Google model product
Gemini Diffusion
Gemini Diffusion is a state-of-the-art, experimental text diffusion model from Google DeepMind.
Updated Aug 17, 2026. Default version: Gemini Diffusion
LLMBoard Score2.9Gemini Diffusion
Coverage80%8 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
Gemini Diffusion Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemini Diffusion Benchmark Results
Benchmark scores for Gemini Diffusion.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkBigCodeBench | Score45.4% | Rank01 | Participants2 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkLBPP (v2) | Score56.8% | Rank01 | Participants1 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkBIG-Bench Extra Hard | Score15.0% | Rank09 | Participants11 | Percentile20.0% | EvidenceC | Evaluated |
| BenchmarkGlobal-MMLU-Lite | Score69.1% | Rank09 | Participants15 | Percentile42.9% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score89.6% | Rank15 | Participants66 | Percentile78.5% | EvidenceC | Evaluated |
| BenchmarkMBPP | Score76.0% | Rank17 | Participants33 | Percentile50.0% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score30.9% | Rank63 | Participants75 | Percentile16.2% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score22.9% | Rank109 | Participants111 | Percentile1.8% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score23.3% | Rank111 | Participants115 | Percentile3.5% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score40.4% | Rank210 | Participants239 | Percentile12.2% | EvidenceC | Evaluated |
Gemini Diffusion Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Gemini Diffusion Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Gemini Diffusion Runtime Performance
Provider-specific output speed and catalog latency for Gemini Diffusion. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Gemini Diffusion Specifications
Technical details for the model's default version.
- Version
- Gemini Diffusion
- Released
- May 20, 2025
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Gemini Diffusion Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGemini Diffusion | Released | LLMBoard2.9 | ParametersN/A | ContextN/A | Max outputN/A | Open weightsNo | LicenseProprietary |
Gemini Diffusion vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Gemini Diffusion
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemma 3n E2B
GOGoogle
Gemini 1.5 Flash 8B
GOGoogle
Gemma 3n E4B
GOGoogle
Gemma 3n E2B LiteRT
GOGoogle
MedGemma 4B IT
GOGoogle
Gemma 3n E4B LiteRT
What is Gemini Diffusion?
Key information about Gemini Diffusion and its available data.
Gemini Diffusion is a state-of-the-art, experimental text diffusion model from Google DeepMind. It explores a new kind of language model designed to provide users with greater control, creativity, and speed in text generation.
Instead of predicting text token-by-token, it learns to generate outputs by refining noise step-by-step, allowing for rapid iteration and error correction during generation.
Key capabilities include rapid response times (reportedly 1479 tokens/sec excluding overhead), generation of more coherent text by outputting entire blocks of tokens at once, and iterative refinement for consistent outputs. It excels at tasks like editing, including in math and code contexts.
Data as of 2026-08-17.
FAQ
Common questions about Gemini Diffusion.
When was Gemini Diffusion released?
Gemini Diffusion's default version was released on May 20, 2025.
How much does Gemini Diffusion cost?
No official standard PAYG price is currently available for Gemini Diffusion.
Who created Gemini Diffusion?
Gemini Diffusion was created by Google.
What is the context window for Gemini Diffusion?
A context window is not available for the default version.
Is Gemini Diffusion open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Gemini Diffusion?
No provider offering is currently linked to the default version.
What models should I compare Gemini Diffusion with?
Nearby ranked alternatives include Claude Sonnet 3, Granite 3.3 8B, Qwen3.5 2B.