Nova Lite vs Nova Pro Comparison

Comparing Nova Lite and Nova Pro across benchmarks, pricing, and capabilities.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

27 benchmarks

Nova Lite outperforms in 0 benchmarks, while Nova Pro is better at 26 benchmarks (ARC-C, BBH, BFCL, ChartQA, CRAG, DocVQA, DROP, EgoSchema, FinQA, GPQA, GroundUI-1K, GSM8k, HumanEval, IFEval, LVBench, MATH, MMLU, MM-Mind2Web, MMMU, SQuALITY, TextVQA, Translation en→Set1 COMET22, Translation en→Set1 spBleu, Translation Set1→en COMET22, Translation Set1→en spBleu, VisualWebBench).

Nova Pro significantly outperforms across most benchmarks.

Sat Mar 14 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Nova Lite costs less

For input processing, Nova Lite ($0.06/1M tokens) is 13.3x cheaper than Nova Pro ($0.80/1M tokens).

For output processing, Nova Lite ($0.24/1M tokens) is 13.3x cheaper than Nova Pro ($3.20/1M tokens).

In conclusion, Nova Pro is more expensive than Nova Lite.*

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

Lowest available price from all providers

Sat Mar 14 2026 • llm-stats.com

Nova Lite

Input tokens$0.06

Output tokens$0.24

Best providerAWS Bedrock

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

Both models have the same input context window of 300,000 tokens. Nova Pro can generate longer responses up to 300,000 tokens, while Nova Lite is limited to 2,048 tokens.

Nova Lite

Input300,000 tokens

Output2,048 tokens

Nova Pro

Input300,000 tokens

Output300,000 tokens

Sat Mar 14 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both Nova Lite and Nova Pro support multimodal inputs.

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

Nova Lite

Text

Images

Audio

Video

Nova Pro

Text

Images

Audio

Video

License

Usage and distribution terms

Both models are licensed under proprietary licenses.

Both models have usage restrictions defined by their respective organizations.

Nova Lite

Proprietary

Closed source

Nova Pro

Proprietary

Closed source

Release Timeline

When each model was launched

Both models were released on 2024-11-20.

They likely represent similar generations of model development.

Nova Lite

Nov 20, 2024

1.3 years ago

Nova Pro

Nov 20, 2024

1.3 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

Nova Lite is available from Bedrock. Nova Pro is available from Bedrock. The availability of providers can affect quality of the model and reliability.

Nova Lite

AWS Bedrock

Input Price:Input: $0.06/1MOutput Price:Output: $0.24/1M

Nova Pro

AWS Bedrock

Input Price:Input: $0.80/1MOutput Price:Output: $3.20/1M

* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Nova Lite

View details

Amazon

Less expensive input tokens

Less expensive output tokens

Nova Pro

View details

Amazon

Higher ARC-C score (94.8% vs 92.4%)

Higher BBH score (86.9% vs 82.4%)

Higher BFCL score (68.4% vs 66.6%)

Higher ChartQA score (89.2% vs 86.8%)

Higher CRAG score (50.3% vs 43.8%)

Higher DocVQA score (93.5% vs 92.4%)

Higher DROP score (85.4% vs 80.2%)

Higher EgoSchema score (72.1% vs 71.4%)

Higher FinQA score (77.2% vs 73.6%)

Higher GPQA score (46.9% vs 42.0%)

Higher GroundUI-1K score (81.4% vs 80.2%)

Higher GSM8k score (94.8% vs 94.5%)

Higher HumanEval score (89.0% vs 85.4%)

Higher IFEval score (92.1% vs 89.7%)

Higher LVBench score (41.6% vs 40.4%)

Higher MATH score (76.6% vs 73.3%)

Higher MMLU score (85.9% vs 80.5%)

Higher MM-Mind2Web score (63.7% vs 60.7%)

Higher MMMU score (61.7% vs 56.2%)

Higher SQuALITY score (19.8% vs 19.2%)

Higher TextVQA score (81.5% vs 80.2%)

Higher Translation en→Set1 COMET22 score (89.1% vs 88.8%)

Higher Translation en→Set1 spBleu score (43.4% vs 41.5%)

Higher Translation Set1→en COMET22 score (89.0% vs 88.8%)

Higher Translation Set1→en spBleu score (44.4% vs 43.1%)

Higher VisualWebBench score (79.7% vs 77.7%)

Detailed Comparison

AI Model Comparison Table
Feature	Nova Lite	Nova Pro