Llama 3.2 Instruct 90B (Vision)
MetaLlamaOpen WeightLlama 3.2 · Commercial OK
Description
Llama 3.2 90B is a large multimodal language model optimized for visual recognition, image reasoning, and captioning tasks. It supports a context length of 128,000 tokens and is designed for deployment on edge and mobile devices, offering state-of-the-art performance in image understanding and generative tasks.
Release Date
2024-09-25
Parameters
90.0B
Context Length
—
Modalities
image, text
Capability Radar
70
general
0
coding
70
reasoning
43
scienceest.
49
agents
85
multimodal
Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Multimodal Ranking | 95 | 46.0 | LS |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))General
MMLU
86.0%SR
Math
MGSM
86.9%SR
MATH
68.0%SR
MathVista
57.3%SR
Multimodal
MMMU
60.3%SR
Reasoning
ChartQAMasry et al. (2022)
85.5%SR
GPQANYU + Cohere + Anthropic (2023)
46.7%SR
Vision
AI2D
92.3%SR
DocVQADocVQA (2020)
90.1%SR
VQAv2
78.1%SR
TextVQA
73.5%SR
InfographicsQA
56.8%SR
MMMU-Pro
45.2%SR
AA Evaluation Indices
(Artificial Analysis)No AA evaluation data available
LLM Stats Category Scores
(LLM Stats (zeroeval))Language90
Legal90
Finance90
Image To Text80
Math70
Multimodal70
Reasoning70
General70
Healthcare70
Vision70
Physics50
Biology50
Chemistry50
Pricing
No pricing data available
Speed
No speed data available
Provider Price Ranking
No provider data available