Model Comparison

Gemini 2.5 Flash-Lite vs Gemini Diffusion

Gemini 2.5 Flash-Lite significantly outperforms across most benchmarks.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

5 benchmarks

Gemini 2.5 Flash-Lite outperforms in 5 benchmarks (AIME 2025, Global-MMLU-Lite, GPQA, LiveCodeBench, SWE-Bench Verified), while Gemini Diffusion is better at 0 benchmarks.

Gemini 2.5 Flash-Lite significantly outperforms across most benchmarks.

Sun May 31 2026 • llm-stats.com

Arena Performance

Human preference votes

Context Window

Maximum input and output token capacity

Only Gemini 2.5 Flash-Lite specifies input context (1,048,576 tokens). Only Gemini 2.5 Flash-Lite specifies output context (65,536 tokens).

Google
Gemini 2.5 Flash-Lite
Input1,048,576 tokens
Output65,536 tokens
Google
Gemini Diffusion
Input- tokens
Output- tokens
Sun May 31 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Gemini 2.5 Flash-Lite supports multimodal inputs, whereas Gemini Diffusion does not.

Gemini 2.5 Flash-Lite can handle both text and other forms of data like images, making it suitable for multimodal applications.

Gemini 2.5 Flash-Lite

Text
Images
Audio
Video

Gemini Diffusion

Text
Images
Audio
Video

License

Usage and distribution terms

Gemini 2.5 Flash-Lite is licensed under Creative Commons Attribution 4.0 License, while Gemini Diffusion uses a proprietary license.

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

Gemini 2.5 Flash-Lite

Creative Commons Attribution 4.0 License

Open weights

Gemini Diffusion

Proprietary

Closed source

Release Timeline

When each model was launched

Gemini 2.5 Flash-Lite was released on 2025-06-17, while Gemini Diffusion was released on 2025-05-20.

Gemini 2.5 Flash-Lite is 1 month newer than Gemini Diffusion.

Gemini 2.5 Flash-Lite

Jun 17, 2025

11 months ago

4w newer
Gemini Diffusion

May 20, 2025

1.0 years ago

Knowledge Cutoff

When training data ends

Gemini 2.5 Flash-Lite has a documented knowledge cutoff of 2025-01-01, while Gemini Diffusion's cutoff date is not specified.

We can confirm Gemini 2.5 Flash-Lite's training data extends to 2025-01-01, but cannot make a direct comparison without Gemini Diffusion's cutoff date.

Gemini 2.5 Flash-Lite

Jan 2025

Gemini Diffusion

—

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Google
Larger context window (1,048,576 tokens)
Supports multimodal inputs
Has open weights
Higher AIME 2025 score (49.8% vs 23.3%)
Higher Global-MMLU-Lite score (81.1% vs 69.1%)
Higher GPQA score (64.6% vs 40.4%)
Higher LiveCodeBench score (33.7% vs 30.9%)
Higher SWE-Bench Verified score (31.6% vs 22.9%)
Google

No standout differentiators in the data we have for this pair.

Detailed Comparison

AI Model Comparison Table
Feature
Google
Gemini 2.5 Flash-Lite
Google
Gemini Diffusion

FAQ

Common questions about Gemini 2.5 Flash-Lite vs Gemini Diffusion.

Which is better, Gemini 2.5 Flash-Lite or Gemini Diffusion?

Gemini 2.5 Flash-Lite significantly outperforms across most benchmarks. Gemini 2.5 Flash-Lite is made by Google and Gemini Diffusion is made by Google. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Gemini 2.5 Flash-Lite compare to Gemini Diffusion in benchmarks?

Gemini 2.5 Flash-Lite scores FACTS Grounding: 84.1%, Global-MMLU-Lite: 81.1%, MMMU: 72.9%, GPQA: 64.6%, Vibe-Eval: 51.3%. Gemini Diffusion scores HumanEval: 89.6%, MBPP: 76.0%, Global-MMLU-Lite: 69.1%, LBPP (v2): 56.8%, BigCodeBench: 45.4%.

What are the context window sizes for Gemini 2.5 Flash-Lite and Gemini Diffusion?

Gemini 2.5 Flash-Lite supports 1.0M tokens and Gemini Diffusion supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Gemini 2.5 Flash-Lite and Gemini Diffusion?

Key differences include multimodal support (yes vs no), licensing (Creative Commons Attribution 4.0 License vs Proprietary). See the full comparison above for benchmark-by-benchmark results.