NOUMENOpen app
NOUMEN

Google · Efficient

Gemini 2.5 Flash 0520 Thinking

Added May 20, 2025

Compare models

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

Loading models…

Use in the app

Deprecated. Mapped to Gemini 2.5 Flash because this model is deprecated

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

Pricing

USD per 1M tokens
Input
$0.15
Output
$3.50
Cache read
$0.015

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
65.5K

Side by side

Gemini 2.5 Flash 0520 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 2.5 Flash 0520 ThinkingGoogleThis modelGemini Flash LatestGoogleRemove
ProviderGoogleGoogle
Discovery tierEfficientEfficient
AddedMay 20, 2025Mar 29, 2026
Limits
Context window1.05M1.05MBest
Max output65.54K65.54K
Pricing, USD per 1M tokens
Input$0.15Best$0.75
Output$3.50Best$3.75
Cache read$0.015Best$0.075
Cache write—$0.0417
Performance
Throughput—194.9 tok/s
Time to first token—5.7 s
Request success (24h)99.3%99.9%Best
Benchmark indexes
Intelligence Index13.139.8Best
Coding Index—74.1
Math Index73.3—
Capabilities
ReasoningYesYes
ToolsNoYes
VisionYesYes
Structured outputNoYes
PDF inputNoYes
Audio inputNoYes
Video inputNoYes
Reasoning effortlow, medium, highminimal, low, medium, high

Public evaluations

Benchmarks

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

  • Gemini 2.5 Flash 0520 Thinking
  • Gemini Flash Latest

Intelligence Index

  • Gemini 2.5 Flash 0520 Thinking13.1
  • Gemini Flash Latest39.8

Gemini 2.5 Flash 0520 Thinking: Better than 32% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Gemini 2.5 Flash 0520 Thinking: —
    • Gemini Flash Latest: 74.1

  • Math Index

    Composite of the math evaluations

    • Gemini 2.5 Flash 0520 Thinking: 73.3
    • Gemini Flash Latest: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Gemini 2.5 Flash 0520 Thinking: —
    • Gemini Flash Latest: 60.9%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Gemini 2.5 Flash 0520 Thinking: —
    • Gemini Flash Latest: 31.1%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Gemini 2.5 Flash 0520 Thinking: —
    • Gemini Flash Latest: 1,181 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Gemini 2.5 Flash 0520 Thinking: —
    • Gemini Flash Latest: 1,423 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Gemini 2.5 Flash 0520 Thinking: —
    • Gemini Flash Latest: 22.8%

  • AA-LCRv1.1

    Reasoning across long documents

    • Gemini 2.5 Flash 0520 Thinking: 65.3%
    • Gemini Flash Latest: 84.0%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • Gemini 2.5 Flash 0520 Thinking: —
    • Gemini Flash Latest: 12.8%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Gemini 2.5 Flash 0520 Thinking: 12.1%
    • Gemini Flash Latest: 42.1%Top

  • GPQA Diamond

    Graduate-level science questions

    • Gemini 2.5 Flash 0520 Thinking: 79.0%
    • Gemini Flash Latest: 93.5%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Gemini 2.5 Flash 0520 Thinking: 83.2%
    • Gemini Flash Latest: —

  • IFBench

    Following precise output instructions

    • Gemini 2.5 Flash 0520 Thinking: 50.3%
    • Gemini Flash Latest: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Gemini 2.5 Flash 0520 Thinking: —
    • Gemini Flash Latest: 19.7%

  • SciCode

    Scientific computing in Python

    • Gemini 2.5 Flash 0520 Thinking: —
    • Gemini Flash Latest: 55.1%

  • LiveCodeBench

    Recent competitive programming problems

    • Gemini 2.5 Flash 0520 Thinking: 69.5%
    • Gemini Flash Latest: —

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Gemini 2.5 Flash 0520 Thinking: 73.3%
    • Gemini Flash Latest: —

  • AIME

    Competition mathematics

    • Gemini 2.5 Flash 0520 Thinking: 82.3%
    • Gemini Flash Latest: —

  • MATH-500

    Competition math problems

    • Gemini 2.5 Flash 0520 Thinking: 98.1%
    • Gemini Flash Latest: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Gemini 2.5 Flash 0520 Thinking: 13.6%
    • Gemini Flash Latest: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Gemini 2.5 Flash 0520 Thinking: 31.6%
    • Gemini Flash Latest: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Gemini 2.5 Flash 0520 Thinking: 65.3%
    • Gemini Flash Latest: 84.0%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.

Request success (24h)
99.3%
Reliable
Hourly request success · last 72 hoursLowest hour 99.0%
  • 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": "gemini-2.5-flash-preview-05-20: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="gemini-2.5-flash-preview-05-20:thinking",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Google

Other Google models, starting with the same family.