Back to Models
Meta Llama 3.2 90B Vision Instruct
Standard
Instruction-tuned image reasoning generative model (text + images in / text out) optimized for visual recognition, image reasoning, captioning and answering general questions about the image.
Features
VisionPDF ComprehensionImage generation
Model details
- Provider
- Meta
- Context
- Unknown
- Multimodal
- No
Benchmark performance
via Artificial AnalysisIntelligence
Coding
Math
Knowledge
46%
Creative Writing
12%
Speed
8%
Value
28%