NOUMENOpen app
NOUMEN

Google · Open weights

Gemma 4 31B Scarlet

Added Oct 8, 2026Open weights

Compare models

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

Loading models…

Use in the app

Scarlet is a multimodal Gemma 4 31B creative finetune for expressive dialogue, long-form storytelling, and roleplay.

  • Reasoning
  • Tools
  • Vision
Input
Text, Images
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.10
Output
$0.45
Cache read
$0.05

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
32.8K
Average output (7 days)
456 tokens
Longer than 45% of 473 models

Side by side

Gemma 4 31B Scarlet 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…

Gemma 4 31B ScarletGoogleThis modelGLM 5.3 FlashZ.aiRemove
ProviderGoogleZ.ai
Discovery tierOpen weightsOpen weights
AddedOct 8, 2026Aug 26, 2026
Limits
Context window262.14K1.05MBest
Max output32.77K131.07KBest
Average output456 tokens1.3K tokens
Pricing, USD per 1M tokens
Input$0.10$0.10
Output$0.45$0.30Best
Cache read$0.05$0.025Best
Performance
Throughput15.5 tok/s174.6 tok/sBest
Time to first token8.5 s2.5 sBest
Request success (24h)94.1%99.6%Best
Benchmark indexes
Intelligence Index—41.8
Coding Index—71.5
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputNoYes
Video inputNoYes
Reasoning effort—low, high, max

Public evaluations

Benchmarks

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

  • Gemma 4 31B Scarlet
  • GLM 5.3 Flash

Intelligence Index

  • Gemma 4 31B Scarlet—
  • GLM 5.3 Flash41.8
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Gemma 4 31B Scarlet: —
    • GLM 5.3 Flash: 71.5

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Gemma 4 31B Scarlet: —
    • GLM 5.3 Flash: 60.4%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Gemma 4 31B Scarlet: —
    • GLM 5.3 Flash: 25.4%

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • Gemma 4 31B Scarlet: —
    • GLM 5.3 Flash: 0.8%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Gemma 4 31B Scarlet: —
    • GLM 5.3 Flash: 1,452 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Gemma 4 31B Scarlet: —
    • GLM 5.3 Flash: 1,642 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Gemma 4 31B Scarlet: —
    • GLM 5.3 Flash: 15.4%

  • AA-LCRv1.1

    Reasoning across long documents

    • Gemma 4 31B Scarlet: —
    • GLM 5.3 Flash: 80.0%

  • MLCR-AA

    Long-context reasoning over medical records

    • Gemma 4 31B Scarlet: —
    • GLM 5.3 Flash: 11.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Gemma 4 31B Scarlet: —
    • GLM 5.3 Flash: 39.9%

  • GPQA Diamond

    Graduate-level science questions

    • Gemma 4 31B Scarlet: —
    • GLM 5.3 Flash: 91.2%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Gemma 4 31B Scarlet: —
    • GLM 5.3 Flash: 32.8%

  • SciCode

    Scientific computing in Python

    • Gemma 4 31B Scarlet: —
    • GLM 5.3 Flash: 51.6%

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Gemma 4 31B Scarlet: —
    • GLM 5.3 Flash: 80.0%

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.

Throughput
15.5 tok/s
Faster than 5% of 260 models
Time to first token
8.5 s
Quicker than 13% of 260 models
Prompt cache hits
6.0%
About $0.097 per 1M input tokens with caching
Request success (24h)
94.1%

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": "gemma-4-31b-it-scarlet",
    "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="gemma-4-31b-it-scarlet",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Google

Other Google models, starting with the same family.