NOUMENOpen app
NOUMEN

Google · Open weights

Gemma 4 31B Thinking

Added Apr 2, 2026Open weights

Compare models

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

Loading models…

Use in the app

Google's Gemma 4 31B instruction-tuned model with thinking explicitly enabled, exposing reasoning traces for complex multimodal and coding workflows. Requests containing video cost $0.14 per million input tokens and $0.40 per million output tokens.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • Video input
Input
Text, Images, Video
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.10
Output
$0.34
Cache read
$0.10

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
131.1K
Average output (7 days)
1.1K tokens
Longer than 74% of 468 models

Side by side

Gemma 4 31B Thinking 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 ThinkingGoogleThis modelGLM 4.7 Flash ThinkingZ.aiRemove
ProviderGoogleZ.ai
Discovery tierOpen weightsOpen weights
AddedApr 2, 2026Jan 19, 2026
Limits
Context window262.14KBest200K
Max output131.07KBest128K
Average output1.1K tokens2.3K tokens
Pricing, USD per 1M tokens
Input$0.10$0.07Best
Output$0.34Best$0.40
Cache read$0.10$0.01Best
Performance
Throughput27.7 tok/s43.1 tok/sBest
Time to first token7.2 s6.6 sBest
Request success (24h)99.7%100.0%Best
Benchmark indexes
Intelligence Index14.714.9Best
Coding Index43.4—
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesNo
Structured outputYesNo
Video inputYesNo
Reasoning effort——

Public evaluations

Benchmarks

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

  • Gemma 4 31B Thinking
  • GLM 4.7 Flash Thinking

Intelligence Index

  • Gemma 4 31B Thinking14.7
  • GLM 4.7 Flash Thinking14.9

Gemma 4 31B Thinking: Better than 35% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Gemma 4 31B Thinking: 43.4
    • GLM 4.7 Flash Thinking: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Gemma 4 31B Thinking: 4.9%
    • GLM 4.7 Flash Thinking: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Gemma 4 31B Thinking: 0.5%
    • GLM 4.7 Flash Thinking: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Gemma 4 31B Thinking: 368 Elo
    • GLM 4.7 Flash Thinking: —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Gemma 4 31B Thinking: 619 Elo
    • GLM 4.7 Flash Thinking: —

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Gemma 4 31B Thinking: 6.0%
    • GLM 4.7 Flash Thinking: —

  • AA-LCRv1.1

    Reasoning across long documents

    • Gemma 4 31B Thinking: 69.7%Top
    • GLM 4.7 Flash Thinking: 41.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Gemma 4 31B Thinking: 23.6%Top
    • GLM 4.7 Flash Thinking: 7.6%

  • GPQA Diamond

    Graduate-level science questions

    • Gemma 4 31B Thinking: 85.7%Top
    • GLM 4.7 Flash Thinking: 58.1%

  • IFBench

    Following precise output instructions

    • Gemma 4 31B Thinking: 75.6%Top
    • GLM 4.7 Flash Thinking: 60.8%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Gemma 4 31B Thinking: 0.0%
    • GLM 4.7 Flash Thinking: —

  • SciCode

    Scientific computing in Python

    • Gemma 4 31B Thinking: 45.5%
    • GLM 4.7 Flash Thinking: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Gemma 4 31B Thinking: 36.4%Top
    • GLM 4.7 Flash Thinking: 22.0%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Gemma 4 31B Thinking: 59.9%
    • GLM 4.7 Flash Thinking: 98.8%Top

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Gemma 4 31B Thinking: 69.7%Top
    • GLM 4.7 Flash Thinking: 41.7%

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
27.7 tok/s
Faster than 19% of 253 models
Time to first token
7.2 s
Quicker than 20% of 253 models
Prompt cache hits
31.6%
About $0.10 per 1M input tokens with caching
Request success (24h)
99.8%
Reliable

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.

Hourly request success · last 72 hoursLowest hour 97.1%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

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

Google

Other Google models, starting with the same family.