NOUMENOpen app
NOUMEN

Google · Open weights

DiffusionGemma

Added Sep 19, 2026Open weights

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

DiffusionGemma is a high-speed diffusion-based version of Gemma 4 26B A4B. It supports optional reasoning and a 262,144-token context window. Temperature, min-p, seed, minimum output tokens, logit bias, bad words, and allowed token IDs are unavailable; omit these parameters to use native diffusion sampling.

  • Reasoning
Input
Text
Output
Text
Reasoning effort
none · xhigh
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.05
Output
$0.15
Cache read
$0.025

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
32.8K
Average output (7 days)
266 tokens
Longer than 28% of 473 models

Side by side

DiffusionGemma compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

DiffusionGemmaGoogleThis modelDeepSeek Chat 0324DeepSeekRemove
ProviderGoogleDeepSeek
Discovery tierOpen weightsOpen weights
AddedSep 19, 2026Jan 1, 2024
Limits
Context window262.14KBest128K
Max output32.77KBest8.19K
Average output266 tokens280 tokens
Pricing, USD per 1M tokens
Input$0.05Best$0.20
Output$0.15Best$0.77
Cache read$0.025Best$0.14
Performance
Throughput—27.9 tok/s
Time to first token—2.6 s
Request success (24h)—99.9%
Benchmark indexes
Intelligence Index9.59.7Best
Coding Index19.721.2Best
Math Index—41.0
Capabilities
ReasoningYesNo
ToolsNoYes
Structured outputNoYes
Reasoning effortnone, xhigh—

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • DiffusionGemma
  • DeepSeek Chat 0324

Intelligence Index

  • DiffusionGemma9.5
  • DeepSeek Chat 03249.7

DiffusionGemma: Better than 19% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • DiffusionGemma: 19.7
    • DeepSeek Chat 0324: 21.2Top

  • Math Index

    Composite of the math evaluations

    • DiffusionGemma: —
    • DeepSeek Chat 0324: 41.0

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • DiffusionGemma: —
    • DeepSeek Chat 0324: 0.3%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • DiffusionGemma: —
    • DeepSeek Chat 0324: 0.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • DiffusionGemma: —
    • DeepSeek Chat 0324: 68 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • DiffusionGemma: 321 EloTop
    • DeepSeek Chat 0324: 69 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • DiffusionGemma: —
    • DeepSeek Chat 0324: 1.6%

  • AA-LCRv1.1

    Reasoning across long documents

    • DiffusionGemma: 19.7%
    • DeepSeek Chat 0324: 40.7%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • DiffusionGemma: 10.8%Top
    • DeepSeek Chat 0324: 4.7%

  • GPQA Diamond

    Graduate-level science questions

    • DiffusionGemma: 66.9%Top
    • DeepSeek Chat 0324: 65.5%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • DiffusionGemma: —
    • DeepSeek Chat 0324: 81.9%

  • IFBench

    Following precise output instructions

    • DiffusionGemma: 59.5%Top
    • DeepSeek Chat 0324: 41.0%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • DiffusionGemma: —
    • DeepSeek Chat 0324: 0.0%

  • SciCode

    Scientific computing in Python

    • DiffusionGemma: —
    • DeepSeek Chat 0324: 39.0%

  • LiveCodeBench

    Recent competitive programming problems

    • DiffusionGemma: —
    • DeepSeek Chat 0324: 40.5%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • DiffusionGemma: —
    • DeepSeek Chat 0324: 41.0%

  • AIME

    Competition mathematics

    • DiffusionGemma: —
    • DeepSeek Chat 0324: 52.0%

  • MATH-500

    Competition math problems

    • DiffusionGemma: —
    • DeepSeek Chat 0324: 94.2%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • DiffusionGemma: —
    • DeepSeek Chat 0324: 15.2%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • DiffusionGemma: —
    • DeepSeek Chat 0324: 47.1%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • DiffusionGemma: 19.7%
    • DeepSeek Chat 0324: 40.7%Top

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Prompt cache hits
0.0%
About $0.05 per 1M input tokens with caching

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/diffusiongemma",
    "reasoning_effort": "none",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="google/diffusiongemma",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Google

Other Google models, starting with the same family.