Model Comparison

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

Llama 3.1 8B Instruct

Meta

Llama 3.1 8B Instruct is a language model developed by Meta. It achieves strong performance with an average score of 61.3% across 18 benchmarks. It excels particularly in GSM-8K (CoT) (84.5%), ARC-C (83.4%), API-Bank (82.6%). It supports a 262K token context window for handling large documents. The model is available through 9 API providers. Released in 2024, it represents Meta's latest advancement in AI technology.

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.

Llama 3.1 8B Instruct

Meta

2024-07-23

Llama 3.2 3B Instruct

Meta

2024-09-25

2 months newer

Pricing Comparison

Cost per million tokens (USD)

Llama 3.1 8B Instruct

Input:$0.03

Output:$0.03

Llama 3.2 3B Instruct

$0.03 cheaper

Input:$0.01

Output:$0.02

Performance Metrics

Context window and performance specifications

Llama 3.1 8B Instruct

Larger context

Max Context:262.1K

Parameters:8.0B

Llama 3.2 3B Instruct

Max Context:256.0K

Parameters:3.2B

Average performance across 5 common benchmarks

Llama 3.1 8B Instruct

+3.1%

Average Score:60.4%

Llama 3.2 3B Instruct

Average Score:57.3%

Performance comparison across key benchmark categories

Llama 3.1 8B Instruct

reasoning

+9.2%

83.4%

code

65.8%

math

+7.1%

68.4%

general

+11.5%

54.0%

Llama 3.2 3B Instruct

reasoning

74.2%

code

+11.6%

77.4%

math

61.3%

general

42.5%

Benchmark Scores - Detailed View

Side-by-side comparison of all benchmark scores

Knowledge Cutoff

Training data recency comparison

Llama 3.1 8B Instruct

2023-12-31

More recent knowledge cutoff means awareness of newer technologies and frameworks

Provider Availability & Performance

Available providers and their performance metrics

Llama 3.1 8B Instruct

9 providers

Sambanova

Throughput: 1050 tok/s

Latency: 0.5ms

Together

Throughput: 194 tok/s

Latency: 0.5ms

Hyperbolic

Throughput: 200 tok/s

Latency: 0.5ms

DeepInfra

Throughput: 118 tok/s

Latency: 0.5ms

Fireworks

Throughput: 292 tok/s

Latency: 0.5ms

Groq

Throughput: 750 tok/s

Latency: 0.5ms

Bedrock

Throughput: 100 tok/s

Latency: 0.5ms

Lambda

Throughput: 42 tok/s

Latency: 0.5ms

Cerebras

Throughput: 2047 tok/s

Latency: 0.2ms

Llama 3.2 3B Instruct

1 providers

DeepInfra

Throughput: 171.5 tok/s

Latency: 0.24ms

Llama 3.1 8B Instruct

+3.1%

Avg Score:60.4%

Providers:9

Llama 3.2 3B Instruct

Avg Score:57.3%

Providers:1