Model Comparison

Gemma 3n E4B Instructed vs Phi 4

Phi 4 significantly outperforms across most benchmarks. Phi 4 is 285.7x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

5 benchmarks

Gemma 3n E4B Instructed outperforms in 0 benchmarks, while Phi 4 is better at 5 benchmarks (GPQA, HumanEval, MGSM, MMLU, MMLU-Pro).

Phi 4 significantly outperforms across most benchmarks.

Thu Jun 04 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Phi 4 costs less

For input processing, Gemma 3n E4B Instructed ($20.00/1M tokens) is 285.7x more expensive than Phi 4 ($0.07/1M tokens).

For output processing, Gemma 3n E4B Instructed ($40.00/1M tokens) is 285.7x more expensive than Phi 4 ($0.14/1M tokens).

In conclusion, Gemma 3n E4B Instructed is more expensive than Phi 4.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Thu Jun 04 2026 • llm-stats.com
Google
Gemma 3n E4B Instructed
Input tokens$20.00
Output tokens$40.00
Best providerTogether
Microsoft
Phi 4
Input tokens$0.07
Output tokens$0.14
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

6.7B diff

Phi 4 has 6.7B more parameters than Gemma 3n E4B Instructed, making it 83.8% larger.

Google
Gemma 3n E4B Instructed
8.0Bparameters
Microsoft
Phi 4
14.7Bparameters
8.0B
Gemma 3n E4B Instructed
14.7B
Phi 4

Context Window

Maximum input and output token capacity

Gemma 3n E4B Instructed accepts 32,000 input tokens compared to Phi 4's 16,000 tokens. Gemma 3n E4B Instructed can generate longer responses up to 32,000 tokens, while Phi 4 is limited to 16,000 tokens.

Google
Gemma 3n E4B Instructed
Input32,000 tokens
Output32,000 tokens
Microsoft
Phi 4
Input16,000 tokens
Output16,000 tokens
Thu Jun 04 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Gemma 3n E4B Instructed supports multimodal inputs, whereas Phi 4 does not.

Gemma 3n E4B Instructed can handle both text and other forms of data like images, making it suitable for multimodal applications.

Gemma 3n E4B Instructed

Text
Images
Audio
Video

Phi 4

Text
Images
Audio
Video

License

Usage and distribution terms

Gemma 3n E4B Instructed is licensed under a proprietary license, while Phi 4 uses MIT.

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

Gemma 3n E4B Instructed

Proprietary

Closed source

Phi 4

MIT

Open weights

Release Timeline

When each model was launched

Gemma 3n E4B Instructed was released on 2025-06-26, while Phi 4 was released on 2024-12-12.

Gemma 3n E4B Instructed is 7 months newer than Phi 4.

Gemma 3n E4B Instructed

Jun 26, 2025

11 months ago

6mo newer
Phi 4

Dec 12, 2024

1.5 years ago

Knowledge Cutoff

When training data ends

Both models have the same knowledge cutoff date of 2024-06-01.

They should have similar awareness of historical events and information up to this date.

Gemma 3n E4B Instructed

Jun 2024

Phi 4

Jun 2024

Provider Availability

Gemma 3n E4B Instructed is available from Together. Phi 4 is available from DeepInfra.

Gemma 3n E4B Instructed

together logo
Together
Input Price:Input: $20.00/1MOutput Price:Output: $40.00/1M

Phi 4

deepinfra logo
Deepinfra
Input Price:Input: $0.07/1MOutput Price:Output: $0.14/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Google
Larger context window (32,000 tokens)
Supports multimodal inputs
Microsoft
Less expensive input tokens
Less expensive output tokens
Has open weights
Higher GPQA score (56.1% vs 23.7%)
Higher HumanEval score (82.6% vs 75.0%)
Higher MGSM score (80.6% vs 67.0%)
Higher MMLU score (84.8% vs 64.9%)
Higher MMLU-Pro score (70.4% vs 50.6%)

Detailed Comparison

AI Model Comparison Table
Feature
Google
Gemma 3n E4B Instructed
Microsoft
Phi 4

FAQ

Common questions about Gemma 3n E4B Instructed vs Phi 4.

Which is better, Gemma 3n E4B Instructed or Phi 4?

Phi 4 significantly outperforms across most benchmarks. Gemma 3n E4B Instructed is made by Google and Phi 4 is made by Microsoft. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Gemma 3n E4B Instructed compare to Phi 4 in benchmarks?

Gemma 3n E4B Instructed scores HumanEval: 75.0%, MGSM: 67.0%, MMLU: 64.9%, Global-MMLU-Lite: 64.5%, MBPP: 63.6%. Phi 4 scores MMLU: 84.8%, HumanEval+: 82.8%, HumanEval: 82.6%, MGSM: 80.6%, MATH: 80.4%.

Is Gemma 3n E4B Instructed cheaper than Phi 4?

Phi 4 is 285.7x cheaper for input tokens. Gemma 3n E4B Instructed costs $20.00/M input and $40.00/M output via together. Phi 4 costs $0.07/M input and $0.14/M output via deepinfra.

What are the context window sizes for Gemma 3n E4B Instructed and Phi 4?

Gemma 3n E4B Instructed supports 32K tokens and Phi 4 supports 16K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Gemma 3n E4B Instructed and Phi 4?

Key differences include context window (32K vs 16K), input pricing ($20.00 vs $0.07/M), multimodal support (yes vs no), licensing (Proprietary vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Gemma 3n E4B Instructed and Phi 4?

Gemma 3n E4B Instructed is developed by Google and Phi 4 is developed by Microsoft.