Model Comparison

Granite 3.3 8B Instruct vs Nova Pro

Nova Pro significantly outperforms across most benchmarks. Granite 3.3 8B Instruct is 2.8x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

5 benchmarks

Granite 3.3 8B Instruct outperforms in 1 benchmarks (HumanEval), while Nova Pro is better at 4 benchmarks (DROP, GSM8k, IFEval, MMLU).

Nova Pro significantly outperforms across most benchmarks.

Thu Apr 16 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Granite 3.3 8B Instruct costs less

For input processing, Granite 3.3 8B Instruct ($0.50/1M tokens) is 1.6x cheaper than Nova Pro ($0.80/1M tokens).

For output processing, Granite 3.3 8B Instruct ($0.50/1M tokens) is 6.4x cheaper than Nova Pro ($3.20/1M tokens).

In conclusion, Nova Pro is more expensive than Granite 3.3 8B Instruct.*

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

Lowest available price from all providers
Thu Apr 16 2026 • llm-stats.com
IBM
Granite 3.3 8B Instruct
Input tokens$0.50
Output tokens$0.50
Best providerReplicate
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

Nova Pro accepts 300,000 input tokens compared to Granite 3.3 8B Instruct's 128,000 tokens. Nova Pro can generate longer responses up to 300,000 tokens, while Granite 3.3 8B Instruct is limited to 8,192 tokens.

IBM
Granite 3.3 8B Instruct
Input128,000 tokens
Output8,192 tokens
Amazon
Nova Pro
Input300,000 tokens
Output300,000 tokens
Thu Apr 16 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both Granite 3.3 8B Instruct and Nova Pro support multimodal inputs.

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

Granite 3.3 8B Instruct

Text
Images
Audio
Video

Nova Pro

Text
Images
Audio
Video

License

Usage and distribution terms

Granite 3.3 8B Instruct is licensed under Apache 2.0, while Nova Pro uses a proprietary license.

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

Granite 3.3 8B Instruct

Apache 2.0

Open weights

Nova Pro

Proprietary

Closed source

Release Timeline

When each model was launched

Granite 3.3 8B Instruct was released on 2025-04-16, while Nova Pro was released on 2024-11-20.

Granite 3.3 8B Instruct is 5 months newer than Nova Pro.

Granite 3.3 8B Instruct

Apr 16, 2025

1.0 years ago

4mo newer
Nova Pro

Nov 20, 2024

1.4 years ago

Knowledge Cutoff

When training data ends

Granite 3.3 8B Instruct has a documented knowledge cutoff of 2024-04-01, while Nova Pro's cutoff date is not specified.

We can confirm Granite 3.3 8B Instruct's training data extends to 2024-04-01, but cannot make a direct comparison without Nova Pro's cutoff date.

Granite 3.3 8B Instruct

Apr 2024

Nova Pro

—

Provider Availability

Granite 3.3 8B Instruct is available from Replicate. Nova Pro is available from Bedrock.

Granite 3.3 8B Instruct

replicate logo
Replicate
Input Price:Input: $0.50/1MOutput Price:Output: $0.50/1M

Nova Pro

bedrock logo
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

IBM
Less expensive input tokens
Less expensive output tokens
Has open weights
Higher HumanEval score (89.7% vs 89.0%)
Amazon
Larger context window (300,000 tokens)
Higher DROP score (85.4% vs 59.4%)
Higher GSM8k score (94.8% vs 80.9%)
Higher IFEval score (92.1% vs 74.8%)
Higher MMLU score (85.9% vs 65.5%)

Detailed Comparison

AI Model Comparison Table
Feature
IBM
Granite 3.3 8B Instruct
Amazon
Nova Pro

FAQ

Common questions about Granite 3.3 8B Instruct vs Nova Pro

Nova Pro significantly outperforms across most benchmarks. Granite 3.3 8B Instruct is made by IBM and Nova Pro is made by Amazon. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
Granite 3.3 8B Instruct scores HumanEval: 89.7%, AttaQ: 88.5%, HumanEval+: 86.1%, AIME 2024: 81.2%, GSM8k: 80.9%. Nova Pro scores ARC-C: 94.8%, GSM8k: 94.8%, DocVQA: 93.5%, IFEval: 92.1%, ChartQA: 89.2%.
Granite 3.3 8B Instruct is 1.6x cheaper for input tokens. Granite 3.3 8B Instruct costs $0.50/M input and $0.50/M output via replicate. Nova Pro costs $0.80/M input and $3.20/M output via bedrock.
Granite 3.3 8B Instruct supports 128K tokens and Nova Pro supports 300K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include context window (128K vs 300K), input pricing ($0.50 vs $0.80/M), licensing (Apache 2.0 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.
Granite 3.3 8B Instruct is developed by IBM and Nova Pro is developed by Amazon.