NOUMENOpen app

Google · Open weights

Gemma 4 31B Agares v1

Added May 15, 2026Open weights

Compare models

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

Loading models…

Use in the app

Gemma 4 31B Agares v1 is a community creative finetune for reasoning, multimodal chat, expressive writing, and roleplay.

  • Reasoning
  • Tools
  • Vision
Input
Text, Images
Output
Text
Reasoning effort
none · high
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.31
Output
$0.31

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
—
Average output (7 days)
129 tokens
Longer than 12% of 465 models

Side by side

Gemma 4 31B Agares v1 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 Agares v1GoogleThis modelGemini 4 ArgonGoogleRemove
ProviderGoogleGoogle
Discovery tierOpen weightsFrontier
AddedMay 15, 2026Oct 13, 2026
Limits
Context window262.14K1.05MBest
Max output—65.54K
Average output129 tokens1.6K tokens
Pricing, USD per 1M tokens
Input$0.31Best$2.00
Output$0.31Best$10.00
Cache read—$0.10
Cache write—$0.19
Performance
Throughput—82.9 tok/s
Time to first token—9.8 s
Request success (24h)—98.6%
Benchmark indexes
Intelligence Index—52.6
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputNoYes
PDF inputNoYes
Audio inputNoYes
Video inputNoYes
Reasoning effortnone, highlow, medium, high

Public evaluations

Benchmarks

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

  • Gemma 4 31B Agares v1
  • Gemini 4 Argon

Intelligence Index

  • Gemma 4 31B Agares v1—
  • Gemini 4 Argon52.6
3.8Catalog models by score55.1

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Gemma 4 31B Agares v1: —
    • Gemini 4 Argon: 77.5%
  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Gemma 4 31B Agares v1: —
    • Gemini 4 Argon: 53.1%
  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • Gemma 4 31B Agares v1: —
    • Gemini 4 Argon: 3.9%
  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Gemma 4 31B Agares v1: —
    • Gemini 4 Argon: 1,486 Elo
  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Gemma 4 31B Agares v1: —
    • Gemini 4 Argon: 1,624 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Gemma 4 31B Agares v1: —
    • Gemini 4 Argon: 21.8%
  • AA-LCRv1.1

    Reasoning across long documents

    • Gemma 4 31B Agares v1: —
    • Gemini 4 Argon: 79.7%
  • MLCR-AA

    Long-context reasoning over medical records

    • Gemma 4 31B Agares v1: —
    • Gemini 4 Argon: 13.9%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Gemma 4 31B Agares v1: —
    • Gemini 4 Argon: 57.1%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Gemma 4 31B Agares v1: —
    • Gemini 4 Argon: 57.1%
  • SciCode

    Scientific computing in Python

    • Gemma 4 31B Agares v1: —
    • Gemini 4 Argon: 61.8%

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Gemma 4 31B Agares v1: —
    • Gemini 4 Argon: 79.7%

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

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-Agares-v1",
    "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="Gemma-4-31B-Agares-v1",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Google

Other Google models, starting with the same family.