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
—
Modalities
image, text
Capability Radar
60
general
70
coding
60
reasoning
51
scienceest.
0
agents
80
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Multimodal Ranking | 44 | 76.0 | LS |
Benchmark Scores (LLM Stats)
Code
HumanEval
72.0%SR
Communication
MT-Bench
0.77 / 100SR
MM-MT-Bench
0.60 / 100SR
Finance
MMLU
69.2%SR
General
IFEval
61.3%SR
MMMU
52.5%SR
Image To Text
DocVQA
90.7%SR
VQAv2
78.6%SR
Math
MathVista
58.0%SR
MATH
48.1%SR
Multimodal
ChartQA
81.8%SR
MM IF-Eval
52.7%SR
AA Evaluation Indices
No AA evaluation data available
LLM Stats Category Scores
Creativity80
Image To Text80
Roleplay80
Vision70
Code70
Communication70
Finance70
Language70
Legal70
Multimodal70
Reasoning70
Structured Output60
General60
Healthcare60
Instruction Following60
Math60
Pricing
No pricing data available
Speed
No speed data available
Available Providers
(LS internal units)No provider data available