Browse all Mistral text models
Provider logo

Ministral 8B

mistralai/ministral-8b-2512
Provider logo

Ministral 8B

mistralai/ministral-8b-2512

Ministral 8B is an efficient 8B parameter model from Mistral AI with vision capabilities, designed for edge deployment.

Added Dec 4, 2025

Model weights

Context Window

262.1K

Max Output

32.8K

Avg output tokens (7d)

80 tokens

5%

Input Price (Auto)

$0.15/1M

Output Price (Auto)

$0.15/1M

Cache Read (Auto)

$0.075/1M

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

5.5

Better than 10% of models compared

Coding Index

9.7

Better than 9% of models compared

Agentic Index

0.6

Better than 4% of models compared

Agentic work

AutomationBench-AA

Workflow automation with guardrail penalties

0.5%

Better than 10% of models compared

AA-Briefcase

Agentic knowledge work (Elo)

99 Elo

Better than 8% of models compared

GDPval-AA v2

Economically valuable tasks (Elo)

405 Elo

Better than 15% of models compared

Document reasoning

GDP.pdf

Professional PDF reasoning: all-pass rate

0.8%

Better than 6% of models compared

AA-LCR v1.1

Long context reasoning with updated grading

25.7%

Better than 29% of models compared

Reasoning

HLE

Humanity's Last Exam

4.3%

Better than 19% of models compared

IFBench

Instruction-following benchmark

29.1%

Better than 13% of models compared

CritPt

Research-level physics reasoning

0.0%

Coding

Terminal-Bench v4.0

Practical coding and terminal tasks

0.0%

Better than 17% of models compared

SciCode

Python programming for scientific computing

20.7%

Better than 2% of models compared

LiveCodeBench

Contamination-free coding benchmark

30.3%

Better than 36% of models compared

Math

AIME 2025

American Invitational Mathematics Examination 2025

31.7%

Better than 33% of models compared

Knowledge

MMLU-Pro

Professional and academic subject knowledge

64.2%

Better than 26% of models compared

AA-Omniscience Accuracy

Proportion of correctly answered questions

13.0%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

94.2%

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

47.1%

Better than 21% of models compared

Terminal-Bench Hard (legacy)

Agentic coding and terminal use

4.5%

Better than 29% of models compared

T²-Bench Telecom (legacy)

Conversational AI agents in dual-control scenarios

26.6%

Better than 32% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

25.7%

Better than 29% of models compared

GDPval-AA (unversioned / legacy)

Economically valuable tasks

0.0%

Last updated Sep 13, 2026

Artificial Analysis

Providers

Auto routing is available for this model. Explicit provider selection is not available.

Loading provider options…

Compare Ministral 8B with similar models from the same provider or model family.