Llama 3.2 90B Instruct
Multimodal
Zero-eval
#1InfographicsQA
#3VQAv2
by Meta
About
Llama 3.2 90B Instruct is a multimodal language model developed by Meta. It achieves strong performance with an average score of 71.3% across 13 benchmarks. It excels particularly in AI2D (92.3%), DocVQA (90.1%), MGSM (86.9%). It supports a 256K token context window for handling large documents. The model is available through 5 API providers. As a multimodal model, it can process and understand text, images, and other input formats seamlessly. It's licensed for commercial use, making it suitable for enterprise applications. Released in 2024, it represents Meta's latest advancement in AI technology.
Pricing Range
Input (per 1M)$0.35 -$2.00
Output (per 1M)$0.40 -$2.00
Providers5
Timeline
AnnouncedSep 25, 2024
ReleasedSep 25, 2024
Specifications
Capabilities
Multimodal
License & Family
License
Llama 3.2
Benchmark Performance Overview
Performance metrics and category breakdown
Overall Performance
13 benchmarks
Average Score
71.3%
Best Score
92.3%
High Performers (80%+)
5Performance Metrics
Max Context Window
256.0KAvg Throughput
54.6 tok/sAvg Latency
1msTop Categories
general
73.5%
math
70.7%
vision
69.4%
Benchmark Performance
Top benchmark scores with normalized values (0-100%)
Ranking Across Benchmarks
Position relative to other models on each benchmark
AI2D
Rank #5 of 17
#2Mistral Small 3.2 24B Instruct
92.9%
#3Pixtral Large
93.8%
#4GPT-4o
94.2%
#5Llama 3.2 90B Instruct
92.3%
#6Llama 3.2 11B Instruct
91.1%
#7Qwen2.5 VL 72B Instruct
88.4%
#8Grok-1.5V
88.3%
DocVQA
Rank #19 of 26
#16Pixtral-12B
90.7%
#17DeepSeek VL2 Small
92.3%
#18Nova Lite
92.4%
#19Llama 3.2 90B Instruct
90.1%
#20DeepSeek VL2 Tiny
88.9%
#21Llama 3.2 11B Instruct
88.4%
#22Gemma 3 12B
87.1%
MGSM
Rank #14 of 31
#11GPT-4o mini
87.0%
#12Gemini 1.5 Pro
87.5%
#13GPT-4 Turbo
88.5%
#14Llama 3.2 90B Instruct
86.9%
#15Claude 3.5 Haiku
85.6%
#16Qwen3 235B A22B
83.5%
#17Claude 3 Sonnet
83.5%
MMLU
Rank #23 of 78
#20Grok-2 mini
86.2%
#21GPT-4
86.4%
#22GPT-4 Turbo
86.5%
#23Llama 3.2 90B Instruct
86.0%
#24Llama 3.3 70B Instruct
86.0%
#25Gemini 1.5 Pro
85.9%
#26Nova Pro
85.9%
ChartQA
Rank #13 of 24
#10GPT-4o
85.7%
#11DeepSeek VL2
86.0%
#12Nova Lite
86.8%
#13Llama 3.2 90B Instruct
85.5%
#14Qwen2.5-Omni-7B
85.3%
#15DeepSeek VL2 Small
84.5%
#16Llama 3.2 11B Instruct
83.4%
All Benchmark Results for Llama 3.2 90B Instruct
Complete list of benchmark scores with detailed information
AI2D AI2D benchmark | general | text | 0.92 | 92.3% | Self-reported |
DocVQA DocVQA benchmark | vision | multimodal | 0.90 | 90.1% | Self-reported |
MGSM MGSM benchmark | math | text | 0.87 | 86.9% | Self-reported |
MMLU MMLU benchmark | general | text | 0.86 | 86.0% | Self-reported |
ChartQA ChartQA benchmark | general | multimodal | 0.85 | 85.5% | Self-reported |
VQAv2 VQAv2 benchmark | vision | multimodal | 0.78 | 78.1% | Self-reported |
TextVQA TextVQA benchmark | vision | multimodal | 0.73 | 73.5% | Self-reported |
MATH MATH benchmark | math | text | 0.68 | 68.0% | Self-reported |
MMMU MMMU benchmark | vision | multimodal | 0.60 | 60.3% | Self-reported |
MathVista MathVista benchmark | math | text | 0.57 | 57.3% | Self-reported |
Showing 1 to 10 of 13 benchmarks