OpenRating is an independent, open-source AI rating platform. Join the community

OOpenRating
All models

Mistral AI · Released Feb 12, 2026

Mistral Medium 3.5

Mistral's refined medium-tier open weights model optimized for European data compliance, code generation, and multi-lingual agility.

Open weights

OpenRating Index

51.2

0–100 composite

Reasoning Index

69.8

0–100 composite

Cost / Task

$0.46

benchmark run

Output speed

146 tok/s

blended tok/s

Time to first token

0.5s

median latency

Input price

$0.25

per 1M tokens

Output price

$0.75

per 1M tokens

Context window

128K

tokens

Strengths

  • European data residency & sovereignty deployment options

  • Clean instruction following and structured JSON generation

  • Fast 145 tok/s output throughput

How we rate Mistral Medium 3.5

OpenRating scores every model on the same axes. The OpenRating Index is a weighted composite of reasoning, knowledge, and agentic benchmarks, normalised to a 0–100 scale. Speed is blended output measured in tokens per second under standardised load, with time-to-first-token reported separately. Prices are list input and output prices per million tokens, and Task Cost measures end-to-end workload spending.

OpenRating Index

51.2

Reasoning Index

69.8

Token Pricing

Input per 1M tokens

$0.25

Output per 1M tokens

$0.75

Cost of 1M input + 1M output

$1

Task Cost Economics

Empirical cost breakdown for a standard OpenRating Index benchmark task ($0.46 total).

Reasoning (Chain of Thought)
$0.14
Answer generation
$0.057
Cache write overhead
$0.16
Cache hit queries
$0.098
Input payload
$0.009