NOUMENOpen app
NOUMEN

Google · Efficient

Gemini 3.5 Flash

Added May 19, 2026

Compare models

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

Loading models…

Use in the app

Google's speed-focused Gemini Flash model for frontier multimodal intelligence across text, images, audio, video, PDFs, and code. Built for agentic coding, reliable tool use, structured outputs, and long-context workflows. Audio input costs $3.00 per million audio tokens.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • 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
$1.50
Output
$9.00
Cache read
$0.15
Cache write
$0.0833

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
65.5K
Average output (7 days)
322 tokens
Longer than 35% of 465 models

Side by side

Gemini 3.5 Flash 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 3.5 FlashGoogleThis modelClaude 4.6 Opus ThinkingAnthropicRemove
ProviderGoogleAnthropic
Discovery tierEfficientFrontier
AddedMay 19, 2026Feb 5, 2026
Limits
Context window1.05MBest1M
Max output65.54K128KBest
Average output322 tokens1.4K tokens
Pricing, USD per 1M tokens
Input$1.50Best$5.00
Output$9.00Best$25.00
Cache read$0.15Best$0.50
Cache write$0.0833—
Performance
Throughput264.0 tok/sBest77.0 tok/s
Time to first token4.8 s1.9 sBest
Request success (24h)98.1%100.0%Best
Benchmark indexes
Intelligence Index32.6Best31.9
Coding Index70.1—
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputNoYes
Audio inputYesNo
Video inputYesNo
Reasoning effortminimal, low, 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 3.5 Flash
  • Claude 4.6 Opus Thinking

Intelligence Index

  • Gemini 3.5 Flash32.6
  • Claude 4.6 Opus Thinking31.9

Gemini 3.5 Flash tested at high reasoning effort

Gemini 3.5 Flash: Better than 76% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Gemini 3.5 Flash: 70.1
    • Claude 4.6 Opus Thinking: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Gemini 3.5 Flash: 42.1%
    • Claude 4.6 Opus Thinking: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Gemini 3.5 Flash: 13.5%
    • Claude 4.6 Opus Thinking: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Gemini 3.5 Flash: 874 Elo
    • Claude 4.6 Opus Thinking: —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Gemini 3.5 Flash: 1,202 Elo
    • Claude 4.6 Opus Thinking: —

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Gemini 3.5 Flash: 19.8%
    • Claude 4.6 Opus Thinking: —

  • AA-LCRv1.1

    Reasoning across long documents

    • Gemini 3.5 Flash: 73.3%
    • Claude 4.6 Opus Thinking: 78.0%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • Gemini 3.5 Flash: 10.0%
    • Claude 4.6 Opus Thinking: —

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Gemini 3.5 Flash: 42.7%Top
    • Claude 4.6 Opus Thinking: 39.9%

  • GPQA Diamond

    Graduate-level science questions

    • Gemini 3.5 Flash: 92.2%Top
    • Claude 4.6 Opus Thinking: 89.6%

  • IFBench

    Following precise output instructions

    • Gemini 3.5 Flash: 76.3%Top
    • Claude 4.6 Opus Thinking: 53.1%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Gemini 3.5 Flash: 6.6%
    • Claude 4.6 Opus Thinking: —

  • SciCode

    Scientific computing in Python

    • Gemini 3.5 Flash: 53.9%
    • Claude 4.6 Opus Thinking: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Gemini 3.5 Flash: 40.9%
    • Claude 4.6 Opus Thinking: 46.2%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Gemini 3.5 Flash: 95.3%Top
    • Claude 4.6 Opus Thinking: 92.1%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Gemini 3.5 Flash: 73.3%
    • Claude 4.6 Opus Thinking: 78.0%Top

Scores from Artificial Analysis, updated Oct 26, 2026. Gemini 3.5 Flash was tested at high reasoning effort; compare scores measured at the same effort.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
264.0 tok/s
Faster than 91% of 250 models
Time to first token
4.8 s
Quicker than 36% of 250 models
Prompt cache hits
14.4%
About $1.31 per 1M input tokens with caching
Request success (24h)
98.1%
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 70.0%
  • 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-3.5-flash",
    "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-3.5-flash",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Google

Other Google models, starting with the same family.