NOUMENOpen app
NOUMEN

Google · Efficient

Gemini 3 Flash Thinking

Added Dec 17, 2025

Compare models

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

Loading models…

Use in the app

Google's Gemini 3 Flash preview model with thinking mode enabled for enhanced reasoning and chain-of-thought capabilities. Audio input costs $1.00 per million audio tokens.

  • Reasoning
  • Vision
  • Audio input
  • Video input
Input
Text, Images, Video, Audio
Output
Text
Reasoning effort
minimal · low · medium · high
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$0.50
Output
$3.00
Cache read
$0.05

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
65.5K
Average output (7 days)
1.7K tokens
Longer than 89% of 468 models

Side by side

Gemini 3 Flash 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…

Gemini 3 Flash ThinkingGoogleThis modelNvidia Nemotron 3.5 Super VLnvidiaRemove
ProviderGooglenvidia
Discovery tierEfficientOpen weights
AddedDec 17, 2025Oct 15, 2026
Limits
Context window1.05MBest262.14K
Max output65.54KBest16.38K
Average output1.7K tokens1.1K tokens
Pricing, USD per 1M tokens
Input$0.50$0.15Best
Output$3.00$0.50Best
Cache read$0.05$0.02Best
Performance
Throughput153.3 tok/s654.7 tok/sBest
Time to first token6.4 s1.8 sBest
Request success (24h)100.0%Best98.0%
Benchmark indexes
Intelligence Index26.326.5Best
Math Index97.0—
Capabilities
ReasoningYesYes
ToolsNoYes
VisionYesYes
Structured outputNoYes
Audio inputYesNo
Video inputYesYes
Reasoning effortminimal, low, medium, highnone, medium, high

Public evaluations

Benchmarks

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

  • Gemini 3 Flash Thinking
  • Nvidia Nemotron 3.5 Super VL

Intelligence Index

  • Gemini 3 Flash Thinking26.3
  • Nvidia Nemotron 3.5 Super VL26.5

Gemini 3 Flash Thinking: Better than 66% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • Gemini 3 Flash Thinking: 97.0
    • Nvidia Nemotron 3.5 Super VL: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Gemini 3 Flash Thinking: —
    • Nvidia Nemotron 3.5 Super VL: 14.8%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Gemini 3 Flash Thinking: —
    • Nvidia Nemotron 3.5 Super VL: 2.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Gemini 3 Flash Thinking: —
    • Nvidia Nemotron 3.5 Super VL: 999 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Gemini 3 Flash Thinking: —
    • Nvidia Nemotron 3.5 Super VL: 1,162 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Gemini 3 Flash Thinking: —
    • Nvidia Nemotron 3.5 Super VL: 8.0%

  • AA-LCRv1.1

    Reasoning across long documents

    • Gemini 3 Flash Thinking: 78.0%Top
    • Nvidia Nemotron 3.5 Super VL: 69.0%

  • MLCR-AA

    Long-context reasoning over medical records

    • Gemini 3 Flash Thinking: —
    • Nvidia Nemotron 3.5 Super VL: 13.3%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Gemini 3 Flash Thinking: 36.6%Top
    • Nvidia Nemotron 3.5 Super VL: 30.7%

  • GPQA Diamond

    Graduate-level science questions

    • Gemini 3 Flash Thinking: 89.8%
    • Nvidia Nemotron 3.5 Super VL: —

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Gemini 3 Flash Thinking: 89.0%
    • Nvidia Nemotron 3.5 Super VL: —

  • IFBench

    Following precise output instructions

    • Gemini 3 Flash Thinking: 78.0%
    • Nvidia Nemotron 3.5 Super VL: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Gemini 3 Flash Thinking: —
    • Nvidia Nemotron 3.5 Super VL: 0.0%

  • SciCode

    Scientific computing in Python

    • Gemini 3 Flash Thinking: —
    • Nvidia Nemotron 3.5 Super VL: 47.8%

  • LiveCodeBench

    Recent competitive programming problems

    • Gemini 3 Flash Thinking: 90.8%
    • Nvidia Nemotron 3.5 Super VL: —

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Gemini 3 Flash Thinking: 97.0%
    • Nvidia Nemotron 3.5 Super VL: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Gemini 3 Flash Thinking: 38.6%
    • Nvidia Nemotron 3.5 Super VL: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Gemini 3 Flash Thinking: 80.4%
    • Nvidia Nemotron 3.5 Super VL: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Gemini 3 Flash Thinking: 78.0%Top
    • Nvidia Nemotron 3.5 Super VL: 69.0%

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
153.3 tok/s
Faster than 76% of 254 models
Time to first token
6.4 s
Quicker than 27% of 254 models
Prompt cache hits
29.9%
About $0.37 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 80.0%
  • 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-3-flash-preview-thinking",
    "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-flash-preview-thinking",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Google

Other Google models, starting with the same family.