DiffusionGemma 26B A4B

Creator

Google DeepMind

Released

2026-06-10

Intelligence

13.5

Artificial Analysis Index

Coding

19.7

Artificial Analysis Index

In $/1M

$0.00

input tokens

Out $/1M

$0.00

output tokens

Blended $/1M

$0.00

3:1 blended

Speed

0

tokens / sec

Profile

License, openness, and modality — the governance layer.

License

Apache 2.0

commercial OK

Weights

Open

downloadable

Modalities

Parameters

25B

total

DiffusionGemma 26B-A4B is Google DeepMind's experimental open-weights text diffusion model based on the Gemma 4 26B-A4B Mixture-of-Experts architecture. It uses discrete diffusion to denoise 256-token canvases in parallel, targeting low-latency local and low-concurrency generation workloads with up to 4x faster text generation on dedicated GPUs. The model has 25.2 billion total parameters, 3.8 billion active parameters, a 256K context window, and multimodal text and image inputs.

Capability profile

Category strength across 20 domains, via LLM Stats.

legal
80finance
80biology
70physics
70language
70chemistry
70math
60agents
60
general
60healthcare
60tool calling
60reasoning
50multimodal
50vision
40long context
30structured output
30
Via LLM Stats

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
67
Humanity’s Last Exam
10
MMLU-Pro
SciCode
34
LiveCodeBench
MATH-500
AIME 2025
τ²-Bench (agentic)
Terminal-Bench Hard
IFBench
59
Via Artificial Analysis
© 2026 NYSGPT2525 LLC