in the loop

Mistral Medium 3
#146 of 274 scored.

MistralMay 7, 2025Closed

Capabilities Index

Range 130.1–135.5

134.1

Context

Takes text, image, file

131K

Input

Per 1M tokens

$0.40

Output

Per 1M tokens

$2.00

Benchmarks

How it scores.

  • GPQA Diamond46.0%

    118th of 186

  • Humanity's Last Exam0.0%

    36th of 40

  • Mock AIME32.1%

    119th of 176

Everything else Epoch has for it

  • MATH level 581.6%
  • Lech Mazur Writing77.3%
  • DTBench37.1%
  • FrontierMath-2025-02-28-Private0.6%

On the index

Around it.

  1. #143o1-previewOpenAI134.8
  2. #144Gemini 2.0 Flash (Feb 2025)Google134.7
  3. #145Gemini 2.0 Flash (Dec 2024)Google134.7
  4. #146Mistral Medium 3Mistral · $0.40 in134.1
  5. #147Gemini 2.5 Flash-Lite (Jun 2025)Google133.9
  6. #148Claude 3.5 Sonnet (October 2024)Anthropic133.6
  7. #149Magistral Small 1.0Mistral133.2

Sources