NOUMENOpen app
NOUMEN

Google · Frontier

Gemini Pro Latest

Added Mar 29, 2026

Compare models

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

Loading models…

Use in the app

Compatibility alias that routes to the newest version of Gemini Pro. Currently routes to Gemini 3.1 Pro Preview High.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • Audio input
  • Video input
Input
Text, Images, Video, Audio
Output
Text
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

Side by side

Gemini Pro Latest 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 Pro LatestGoogleThis modelGemini 3.1 Pro (Preview)GoogleRemove
ProviderGoogleGoogle
Discovery tierFrontierFrontier
AddedMar 29, 2026Feb 19, 2026
Limits
Context window1.05M1.05M
Max output65.54K65.54K
Average output—699 tokens
Pricing, USD per 1M tokens
Input$2.00$2.00
Output$12.00$12.00
Cache read$0.20$0.20
Cache write$0.38$0.38
Performance
Throughput36.1 tok/s68.0 tok/sBest
Time to first token8.7 s4.7 sBest
Request success (24h)100.0%Best99.8%
Benchmark indexes
Intelligence Index29.729.7
Coding Index68.868.8
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
Audio inputYesYes
Video inputYesYes
Reasoning effort—low, medium, high

Public evaluations

Benchmarks

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

  • Gemini Pro Latest
  • Gemini 3.1 Pro (Preview)

Intelligence Index

  • Gemini Pro Latest29.7
  • Gemini 3.1 Pro (Preview)29.7

Gemini Pro Latest: Better than 71% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Gemini Pro Latest: 68.8Top
    • Gemini 3.1 Pro (Preview): 68.8Top

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Gemini Pro Latest: 35.4%Top
    • Gemini 3.1 Pro (Preview): 35.4%Top

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Gemini Pro Latest: 9.4%Top
    • Gemini 3.1 Pro (Preview): 9.4%Top

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • Gemini Pro Latest: 0.0%Top
    • Gemini 3.1 Pro (Preview): 0.0%Top

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Gemini Pro Latest: 456 EloTop
    • Gemini 3.1 Pro (Preview): 456 EloTop

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Gemini Pro Latest: 791 EloTop
    • Gemini 3.1 Pro (Preview): 791 EloTop

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Gemini Pro Latest: 17.8%Top
    • Gemini 3.1 Pro (Preview): 17.8%Top

  • AA-LCRv1.1

    Reasoning across long documents

    • Gemini Pro Latest: 82.0%Top
    • Gemini 3.1 Pro (Preview): 82.0%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • Gemini Pro Latest: 11.1%Top
    • Gemini 3.1 Pro (Preview): 11.1%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Gemini Pro Latest: 47.0%Top
    • Gemini 3.1 Pro (Preview): 47.0%Top

  • GPQA Diamond

    Graduate-level science questions

    • Gemini Pro Latest: 94.1%Top
    • Gemini 3.1 Pro (Preview): 94.1%Top

  • IFBench

    Following precise output instructions

    • Gemini Pro Latest: 77.1%Top
    • Gemini 3.1 Pro (Preview): 77.1%Top

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Gemini Pro Latest: 4.0%Top
    • Gemini 3.1 Pro (Preview): 4.0%Top

  • SciCode

    Scientific computing in Python

    • Gemini Pro Latest: 58.7%Top
    • Gemini 3.1 Pro (Preview): 58.7%Top

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Gemini Pro Latest: 53.8%Top
    • Gemini 3.1 Pro (Preview): 53.8%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Gemini Pro Latest: 95.6%Top
    • Gemini 3.1 Pro (Preview): 95.6%Top

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Gemini Pro Latest: 82.0%Top
    • Gemini 3.1 Pro (Preview): 82.0%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.

Throughput
36.1 tok/s
Faster than 26% of 250 models
Time to first token
8.7 s
Quicker than 13% of 250 models
Prompt cache hits
66.4%
About $0.81 per 1M input tokens with caching
Request success (24h)
100.0%
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 100.0%
  • 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/gemini-pro-latest",
    "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-pro-latest",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Google

Other Google models, starting with the same family.