Model Comparison
Llama 3.2 90B Instruct vs Mistral Small 3.1 24B BaseWhich is better in 2026?
Llama 3.2 90B Instruct significantly outperforms across most benchmarks. Mistral Small 3.1 24B Base is 2.4x cheaper per token.
Verdict: Llama 3.2 90B Instruct vs Mistral Small 3.1 24B Base — which is better?
Llama 3.2 90B Instruct (by Meta) and Mistral Small 3.1 24B Base (by Mistral AI) 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.
Llama 3.2 90B Instruct outperforms in 3 benchmarks (GPQA, MMLU, MMMU), while Mistral Small 3.1 24B Base is better at 0 benchmarks. Llama 3.2 90B Instruct significantly outperforms across most benchmarks.
On price, Mistral Small 3.1 24B Base is roughly 2.4x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Choose Llama 3.2 90B Instruct if…
- you want the strongest raw capability — it leads on 3 of 3 shared benchmarks
Choose Mistral Small 3.1 24B Base if…
- cost matters — it's about 2.4x cheaper per token
- you want the most recent training data — it shipped Mar 2025
Performance Benchmarks
Comparative analysis across standard metrics
Llama 3.2 90B Instruct outperforms in 3 benchmarks (GPQA, MMLU, MMMU), while Mistral Small 3.1 24B Base is better at 0 benchmarks.
Llama 3.2 90B Instruct significantly outperforms across most benchmarks.
Arena Performance
Human preference votes
Pricing Analysis
Price comparison per million tokens
For input processing, Llama 3.2 90B Instruct ($0.35/1M tokens) is 3.5x more expensive than Mistral Small 3.1 24B Base ($0.10/1M tokens).
For output processing, Llama 3.2 90B Instruct ($0.40/1M tokens) is 1.3x more expensive than Mistral Small 3.1 24B Base ($0.30/1M tokens).
In conclusion, Llama 3.2 90B Instruct is more expensive than Mistral Small 3.1 24B Base.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
Llama 3.2 90B Instruct has 66.0B more parameters than Mistral Small 3.1 24B Base, making it 275.0% larger.
Context Window
Maximum input and output token capacity
Both models have the same input context window of 128,000 tokens. Both models can generate responses up to 128,000 tokens.
Input Capabilities
Supported data types and modalities
Both Llama 3.2 90B Instruct and Mistral Small 3.1 24B Base support multimodal inputs.
They are both capable of processing various types of data, offering versatility in application.
Llama 3.2 90B Instruct
Mistral Small 3.1 24B Base
License
Usage and distribution terms
Llama 3.2 90B Instruct is licensed under Llama 3.2, while Mistral Small 3.1 24B Base uses Apache 2.0.
License differences may affect how you can use these models in commercial or open-source projects.
Llama 3.2
Open weights
Apache 2.0
Open weights
Release Timeline
When each model was launched
Llama 3.2 90B Instruct was released on 2024-09-25, while Mistral Small 3.1 24B Base was released on 2025-03-17.
Mistral Small 3.1 24B Base is 6 months newer than Llama 3.2 90B Instruct.
Sep 25, 2024
1.8 years ago
Mar 17, 2025
1.3 years ago
5mo newerKnowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
Llama 3.2 90B Instruct is available from DeepInfra, Bedrock, Fireworks, Together, Hyperbolic. Mistral Small 3.1 24B Base is available from Mistral AI.
Llama 3.2 90B Instruct
Mistral Small 3.1 24B Base
Outputs Comparison
Key Takeaways
Mistral Small 3.1 24B Base
View detailsMistral AI
Detailed Comparison
Interactive Arena
Judge for yourself.
Run your own prompts against Llama 3.2 90B Instruct and Mistral Small 3.1 24B Base side-by-side, then vote on the output you prefer.
| Feature | | |
|---|
FAQ
Common questions about Llama 3.2 90B Instruct vs Mistral Small 3.1 24B Base.