Model Comparison

Gemma 3n E2B Instructed vs Magistral Small 2506Which is better in 2026?

Magistral Small 2506 significantly outperforms across most benchmarks.

Verdict: Gemma 3n E2B Instructed vs Magistral Small 2506 — which is better?

Gemma 3n E2B Instructed (by Google) and Magistral Small 2506 (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.

Gemma 3n E2B Instructed outperforms in 0 benchmarks, while Magistral Small 2506 is better at 3 benchmarks (AIME 2025, GPQA, LiveCodeBench). Magistral Small 2506 significantly outperforms across most benchmarks.

Choose Gemma 3n E2B Instructed if…

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

Choose Magistral Small 2506 if…

  • you want the strongest raw capability — it leads on 3 of 3 shared benchmarks
  • you need open weights you can self-host or fine-tune

Performance Benchmarks

Comparative analysis across standard metrics

3 benchmarks

Gemma 3n E2B Instructed outperforms in 0 benchmarks, while Magistral Small 2506 is better at 3 benchmarks (AIME 2025, GPQA, LiveCodeBench).

Magistral Small 2506 significantly outperforms across most benchmarks.

Sat Jul 18 2026 • llm-stats.com

Arena Performance

Human preference votes

Model Size

Parameter count comparison

16.0B diff

Magistral Small 2506 has 16.0B more parameters than Gemma 3n E2B Instructed, making it 200.0% larger.

Google
Gemma 3n E2B Instructed
8.0Bparameters
Mistral AI
Magistral Small 2506
24.0Bparameters
8.0B
Gemma 3n E2B Instructed
24.0B
Magistral Small 2506

Input Capabilities

Supported data types and modalities

Gemma 3n E2B Instructed supports multimodal inputs, whereas Magistral Small 2506 does not.

Gemma 3n E2B Instructed can handle both text and other forms of data like images, making it suitable for multimodal applications.

Gemma 3n E2B Instructed

Text
Images
Audio
Video

Magistral Small 2506

Text
Images
Audio
Video

License

Usage and distribution terms

Gemma 3n E2B Instructed is licensed under a proprietary license, while Magistral Small 2506 uses Apache 2.0.

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

Gemma 3n E2B Instructed

Proprietary

Closed source

Magistral Small 2506

Apache 2.0

Open weights

Release Timeline

When each model was launched

Gemma 3n E2B Instructed was released on 2025-06-26, while Magistral Small 2506 was released on 2025-06-10.

Gemma 3n E2B Instructed is 1 month newer than Magistral Small 2506.

Gemma 3n E2B Instructed

Jun 26, 2025

1.1 years ago

2w newer
Magistral Small 2506

Jun 10, 2025

1.1 years ago

Knowledge Cutoff

When training data ends

Gemma 3n E2B Instructed has a knowledge cutoff of 2024-06-01, while Magistral Small 2506 has a cutoff of 2025-06-01.

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 Gemma 3n E2B Instructed (2024-06-01).

Gemma 3n E2B Instructed

Jun 2024

Magistral Small 2506

Jun 2025

1 yr newer

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Google
Supports multimodal inputs
Mistral AI
Has open weights
Higher AIME 2025 score (62.8% vs 6.7%)
Higher GPQA score (68.2% vs 24.8%)
Higher LiveCodeBench score (51.3% vs 13.2%)

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against Gemma 3n E2B Instructed and Magistral Small 2506 side-by-side, then vote on the output you prefer.

Gemma 3n E2B Instructed
✓ Preferred
Magistral Small 2506
Open in Playground
AI Model Comparison Table
Feature
Google
Gemma 3n E2B Instructed
Mistral AI
Magistral Small 2506

FAQ

Common questions about Gemma 3n E2B Instructed vs Magistral Small 2506.

Which is better, Gemma 3n E2B Instructed or Magistral Small 2506?

Magistral Small 2506 significantly outperforms across most benchmarks. Gemma 3n E2B Instructed is made by Google and Magistral Small 2506 is made by Mistral AI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Gemma 3n E2B Instructed compare to Magistral Small 2506 in benchmarks?

Gemma 3n E2B Instructed scores HumanEval: 66.5%, MMLU: 60.1%, Global-MMLU-Lite: 59.0%, MBPP: 56.6%, Global-MMLU: 55.1%. Magistral Small 2506 scores AIME 2024: 70.7%, GPQA: 68.2%, AIME 2025: 62.8%, LiveCodeBench: 51.3%.

What are the main differences between Gemma 3n E2B Instructed and Magistral Small 2506?

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

Who makes Gemma 3n E2B Instructed and Magistral Small 2506?

Gemma 3n E2B Instructed is developed by Google and Magistral Small 2506 is developed by Mistral AI.

Related comparisons