NOUMENOpen app
NOUMEN

Google · Frontier

Gemini 3.1 Pro (Preview Custom Tools)

Added Feb 27, 2026

Compare models

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

Loading models…

Use in the app

Gemini 3.1 Pro preview variant tuned for better tool selection behavior in coding agents and multi-tool workflows. It reduces overuse of generic bash tools and improves function-calling reliability while retaining Gemini 3.1 Pro's multimodal reasoning and 1M-token context. NOTE: Inputs > 200k tokens are charged at 2x input and 1.5x output rates.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • Audio input
  • Video input
Input
Text, Images, Video, Audio
Output
Text
Reasoning effort
low · medium · high
Discovery tier
Frontier

Pricing

USD per 1M tokens
Input
$2.00
Output
$12.00
Cache read
$0.20
Cache write
$0.38

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
65.5K
Average output (7 days)
903 tokens
Longer than 68% of 465 models

Side by side

Gemini 3.1 Pro (Preview Custom Tools) 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…

Gemini 3.1 Pro (Preview Custom Tools)GoogleThis modelClaude Sonnet 4.6 ThinkingAnthropicRemove
ProviderGoogleAnthropic
Discovery tierFrontierFrontier
AddedFeb 27, 2026Feb 17, 2026
Limits
Context window1.05MBest1M
Max output65.54K128KBest
Average output903 tokens598 tokens
Pricing, USD per 1M tokens
Input$2.00Best$3.00
Output$12.00Best$15.00
Cache read$0.20Best$0.30
Cache write$0.38—
Performance
Throughput—208.2 tok/s
Time to first token—4.3 s
Request success (24h)—100.0%
Benchmark indexes
Intelligence Index29.730.1Best
Coding Index68.8Best63.0
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputNoYes
Audio inputYesNo
Video inputYesNo
Reasoning effortlow, medium, highlow, medium, high, xhigh, max

Public evaluations

Benchmarks

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

  • Gemini 3.1 Pro (Preview Custom Tools)
  • Claude Sonnet 4.6 Thinking

Intelligence Index

  • Gemini 3.1 Pro (Preview Custom Tools)29.7
  • Claude Sonnet 4.6 Thinking30.1

Gemini 3.1 Pro (Preview Custom Tools): Better than 71% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Gemini 3.1 Pro (Preview Custom Tools): 68.8Top
    • Claude Sonnet 4.6 Thinking: 63.0

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Gemini 3.1 Pro (Preview Custom Tools): 35.4%Top
    • Claude Sonnet 4.6 Thinking: 20.1%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Gemini 3.1 Pro (Preview Custom Tools): 9.4%Top
    • Claude Sonnet 4.6 Thinking: 3.7%

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • Gemini 3.1 Pro (Preview Custom Tools): 0.0%
    • Claude Sonnet 4.6 Thinking: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Gemini 3.1 Pro (Preview Custom Tools): 456 Elo
    • Claude Sonnet 4.6 Thinking: 1,062 EloTop

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Gemini 3.1 Pro (Preview Custom Tools): 791 Elo
    • Claude Sonnet 4.6 Thinking: 1,233 EloTop

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Gemini 3.1 Pro (Preview Custom Tools): 17.8%Top
    • Claude Sonnet 4.6 Thinking: 15.8%

  • AA-LCRv1.1

    Reasoning across long documents

    • Gemini 3.1 Pro (Preview Custom Tools): 82.0%Top
    • Claude Sonnet 4.6 Thinking: 80.0%

  • MLCR-AA

    Long-context reasoning over medical records

    • Gemini 3.1 Pro (Preview Custom Tools): 11.1%Top
    • Claude Sonnet 4.6 Thinking: 7.8%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Gemini 3.1 Pro (Preview Custom Tools): 47.0%Top
    • Claude Sonnet 4.6 Thinking: 33.6%

  • GPQA Diamond

    Graduate-level science questions

    • Gemini 3.1 Pro (Preview Custom Tools): 94.1%Top
    • Claude Sonnet 4.6 Thinking: 87.5%

  • IFBench

    Following precise output instructions

    • Gemini 3.1 Pro (Preview Custom Tools): 77.1%Top
    • Claude Sonnet 4.6 Thinking: 56.6%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Gemini 3.1 Pro (Preview Custom Tools): 4.0%Top
    • Claude Sonnet 4.6 Thinking: 3.0%

  • SciCode

    Scientific computing in Python

    • Gemini 3.1 Pro (Preview Custom Tools): 58.7%Top
    • Claude Sonnet 4.6 Thinking: 50.1%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Gemini 3.1 Pro (Preview Custom Tools): 53.8%Top
    • Claude Sonnet 4.6 Thinking: 53.0%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Gemini 3.1 Pro (Preview Custom Tools): 95.6%Top
    • Claude Sonnet 4.6 Thinking: 75.7%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Gemini 3.1 Pro (Preview Custom Tools): 82.0%Top
    • Claude Sonnet 4.6 Thinking: 80.0%

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": "google/gemini-3.1-pro-preview-customtools",
    "reasoning_effort": "medium",
    "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/gemini-3.1-pro-preview-customtools",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Google

Other Google models, starting with the same family.