Model Comparison

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

Google

Gemma 3 4B

Google

Gemma 3 4B is a multimodal language model developed by Google. The model shows competitive results across 26 benchmarks. It excels particularly in IFEval (90.2%), GSM8k (89.2%), DocVQA (75.8%). It supports a 262K token context window for handling large documents. The model is available through 1 API provider. 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 2025, it represents Google's latest advancement in AI technology.

Amazon

Nova Pro

Amazon

Nova Pro is a multimodal language model developed by Amazon. It achieves strong performance with an average score of 73.2% across 27 benchmarks. It excels particularly in ARC-C (94.8%), GSM8k (94.8%), DocVQA (93.5%). It supports a 600K token context window for handling large documents. The model is available through 1 API provider. As a multimodal model, it can process and understand text, images, and other input formats seamlessly. Released in 2024, it represents Amazon's latest advancement in AI technology.

Amazon

Nova Pro

Amazon

2024-11-20

Google

Gemma 3 4B

Google

2025-03-12

3 months newer

Pricing Comparison

Cost per million tokens (USD)

Google

Gemma 3 4B

$3.94 cheaper
Input:$0.02
Output:$0.04
Amazon

Nova Pro

Input:$0.80
Output:$3.20

Performance Metrics

Context window and performance specifications

Google

Gemma 3 4B

Max Context:262.1K
Parameters:4.0B
Amazon

Nova Pro

Larger context
Max Context:600.0K

Average performance across 8 common benchmarks

Google

Gemma 3 4B

Average Score:69.9%
Amazon

Nova Pro

+13.0%
Average Score:82.9%

Performance comparison across key benchmark categories

Google

Gemma 3 4B

code
61.5%
math
64.5%
vision
59.0%
general
40.7%
Amazon

Nova Pro

code
+29.0%
90.5%
math
+21.3%
85.7%
vision
+20.1%
79.1%
general
+26.7%
67.4%
Benchmark Scores - Detailed View
Side-by-side comparison of all benchmark scores
Knowledge Cutoff
Training data recency comparison

Gemma 3 4B

2024-08-01

More recent knowledge cutoff means awareness of newer technologies and frameworks

Provider Availability & Performance

Available providers and their performance metrics

Google

Gemma 3 4B

1 providers

DeepInfra

Throughput: 33 tok/s
Latency: 0.2ms
Amazon

Nova Pro

1 providers

Bedrock

Throughput: 100 tok/s
Latency: 0.5ms
Google

Gemma 3 4B

Avg Score:69.9%
Providers:1
Amazon

Nova Pro

+13.0%
Avg Score:82.9%
Providers:1