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.

Proprietary

OpenRating Index

5.0

0–100 composite

Reasoning Index

6.8

0–100 composite

Cost / Task

$1.04

benchmark run

Output speed

145 tok/s

blended tok/s

Time to first token

27.1s

median latency

Input price

$1.5

per 1M tokens

Output price

$7.5

per 1M tokens

Context window

256K

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

5.0

Reasoning Index

6.8

Token Pricing

Input per 1M tokens

$1.5

Output per 1M tokens

$7.5

Cost of 1M input + 1M output

$9

Task Cost Economics

Empirical cost breakdown for a standard OpenRating Index benchmark task ($1.04 total).

Reasoning (Chain of Thought)
$0.50
Answer generation
$0.17
Cache write overhead
$0.19
Cache hit queries
$0.096
Input payload
$0.092