUMEN

Mistral · Open weights

Ministral 3B

Added Dec 4, 2025Open weights

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

Ministral 3B is a tiny, efficient 3B parameter model from Mistral AI with vision capabilities, designed for edge deployment.

Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.10
Output
$0.10

Reference prices as published by the model provider. API example

Specifications

Context window
131.1K
Max output
32.8K
Average output (7 days)
54 tokens
Longer than 4% of 468 models

Side by side

Ministral 3B compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Ministral 3BMistralThis modelMistral Large 4MistralRemove
ProviderMistralMistral
Discovery tierOpen weightsOpen weights
AddedDec 4, 2025Oct 6, 2026
Limits
Context window131.07K524.29KBest
Max output32.77K—
Average output54 tokens—
Pricing, USD per 1M tokens
Input$0.10Best$0.68
Output$0.10Best$2.09
Cache read—$0.07
Performance
Request success (24h)—69.0%
Benchmark indexes
Intelligence Index4.8—
Coding Index4.8—
Math Index22.0—
Capabilities
ReasoningNoYes
ToolsNoYes
VisionNoYes
Structured outputNoYes
Reasoning effort—none, high

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Ministral 3B
  • Mistral Large 4

Intelligence Index

  • Ministral 3B4.8
  • Mistral Large 4—

Ministral 3B: Better than 0% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Ministral 3B: 4.8
    • Mistral Large 4: —

  • Math Index

    Composite of the math evaluations

    • Ministral 3B: 22.0
    • Mistral Large 4: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Ministral 3B: 0.7%
    • Mistral Large 4: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Ministral 3B: 0.0%
    • Mistral Large 4: —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Ministral 3B: 29 Elo
    • Mistral Large 4: —

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Ministral 3B: 0.0%
    • Mistral Large 4: —

  • AA-LCRv1.1

    Reasoning across long documents

    • Ministral 3B: 17.0%
    • Mistral Large 4: —

  • MLCR-AA

    Long-context reasoning over medical records

    • Ministral 3B: 0.0%
    • Mistral Large 4: —

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Ministral 3B: 5.4%
    • Mistral Large 4: —

  • GPQA Diamond

    Graduate-level science questions

    • Ministral 3B: 35.8%
    • Mistral Large 4: —

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Ministral 3B: 52.4%
    • Mistral Large 4: —

  • IFBench

    Following precise output instructions

    • Ministral 3B: 26.8%
    • Mistral Large 4: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Ministral 3B: 0.0%
    • Mistral Large 4: —

  • SciCode

    Scientific computing in Python

    • Ministral 3B: 15.3%
    • Mistral Large 4: —

  • LiveCodeBench

    Recent competitive programming problems

    • Ministral 3B: 24.7%
    • Mistral Large 4: —

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Ministral 3B: 22.0%
    • Mistral Large 4: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Ministral 3B: 0.0%
    • Mistral Large 4: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Ministral 3B: 24.9%
    • Mistral Large 4: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Ministral 3B: 17.0%
    • Mistral Large 4: —

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/ministral-3b-2512",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="mistralai/ministral-3b-2512",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Mistral

Other Mistral models, starting with the same family.