NOUMENOpen app
NOUMEN

Google · Efficient

Gemini 2.5 Flash 0520 Thinking

Added May 20, 2025

Compare models

Choose up to 3 models to compare.0 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

Compare models

Put Gemini 2.5 Flash 0520 Thinking next to up to three other models. The comparison stays in the link, so you can share it.

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

TryDeepSeek R1 0528GPT 5 NanoNvidia Nemotron 3.5 Lightning TEEAll 3

Public evaluations

Benchmarks

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

Intelligence Index

13.1

Better than 32% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    73.3

    Composite of the math evaluations

    Better than 67% of 118 scored models

Document reasoning

  • AA-LCRv1.1

    65.3%

    Reasoning across long documents

    Better than 41% of 309 scored models

Reasoning and knowledge

  • Humanity’s Last Exam

    12.1%

    Expert-level questions across academic fields

    Better than 38% of 323 scored models

  • GPQA Diamond

    79.0%

    Graduate-level science questions

    Better than 45% of 291 scored models

  • MMLU-Pro

    83.2%

    Multi-subject knowledge and reasoning

    Better than 71% of 132 scored models

  • IFBench

    50.3%

    Following precise output instructions

    Better than 50% of 215 scored models

Coding

  • LiveCodeBench

    69.5%

    Recent competitive programming problems

    Better than 68% of 129 scored models

Math

  • AIME 2025

    73.3%

    Competition mathematics, 2025 problems

    Better than 67% of 118 scored models

  • AIME

    82.3%

    Competition mathematics

    Better than 79% of 72 scored models

  • MATH-500

    98.1%

    Competition math problems

    Better than 91% of 73 scored models

Legacy evaluations

  • Terminal-Bench Hard

    13.6%

    Earlier terminal task suite

    Better than 28% of 212 scored models

  • τ²-Bench Telecom

    31.6%

    Tool use in a customer-support simulation

    Better than 23% of 214 scored models

  • AA-LCR (unversioned)

    65.3%

    Long-context reasoning, earlier grading

    Better than 41% of 309 scored models

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.