Gemini Diffusion

GoogleProprietaryVerified

Our state-of-the-art, experimental text diffusion model that uses diffusion techniques to explore a new kind of language model that gives users greater control, creativity, and speed in text generation.

2025-05-20

Diffusion model

Proprietary

Compare with other models

Specifications

Architecture: Diffusion model
License: Proprietary
Type: text
Modalities: text

Benchmark Scores

HumanEval89.6

Evaluates code generation capabilities by asking models to complete Python functions based on docstr...

GPQA40.4

Graduate-level Problems in Quantitative Analysis (GPQA) evaluates advanced reasoning on graduate-lev...

AIME-202523.3

American Invitational Mathematics Examination (AIME) 2025 problems....

BIG-bench15

Beyond the Imitation Game Benchmark (BIG-bench) is a collaborative benchmark of 204 diverse tasks....

MMLU69.1

Massive Multitask Language Understanding (MMLU) tests knowledge across 57 subjects including mathema...

SWE-bench22.9

Software Engineering Benchmark (SWE-bench) evaluates models on real-world software engineering tasks...

See all benchmarks

Advanced Specifications

Model Family: Gemini
API Access: Not Available
Chat Interface: Not Available
Multilingual Support: Yes

Capabilities & Limitations

Capabilities: rapid responsemore coherent textiterative refinementcodemathreasoning

Resources

deepmind.google/models/gemini-diffusion/

Related Models

Gemini 2.5 Flash

Google

Improved across key benchmarks for reasoning, multimodality, code and long context while getting even more efficient. Best for fast performance on complex tasks.

Gemma 3n

Google

Gemma 3n is a mobile-first AI model built on a groundbreaking architecture optimized for on-device performance. It features Per-Layer Embeddings (PLE) for reduced RAM usage, allowing larger models to run on mobile devices with a memory footprint comparable to much smaller models. Supports multimodal understanding including text, images, audio, and video.

Gemini 2.5 Pro

Google

Gemini 2.5 Pro is capable of reasoning through its thoughts before responding, resulting in enhanced performance and improved accuracy. Features Deep Think, an enhanced reasoning mode, and native audio outputs that capture subtle nuances of speech.