Model Comparison

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

Jamba 1.5 Mini

AI21 Labs

Jamba 1.5 Mini is a language model developed by AI21 Labs. The model shows competitive results across 8 benchmarks. It excels particularly in ARC-C (85.7%), GSM8k (75.8%), MMLU (69.7%). It supports a 512K token context window for handling large documents. The model is available through 2 API providers. Released in 2024, it represents AI21 Labs'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.

Jamba 1.5 Mini

AI21 Labs

2024-08-22

Llama 3.2 3B Instruct

Pricing Comparison

Cost per million tokens (USD)

Jamba 1.5 Mini

Input:$0.20

Output:$0.40

Llama 3.2 3B Instruct

$0.57 cheaper

Input:$0.01

Output:$0.02

Performance Metrics

Context window and performance specifications

Jamba 1.5 Mini

Larger context

Max Context:512.3K

Parameters:52.0B

Llama 3.2 3B Instruct

Max Context:256.0K

Parameters:3.2B

Average performance across 4 common benchmarks

Jamba 1.5 Mini

+2.8%

Average Score:65.9%

Llama 3.2 3B Instruct

Average Score:63.1%

Performance comparison across key benchmark categories

Jamba 1.5 Mini

reasoning

+11.5%

85.7%

math

+14.5%

75.8%

general

+4.1%

46.6%

Llama 3.2 3B Instruct

reasoning

74.2%

math

61.3%

general

42.5%

Benchmark Scores - Detailed View

Side-by-side comparison of all benchmark scores

Knowledge Cutoff

Training data recency comparison

Jamba 1.5 Mini

2024-03-05

More recent knowledge cutoff means awareness of newer technologies and frameworks

Provider Availability & Performance

Available providers and their performance metrics

Jamba 1.5 Mini

2 providers

Google

Throughput: 100 tok/s

Latency: 0.3ms

Bedrock

Throughput: 100 tok/s

Latency: 0.5ms

Llama 3.2 3B Instruct

1 providers

DeepInfra

Throughput: 171.5 tok/s

Latency: 0.24ms

Jamba 1.5 Mini

+2.8%

Avg Score:65.9%

Providers:2

Llama 3.2 3B Instruct

Avg Score:63.1%

Providers:1