Model Comparison

Mistral Small 3 24B Base vs Phi 4 MiniWhich is better in 2026?

Mistral Small 3 24B Base shows notably better performance in the majority of benchmarks.

Verdict: Mistral Small 3 24B Base vs Phi 4 Mini — which is better?

Mistral Small 3 24B Base (by Mistral AI) and Phi 4 Mini (by Microsoft) 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 Base outperforms in 4 benchmarks (ARC-C, GPQA, MMLU, MMLU-Pro), while Phi 4 Mini is better at 2 benchmarks (GSM8k, MATH). Mistral Small 3 24B Base shows notably better performance in the majority of benchmarks.

Choose Mistral Small 3 24B Base if…

  • you want the strongest raw capability — it leads on 4 of 6 shared benchmarks

Choose Phi 4 Mini if…

  • you want the most recent training data — it shipped Feb 2025

Performance Benchmarks

Comparative analysis across standard metrics

6 benchmarks

Mistral Small 3 24B Base outperforms in 4 benchmarks (ARC-C, GPQA, MMLU, MMLU-Pro), while Phi 4 Mini is better at 2 benchmarks (GSM8k, MATH).

Mistral Small 3 24B Base shows notably better performance in the majority of benchmarks.

Tue Jul 28 2026 • llm-stats.com

Arena Performance

Human preference votes

Model Size

Parameter count comparison

19.8B diff

Mistral Small 3 24B Base has 19.8B more parameters than Phi 4 Mini, making it 514.6% larger.

Mistral AI
Mistral Small 3 24B Base
23.6Bparameters
Microsoft
Phi 4 Mini
3.8Bparameters
23.6B
Mistral Small 3 24B Base
3.8B
Phi 4 Mini

Input Capabilities

Supported data types and modalities

Mistral Small 3 24B Base supports multimodal inputs, whereas Phi 4 Mini does not.

Mistral Small 3 24B Base can handle both text and other forms of data like images, making it suitable for multimodal applications.

Mistral Small 3 24B Base

Text
Images
Audio
Video

Phi 4 Mini

Text
Images
Audio
Video

License

Usage and distribution terms

Mistral Small 3 24B Base is licensed under Apache 2.0, while Phi 4 Mini uses MIT.

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

Mistral Small 3 24B Base

Apache 2.0

Open weights

Phi 4 Mini

MIT

Open weights

Release Timeline

When each model was launched

Mistral Small 3 24B Base was released on 2025-01-30, while Phi 4 Mini was released on 2025-02-01.

Phi 4 Mini is 0 month newer than Mistral Small 3 24B Base.

Mistral Small 3 24B Base

Jan 30, 2025

1.5 years ago

Phi 4 Mini

Feb 1, 2025

1.5 years ago

2d newer

Knowledge Cutoff

When training data ends

Mistral Small 3 24B Base has a knowledge cutoff of 2023-10-01, while Phi 4 Mini has a cutoff of 2024-06-01.

Phi 4 Mini has more recent training data (up to 2024-06-01), making it potentially better informed about events through that date compared to Mistral Small 3 24B Base (2023-10-01).

Mistral Small 3 24B Base

Oct 2023

Phi 4 Mini

Jun 2024

8 mo newer

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Mistral AI
Supports multimodal inputs
Higher ARC-C score (91.3% vs 83.7%)
Higher GPQA score (34.4% vs 25.2%)
Higher MMLU score (80.7% vs 67.3%)
Higher MMLU-Pro score (54.4% vs 52.8%)
Microsoft
Higher GSM8k score (88.6% vs 80.7%)
Higher MATH score (64.0% vs 46.0%)

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against Mistral Small 3 24B Base and Phi 4 Mini side-by-side, then vote on the output you prefer.

Mistral Small 3 24B Base
✓ Preferred
Phi 4 Mini
Open in Playground
AI Model Comparison Table
Feature
Mistral AI
Mistral Small 3 24B Base
Microsoft
Phi 4 Mini

FAQ

Common questions about Mistral Small 3 24B Base vs Phi 4 Mini.

Which is better, Mistral Small 3 24B Base or Phi 4 Mini?

Mistral Small 3 24B Base shows notably better performance in the majority of benchmarks. Mistral Small 3 24B Base is made by Mistral AI and Phi 4 Mini is made by Microsoft. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Mistral Small 3 24B Base compare to Phi 4 Mini in benchmarks?

Mistral Small 3 24B Base scores ARC-C: 91.3%, GSM8k: 80.7%, MMLU: 80.7%, TriviaQA: 80.3%, MBPP: 69.6%. Phi 4 Mini scores GSM8k: 88.6%, ARC-C: 83.7%, BoolQ: 81.2%, OpenBookQA: 79.2%, PIQA: 77.6%.

What are the main differences between Mistral Small 3 24B Base and Phi 4 Mini?

Key differences include multimodal support (yes vs no), licensing (Apache 2.0 vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Mistral Small 3 24B Base and Phi 4 Mini?

Mistral Small 3 24B Base is developed by Mistral AI and Phi 4 Mini is developed by Microsoft.

Related comparisons