Model Comparison

DeepSeek-V2.5 vs Gemma 3n E4B Instructed LiteRT Preview

DeepSeek-V2.5 significantly outperforms across most benchmarks.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

2 benchmarks

DeepSeek-V2.5 outperforms in 2 benchmarks (HumanEval, MMLU), while Gemma 3n E4B Instructed LiteRT Preview is better at 0 benchmarks.

DeepSeek-V2.5 significantly outperforms across most benchmarks.

Thu Apr 16 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Cost data unavailable.

Lowest available price from all providers
Thu Apr 16 2026 • llm-stats.com
DeepSeek
DeepSeek-V2.5
Input tokens$0.14
Output tokens$0.28
Best providerDeepSeek
Google
Gemma 3n E4B Instructed LiteRT Preview
Input tokens$0.00
Output tokens$0.00
Best providerUnknown Organization
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

234.1B diff

DeepSeek-V2.5 has 234.1B more parameters than Gemma 3n E4B Instructed LiteRT Preview, making it 12256.0% larger.

DeepSeek
DeepSeek-V2.5
236.0Bparameters
Google
Gemma 3n E4B Instructed LiteRT Preview
1.9Bparameters
236.0B
DeepSeek-V2.5
1.9B
Gemma 3n E4B Instructed LiteRT Preview

Context Window

Maximum input and output token capacity

Only DeepSeek-V2.5 specifies input context (8,192 tokens). Only DeepSeek-V2.5 specifies output context (8,192 tokens).

DeepSeek
DeepSeek-V2.5
Input8,192 tokens
Output8,192 tokens
Google
Gemma 3n E4B Instructed LiteRT Preview
Input- tokens
Output- tokens
Thu Apr 16 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Gemma 3n E4B Instructed LiteRT Preview supports multimodal inputs, whereas DeepSeek-V2.5 does not.

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

DeepSeek-V2.5

Text
Images
Audio
Video

Gemma 3n E4B Instructed LiteRT Preview

Text
Images
Audio
Video

License

Usage and distribution terms

DeepSeek-V2.5 is licensed under deepseek, while Gemma 3n E4B Instructed LiteRT Preview uses Gemma.

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

DeepSeek-V2.5

deepseek

Open weights

Gemma 3n E4B Instructed LiteRT Preview

Gemma

Open weights

Release Timeline

When each model was launched

DeepSeek-V2.5 was released on 2024-05-08, while Gemma 3n E4B Instructed LiteRT Preview was released on 2025-05-20.

Gemma 3n E4B Instructed LiteRT Preview is 13 months newer than DeepSeek-V2.5.

DeepSeek-V2.5

May 8, 2024

1.9 years ago

Gemma 3n E4B Instructed LiteRT Preview

May 20, 2025

11 months ago

1.0yr newer

Knowledge Cutoff

When training data ends

Gemma 3n E4B Instructed LiteRT Preview has a documented knowledge cutoff of 2024-06-01, while DeepSeek-V2.5's cutoff date is not specified.

We can confirm Gemma 3n E4B Instructed LiteRT Preview's training data extends to 2024-06-01, but cannot make a direct comparison without DeepSeek-V2.5's cutoff date.

DeepSeek-V2.5

—

Gemma 3n E4B Instructed LiteRT Preview

Jun 2024

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

DeepSeek
Larger context window (8,192 tokens)
Higher HumanEval score (89.0% vs 75.0%)
Higher MMLU score (80.4% vs 64.9%)
Google
Supports multimodal inputs

Detailed Comparison

AI Model Comparison Table
Feature
DeepSeek
DeepSeek-V2.5
Google
Gemma 3n E4B Instructed LiteRT Preview

FAQ

Common questions about DeepSeek-V2.5 vs Gemma 3n E4B Instructed LiteRT Preview

DeepSeek-V2.5 significantly outperforms across most benchmarks. DeepSeek-V2.5 is made by DeepSeek and Gemma 3n E4B Instructed LiteRT Preview is made by Google. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
DeepSeek-V2.5 scores GSM8k: 95.1%, MT-Bench: 90.2%, HumanEval: 89.0%, BBH: 84.3%, AlignBench: 80.4%. Gemma 3n E4B Instructed LiteRT Preview scores ARC-E: 81.6%, BoolQ: 81.6%, PIQA: 81.0%, HellaSwag: 78.6%, HumanEval: 75.0%.
DeepSeek-V2.5 supports 8K tokens and Gemma 3n E4B Instructed LiteRT Preview supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include multimodal support (no vs yes), licensing (deepseek vs Gemma). See the full comparison above for benchmark-by-benchmark results.
DeepSeek-V2.5 is developed by DeepSeek and Gemma 3n E4B Instructed LiteRT Preview is developed by Google.