Model Comparison

Gemma 3 27B vs Nova Lite

Gemma 3 27B shows notably better performance in the majority of benchmarks. Nova Lite is 1.2x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

8 benchmarks

Gemma 3 27B outperforms in 5 benchmarks (GPQA, GSM8k, HumanEval, IFEval, MATH), while Nova Lite is better at 3 benchmarks (ChartQA, DocVQA, TextVQA).

Gemma 3 27B shows notably better performance in the majority of benchmarks.

Wed Apr 22 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Nova Lite costs less

For input processing, Gemma 3 27B ($0.10/1M tokens) is 1.7x more expensive than Nova Lite ($0.06/1M tokens).

For output processing, Gemma 3 27B ($0.20/1M tokens) is 1.2x cheaper than Nova Lite ($0.24/1M tokens).

In conclusion, Gemma 3 27B is more expensive than Nova Lite.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Wed Apr 22 2026 • llm-stats.com
Google
Gemma 3 27B
Input tokens$0.10
Output tokens$0.20
Best providerDeepinfra
Amazon
Nova Lite
Input tokens$0.06
Output tokens$0.24
Best providerAWS Bedrock
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Nova Lite accepts 300,000 input tokens compared to Gemma 3 27B's 131,072 tokens. Gemma 3 27B can generate longer responses up to 131,072 tokens, while Nova Lite is limited to 2,048 tokens.

Google
Gemma 3 27B
Input131,072 tokens
Output131,072 tokens
Amazon
Nova Lite
Input300,000 tokens
Output2,048 tokens
Wed Apr 22 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both Gemma 3 27B and Nova Lite support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Gemma 3 27B

Text
Images
Audio
Video

Nova Lite

Text
Images
Audio
Video

License

Usage and distribution terms

Gemma 3 27B is licensed under Gemma, while Nova Lite uses a proprietary license.

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

Gemma 3 27B

Gemma

Open weights

Nova Lite

Proprietary

Closed source

Release Timeline

When each model was launched

Gemma 3 27B was released on 2025-03-12, while Nova Lite was released on 2024-11-20.

Gemma 3 27B is 4 months newer than Nova Lite.

Gemma 3 27B

Mar 12, 2025

1.1 years ago

3mo newer
Nova Lite

Nov 20, 2024

1.4 years ago

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

Provider Availability

Gemma 3 27B is available from DeepInfra, Novita. Nova Lite is available from Bedrock.

Gemma 3 27B

deepinfra logo
Deepinfra
Input Price:Input: $0.10/1MOutput Price:Output: $0.20/1M
novita logo
Novita
Input Price:Input: $0.11/1MOutput Price:Output: $0.20/1M

Nova Lite

bedrock logo
AWS Bedrock
Input Price:Input: $0.06/1MOutput Price:Output: $0.24/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Google
Less expensive output tokens
Has open weights
Higher GPQA score (42.4% vs 42.0%)
Higher GSM8k score (95.9% vs 94.5%)
Higher HumanEval score (87.8% vs 85.4%)
Higher IFEval score (90.4% vs 89.7%)
Higher MATH score (89.0% vs 73.3%)
Amazon
Larger context window (300,000 tokens)
Less expensive input tokens
Higher ChartQA score (86.8% vs 78.0%)
Higher DocVQA score (92.4% vs 86.6%)
Higher TextVQA score (80.2% vs 65.1%)

Detailed Comparison

AI Model Comparison Table
Feature
Google
Gemma 3 27B
Amazon
Nova Lite

FAQ

Common questions about Gemma 3 27B vs Nova Lite

Gemma 3 27B shows notably better performance in the majority of benchmarks. Gemma 3 27B is made by Google and Nova Lite is made by Amazon. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
Gemma 3 27B scores GSM8k: 95.9%, IFEval: 90.4%, MATH: 89.0%, HumanEval: 87.8%, BIG-Bench Hard: 87.6%. Nova Lite scores GSM8k: 94.5%, ARC-C: 92.4%, DocVQA: 92.4%, IFEval: 89.7%, Translation en→Set1 COMET22: 88.8%.
Nova Lite is 1.7x cheaper for input tokens. Gemma 3 27B costs $0.10/M input and $0.20/M output via deepinfra. Nova Lite costs $0.06/M input and $0.24/M output via bedrock.
Gemma 3 27B supports 131K tokens and Nova Lite supports 300K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include context window (131K vs 300K), input pricing ($0.10 vs $0.06/M), licensing (Gemma vs Proprietary). See the full comparison above for benchmark-by-benchmark results.
Gemma 3 27B is developed by Google and Nova Lite is developed by Amazon.