Model Comparison
Mistral Small 3 24B Instruct vs Nova ProWhich is better in 2026?
Nova Pro significantly outperforms across most benchmarks. Mistral Small 3 24B Instruct is 16.0x cheaper per token.
Verdict: Mistral Small 3 24B Instruct vs Nova Pro — which is better?
Mistral Small 3 24B Instruct (by Mistral AI) and Nova Pro (by Amazon) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.
Mistral Small 3 24B Instruct outperforms in 0 benchmarks, while Nova Pro is better at 4 benchmarks (GPQA, HumanEval, IFEval, MATH). Nova Pro significantly outperforms across most benchmarks.
On price, Mistral Small 3 24B Instruct is roughly 16.0x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Nova Pro also accepts a larger context window (300,000 input tokens), making it the stronger choice for long documents and large codebases.
Choose Mistral Small 3 24B Instruct if…
- cost matters — it's about 16.0x cheaper per token
- you want the most recent training data — it shipped Jan 2025
- you need open weights you can self-host or fine-tune
Choose Nova Pro if…
- you want the strongest raw capability — it leads on 4 of 4 shared benchmarks
- you process long inputs — it offers a 300,000 token context window
Performance Benchmarks
Comparative analysis across standard metrics
Mistral Small 3 24B Instruct outperforms in 0 benchmarks, while Nova Pro is better at 4 benchmarks (GPQA, HumanEval, IFEval, MATH).
Nova Pro significantly outperforms across most benchmarks.
Arena Performance
Human preference votes
Pricing Analysis
Price comparison per million tokens
For input processing, Mistral Small 3 24B Instruct ($0.07/1M tokens) is 11.4x cheaper than Nova Pro ($0.80/1M tokens).
For output processing, Mistral Small 3 24B Instruct ($0.14/1M tokens) is 22.9x cheaper than Nova Pro ($3.20/1M tokens).
In conclusion, Nova Pro is more expensive than Mistral Small 3 24B Instruct.*
* Using a 3:1 ratio of input to output tokens
Context Window
Maximum input and output token capacity
Nova Pro accepts 300,000 input tokens compared to Mistral Small 3 24B Instruct's 32,000 tokens. Nova Pro can generate longer responses up to 300,000 tokens, while Mistral Small 3 24B Instruct is limited to 32,000 tokens.
Input Capabilities
Supported data types and modalities
Nova Pro supports multimodal inputs, whereas Mistral Small 3 24B Instruct does not.
Nova Pro can handle both text and other forms of data like images, making it suitable for multimodal applications.
Mistral Small 3 24B Instruct
Nova Pro
License
Usage and distribution terms
Mistral Small 3 24B 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.
Apache 2.0
Open weights
Proprietary
Closed source
Release Timeline
When each model was launched
Mistral Small 3 24B Instruct was released on 2025-01-30, while Nova Pro was released on 2024-11-20.
Mistral Small 3 24B Instruct is 2 months newer than Nova Pro.
Jan 30, 2025
1.4 years ago
2mo newerNov 20, 2024
1.5 years ago
Knowledge Cutoff
When training data ends
Mistral Small 3 24B Instruct has a documented knowledge cutoff of 2023-10-01, while Nova Pro's cutoff date is not specified.
We can confirm Mistral Small 3 24B Instruct's training data extends to 2023-10-01, but cannot make a direct comparison without Nova Pro's cutoff date.
Oct 2023
—
Provider Availability
Mistral Small 3 24B Instruct is available from DeepInfra, Mistral AI. Nova Pro is available from Bedrock.
Mistral Small 3 24B Instruct
Nova Pro
Outputs Comparison
Key Takeaways
Mistral Small 3 24B Instruct
View detailsMistral AI
Nova Pro
View detailsAmazon
Detailed Comparison
| Feature | | |
|---|
FAQ
Common questions about Mistral Small 3 24B Instruct vs Nova Pro.