Mistral Medium 3

Last updated: Recently

Model Type

MText

Max Context

131K

Max Output

Parameter Scale

131,072 token context window. Includes independent benchmarks from Artificial Analysis.

Input Modality

text, image, file

Output Modality

text

Inference Speed

42.474 tokens/s

Latest Release Date

5/7/2025

SDK Ecosystem

artificial-analysismanufactureraa-bootstrap

Model Overview Fields

name

Mistral Medium 3

Release date

5/7/2025

Performance

42.474 tokens/s

model_creator.name

Mistral

AA Evaluation Scores

AA Intelligence Index

18.8

AA Coding Index

13.6

AA Math Index

30.3

MMLU Pro

0.76

GPQA

0.578

HLE

0.043

LiveCodeBench

0.4

SciCode

0.331

Math-500

0.906666666666667

AIME

0.44

AIME 2025

0.303333333333333

IFBench

0.392517006802721

LCR

0.28

TerminalBench Hard

0.0378787878787879

TAU2

0.242690058479532

Output Speed (tokens/s)

42.474 tok/s

TTFT (s)

0.531s

First Answer Token (s)

0.531s

Mistral

Mistral Medium 3

$0.40/M$2.00/M

131,072 token context window. Includes independent benchmarks from Artificial Analysis.

There are no reviews for this model yet.

artificial-analysismanufactureraa-bootstrap

0.0