Back
FR

Model creator

Mistral

Every Mistral model in the BenchSift catalogue, with its scores, ranks, prices and capabilities as the sources publish them.

Hugging Face · mistralai
View in the catalogue
Models
67
69 configurations, reasoning levels included
Open weights
46
46 of 67 models
Latest release
Oct 29, 2026
Mistral Large 4 (High) · First dated model: Sep 27, 2023
Median price
$0.262
$0.0293 to $6 per million tokens, across 36 priced models

Best scores and ranks

The creator's best model on each measure, and its rank among every measured model in the catalogue.

Intelligence

Mistral Large 4 (High)
26.1Rank 171 of 782 measured models

Coding

Mistral Medium 3.5
46.9Rank 132 of 301 measured models

Math

Magistral Medium 1.2
82.0Rank 60 of 270 measured models

Agentic

Mistral Medium 3.5
7.0Rank 128 of 191 measured models

Output speed

Mistral Small (Feb '24)
157 t/sRank 57 of 449 measured models

Lowest price

Mistral Nemo
$0.0293Rank 35 of 740 measured models

OpenRouter ranking

Mistral Nemo
#47

Capabilities

Number of models that declare each capability. Tool calling and structured outputs come from OpenRouter.
Reasoning9 of 67
Open weights46 of 67
Tool calling20 of 67
Structured outputs21 of 67

Input

  • Text64
  • Image28
  • Files12
  • Audio5

Output

  • Text58
  • Speech8
  • Transcription4
  • Embeddings2

Overview

Model types

  • Text58
  • Audio7
  • Embeddings2

Releases by year

  • 202611
  • 202535
  • 202414
  • 20235

Hugging Face

Official repositories confirmed by Hugging Face metadata.

4 official repositories

Licenses

  • apache-2.03
  • other1

Models

67

Reasoning levels are folded into one entry. The rank is the whole catalogue's: sorting does not change it.

Where these figures come from

Each catalogue model is tied to its creator by the identity Artificial Analysis publishes, or OpenRouter's and Models.dev's for models it does not track. Counts fold the reasoning levels of one model together. Ranks compare each measure with every measured model in the catalogue, configurations included, as model pages do. The price is the published blended price (3 input tokens to 1 output token).

Figures computed by BenchSift from the catalogue: Artificial Analysis, OpenRouter, Models.dev and Hugging Face. A value no model carries is not shown.

Data retrieved on Nov 12, 2026.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy