Model Comparison

Comprehensive side-by-side analysis of model capabilities and performance

Meta

Llama 3.2 3B Instruct

Meta

Llama 3.2 3B Instruct is a language model developed by Meta. The model shows competitive results across 15 benchmarks. It excels particularly in NIH/Multi-needle (84.7%), ARC-C (78.6%), GSM8k (77.7%). It supports a 256K token context window for handling large documents. The model is available through 1 API provider. Released in 2024, it represents Meta's latest advancement in AI technology.

Meta

Llama 4 Maverick

Meta

Llama 4 Maverick is a multimodal language model developed by Meta. It achieves strong performance with an average score of 71.8% across 13 benchmarks. It excels particularly in DocVQA (94.4%), MGSM (92.3%), ChartQA (90.0%). The model shows particular specialization in vision tasks with an average performance of 75.8%. With a 2.0M token context window, it can handle extensive documents and complex multi-turn conversations. The model is available through 7 API providers. As a multimodal model, it can process and understand text, images, and other input formats seamlessly. Released in 2025, it represents Meta's latest advancement in AI technology.

Meta

Llama 3.2 3B Instruct

Meta

2024-09-25

Meta

Llama 4 Maverick

Meta

2025-04-05

6 months newer

Pricing Comparison

Cost per million tokens (USD)

Meta

Llama 3.2 3B Instruct

$0.74 cheaper
Input:$0.01
Output:$0.02
Meta

Llama 4 Maverick

Input:$0.17
Output:$0.60

Performance Metrics

Context window and performance specifications

Meta

Llama 3.2 3B Instruct

Max Context:256.0K
Parameters:3.2B
Meta

Llama 4 Maverick

Larger context
Max Context:2.0M
Parameters:400.0B

Average performance across 4 common benchmarks

Meta

Llama 3.2 3B Instruct

Average Score:50.6%
Meta

Llama 4 Maverick

+26.6%
Average Score:77.2%

Performance comparison across key benchmark categories

Meta

Llama 3.2 3B Instruct

code
+16.9%
77.4%
math
61.3%
general
42.5%
Meta

Llama 4 Maverick

code
60.5%
math
+14.4%
75.7%
general
+29.0%
71.5%
Benchmark Scores - Detailed View
Side-by-side comparison of all benchmark scores

Provider Availability & Performance

Available providers and their performance metrics

Meta

Llama 3.2 3B Instruct

1 providers

DeepInfra

Throughput: 171.5 tok/s
Latency: 0.24ms
Meta

Llama 4 Maverick

7 providers

Sambanova

Throughput: 638.7 tok/s
Latency: 2.04ms

Together

Throughput: 97.93 tok/s
Latency: 0.2ms

DeepInfra

Throughput: 83.59 tok/s
Latency: 0.38ms

Fireworks

Throughput: 63.03 tok/s
Latency: 0.62ms

Groq

Throughput: 307.3 tok/s
Latency: 0.27ms

Novita

Throughput: 69.42 tok/s
Latency: 0.62ms

Lambda

Throughput: 93.69 tok/s
Latency: 0.65ms
Meta

Llama 3.2 3B Instruct

Avg Score:50.6%
Providers:1
Meta

Llama 4 Maverick

+26.6%
Avg Score:77.2%
Providers:7