Gemma 2 27B vs Nova Pro

Comparing Gemma 2 27B by Google and Nova Pro by Amazon across benchmarks, pricing, and capabilities.

Nova Pro significantly outperforms across most benchmarks.

Performance Benchmarks

Comparative analysis across standard metrics

5 benchmarks

Gemma 2 27B outperforms in 0 benchmarks, while Nova Pro is better at 5 benchmarks (ARC-C, GSM8k, HumanEval, MATH, MMLU).

Nova Pro significantly outperforms across most benchmarks.

Wed Mar 25 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Cost data unavailable.

Lowest available price from all providers
Wed Mar 25 2026 • llm-stats.com
Google
Gemma 2 27B
Input tokens$0.00
Output tokens$0.00
Best providerUnknown Organization
Amazon
Nova Pro
Input tokens$0.80
Output tokens$3.20
Best providerAWS Bedrock
Notice missing or incorrect data?Start an Issue

Context Window

Maximum input and output token capacity

Only Nova Pro specifies input context (300,000 tokens). Only Nova Pro specifies output context (300,000 tokens).

Google
Gemma 2 27B
Input- tokens
Output- tokens
Amazon
Nova Pro
Input300,000 tokens
Output300,000 tokens
Wed Mar 25 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Nova Pro supports multimodal inputs, whereas Gemma 2 27B does not.

Nova Pro can handle both text and other forms of data like images, making it suitable for multimodal applications.

Gemma 2 27B

Text
Images
Audio
Video

Nova Pro

Text
Images
Audio
Video

License

Usage and distribution terms

Gemma 2 27B is licensed under Gemma, while Nova Pro uses a proprietary license.

License differences may affect how you can use these models in commercial or open-source projects.

Gemma 2 27B

Gemma

Open weights

Nova Pro

Proprietary

Closed source

Release Timeline

When each model was launched

Gemma 2 27B was released on 2024-06-27, while Nova Pro was released on 2024-11-20.

Nova Pro is 5 months newer than Gemma 2 27B.

Gemma 2 27B

Jun 27, 2024

1.7 years ago

Nova Pro

Nov 20, 2024

1.3 years ago

4mo newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Key Takeaways

Has open weights
Larger context window (300,000 tokens)
Supports multimodal inputs
Higher ARC-C score (94.8% vs 71.4%)
Higher GSM8k score (94.8% vs 74.0%)
Higher HumanEval score (89.0% vs 51.8%)
Higher MATH score (76.6% vs 42.3%)
Higher MMLU score (85.9% vs 75.2%)

Detailed Comparison

AI Model Comparison Table
Feature
Google
Gemma 2 27B
Amazon
Nova Pro