Skip to main content

Pixtral-12B

Mistral AIOpen WeightApache 2.0 · Commercial OK

Description

A 12B parameter multimodal model with a 400M parameter vision encoder, capable of understanding both natural images and documents. Excels at multimodal tasks while maintaining strong text-only performance. Supports variable image sizes and multiple images in context.

Release Date
2024-09-17
Parameters
12.4B
Context Length
128K
Modalities
image, text

Capability Radar

70
general
70
coding
60
reasoning
51
scienceest.
63
agents
80
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Code

HumanEvalOpenAI (2021)72.0%SR

Communication

MT-Bench0.77 / 100SR
MM-MT-Bench0.60 / 100SR

Finance

MMLU69.2%SR

General

IFEvalGoogle Research (2023)61.3%SR
MMMU52.5%SR

Image To Text

DocVQADocVQA (2020)90.7%SR
VQAv278.6%SR

Math

MathVista58.0%SR
MATH48.1%SR

Multimodal

ChartQAMasry et al. (2022)81.8%SR
MM IF-Eval52.7%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Image To Text
80
Roleplay
80
Creativity
80
Language
70
Legal
70
Multimodal
70
Reasoning
70
Finance
70
General
70
Code
70
Communication
70
Vision
70
Instruction Following
60
Math
60
Structured Output
60
Healthcare
60

Pricing

Input Price$0.15 / 1M tokens
Output Price$0.15 / 1M tokens
Blended Price (3:1)$0.15 / 1M tokens

Speed

No speed data available

Provider Price Ranking

Provider Price Ranking

5 providers

Cheapest: Mistral AIMost Expensive: GreenPT
ProviderInputOutput
1Mistral AIPRIMARY
$0.15
$0.15
2Mistral
$0.15
$0.15
3Scaleway
$0.2
$0.2
4Cortecs
$0.223
$0.223
5GreenPT
$0.285
$0.285

Compare pricing across different API providers for this model.

External Sources