Llama 3.2 Instruct 90B (Vision): Intelligence, Performance & Price Analysis
Analysis of Meta's Llama 3.2 Instruct 90B (Vision) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more. Click on any model to compare API providers for that model. For more details including relating to our methodology, see our FAQs.
Comparison Summary
Intelligence:
Llama 3.2 90B (Vision) is of lower quality compared to average, with a MMLU score of 0.671 and a Intelligence Index across evaluations of 33.
Price:Llama 3.2 90B (Vision) is cheaper compared to average with a price of $0.54 per 1M Tokens (blended 3:1).
Llama 3.2 90B (Vision) Input token price: $0.53, Output token price: $0.56 per 1M Tokens.
Speed:Llama 3.2 90B (Vision) Input token price: $0.53, Output token price: $0.56 per 1M Tokens.
Llama 3.2 90B (Vision) is slower compared to average, with a output speed of 34.5 tokens per second.
Latency:Llama 3.2 90B (Vision) has a lower latency compared to average, taking 0.30s to receive the first token (TTFT).
Context Window:Llama 3.2 90B (Vision) has a smaller context windows than average, with a context window of 130k tokens.
Highlights
Intelligence
Artificial Analysis Intelligence Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:
Llama 3.2 Instruct 90B (Vision) Model Details
Comparisons to Llama 3.2 90B (Vision)
Llama 3.2 90B (Vision)
GPT-4.1
o3
o4-mini (high)
o3-pro
Llama 4 Scout
Llama 4 Maverick
Gemini 2.5 Flash (Reasoning)
Gemini 2.5 Pro
Claude 4 Opus Thinking
Claude 4 Sonnet
Claude 4 Sonnet Thinking
Magistral Small
DeepSeek R1 0528 (May '25)
DeepSeek V3 0324 (Mar '25)
Grok 3 mini Reasoning (high)
Nova Premier
MiniMax M1 80k
Llama Nemotron Ultra Reasoning
Qwen3 235B (Reasoning)
GPT-4o (Nov '24)
Further details