Pass IndexThe State of AISign in

Mistral Small 3.1 (25.03)

A new leader in the small models category with image understanding capabilities, released March 2025; it is retired, with Mistral Small 4 recommended for new integrations.

text + image → text · made by Mistral AI

$0.1$0.3per Mtok in / out
Google Vertex AI

Sold by 2 ways

SellerLaneRate
Google Vertex AI 0 ways$0.1per Mtok in$0.3per Mtok out
Google Vertex AI cloudnot on the seller's list todaystandard$0.1per Mtok in$0.3per Mtok outcloud.google.com · read 2026-08-24
Microsoft Azure AI 0 ways$0.1per Mtok in$0.3per Mtok out
Microsoft Azure AI cloudnot on the seller's list todaystandard$0.1per Mtok in$0.3per Mtok outmodels.dev · read 2026-08-27

Measured 4 standings

PlaceBoardMetricScore
186thof 222Chess puzzles — Epoch AImean_score1
261stof 313GPQA Diamondmean_score41.919
264thof 290OTIS Mock AIME 2024-2025mean_score3.889
541stof 656Epoch capabilities index — Epoch AIECI Score127.48

About

Mistral Small 3.1 (25.03) — a text model from Mistral AI, placed 541st of 656 on Epoch capabilities index — Epoch AI.

It takes text and images and returns text, with a context window of 131,072 tokens. The catalogue files it under reasoning. It has been measured on 4 boards, and stands best at 541st of 656 on Epoch capabilities index — Epoch AI.

Every current figure

Maker
Mistral AI
Register
model
Takes
text + image
Returns
text
Context
131,072 tokens
Boards
4
Best place
541st of 656 — Epoch capabilities index — Epoch AI