The AI arena is free today

Open Superagent

Magistral Small 2506 vs Phi 4 Reasoning

Phi 4 Reasoning shows notably better performance in the majority of benchmarks.

Mistral AI · Microsoft · Updated for 2026

Which is better?

Magistral Small 2506 outperforms in 1 benchmarks (GPQA), while Phi 4 Reasoning is better at 3 benchmarks (AIME 2024, AIME 2025, LiveCodeBench). Phi 4 Reasoning shows notably better performance in the majority of benchmarks.

Based on current benchmark, pricing, and model metadata for 2026.

Choose Magistral Small 2506

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

Choose Phi 4 Reasoning

  • you want the strongest raw capability — it leads on 3 of 4 shared benchmarks

At a glance

The differences that matter most.

Magistral Small 2506
Mistral AI
Phi 4 Reasoning
Microsoft
Benchmark wins
1 of 4
3 of 4
Input price
— / M
— / M
Output price
— / M
— / M
Context window
—
—
Released
Jun 2025
Apr 2025
License
Apache 2.0
MIT

Performance Benchmarks

Comparative analysis across standard metrics

4 benchmarks

Magistral Small 2506 outperforms in 1 benchmarks (GPQA), while Phi 4 Reasoning is better at 3 benchmarks (AIME 2024, AIME 2025, LiveCodeBench).

Phi 4 Reasoning shows notably better performance in the majority of benchmarks.

Tue Aug 25 2026 • llm-stats.com

Arena Performance

Playground indexes and blind preference scores

Model Size

Parameter count comparison

10.0B diff

Magistral Small 2506 has 10.0B more parameters than Phi 4 Reasoning, making it 71.4% larger.

Mistral AI
Magistral Small 2506
24.0Bparameters
Microsoft
Phi 4 Reasoning
14.0Bparameters
24.0B
Magistral Small 2506
14.0B
Phi 4 Reasoning

License

Usage and distribution terms

Magistral Small 2506 is licensed under Apache 2.0, while Phi 4 Reasoning uses MIT.

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

Magistral Small 2506

Apache 2.0

Open weights

Phi 4 Reasoning

MIT

Open weights

Release Timeline

When each model was launched

Magistral Small 2506 was released on 2025-06-10, while Phi 4 Reasoning was released on 2025-04-30.

Magistral Small 2506 is 1 month newer than Phi 4 Reasoning.

Magistral Small 2506

Jun 10, 2025

1.2 years ago

1mo newer
Phi 4 Reasoning

Apr 30, 2025

1.3 years ago

Knowledge Cutoff

When training data ends

Magistral Small 2506 has a knowledge cutoff of 2025-06-01, while Phi 4 Reasoning has a cutoff of 2025-03-01.

Magistral Small 2506 has more recent training data (up to 2025-06-01), making it potentially better informed about events through that date compared to Phi 4 Reasoning (2025-03-01).

Magistral Small 2506

Jun 2025

3 mo newer
Phi 4 Reasoning

Mar 2025

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Magistral Small 2506 and Phi 4 Reasoning side-by-side, then vote on the output you prefer.

Magistral Small 2506
✓ Preferred
Phi 4 Reasoning
Open in Playground

FAQ

Common questions about Magistral Small 2506 vs Phi 4 Reasoning.

Which is better, Magistral Small 2506 or Phi 4 Reasoning?

Phi 4 Reasoning shows notably better performance in the majority of benchmarks. Magistral Small 2506 is made by Mistral AI and Phi 4 Reasoning is made by Microsoft. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Magistral Small 2506 compare to Phi 4 Reasoning in benchmarks?

Magistral Small 2506 scores AIME 2024: 70.7%, GPQA: 68.2%, AIME 2025: 62.8%, LiveCodeBench: 51.3%. Phi 4 Reasoning scores FlenQA: 97.7%, HumanEval+: 92.9%, IFEval: 83.4%, OmniMath: 76.6%, AIME 2024: 75.3%.

What are the main differences between Magistral Small 2506 and Phi 4 Reasoning?

Key differences include licensing (Apache 2.0 vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Magistral Small 2506 and Phi 4 Reasoning?

Magistral Small 2506 is developed by Mistral AI and Phi 4 Reasoning is developed by Microsoft.

Related comparisons