NOUMENOpen app
NOUMEN

Google · Balanced

Gemini 2.0 Pro Reasoner

Added Jan 1, 2024

Compare models

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

Loading models…

Use in the app

Note: This model is now being routed to Gemini 2.5 Pro because Google no longer has the Gemini 2.0 Pro model available and Gemini 2.5 Pro is an across the board improvement. 'DeepGemini', fusion of Gemini 2.5 Pro and Deepseek R1.

  • Audio input
Input
Text, Audio
Output
Text
Discovery tier
Balanced

Pricing

USD per 1M tokens
Input
$1.29
Output
$5.00
Cache read
$0.32

Reference prices as published by the model provider. API example

Specifications

Context window
128K
Max output
65.5K

Side by side

Compare models

Put Gemini 2.0 Pro Reasoner 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 V3.2Step 3.5 FlashQwen3 MaxAll 3

Public evaluations

Benchmarks

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

Intelligence Index

16.1

Better than 41% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    33.3

    Composite of the coding evaluations

    Better than 25% of 168 scored models

  • Math Index

    87.7

    Composite of the math evaluations

    Better than 79% of 118 scored models

Agentic work

  • AutomationBench-AA

    2.2%

    Workflow automation, penalized for guardrail violations

    Better than 14% of 173 scored models

  • AutomationBench-AA tasks completed

    0.0%

    Workflows finished end to end without a guardrail violation

    Better than 0% of 173 scored models

  • AA-Briefcasev1.1

    302 Elo

    Agentic knowledge work, rated head to head

    Better than 6% of 166 scored models

  • GDPval-AAv2.1

    455 Elo

    Economically valuable occupational tasks, rated head to head

    Better than 8% of 187 scored models

Document reasoning

  • GDP.pdf

    10.2%

    Professional reasoning over PDF documents, all-pass rate

    Better than 39% of 171 scored models

  • AA-LCRv1.1

    69.0%

    Reasoning across long documents

    Better than 45% of 309 scored models

  • MLCR-AA

    12.2%

    Long-context reasoning over medical records

    Better than 47% of 121 scored models

Reasoning and knowledge

  • Humanity’s Last Exam

    22.5%

    Expert-level questions across academic fields

    Better than 50% of 323 scored models

  • GPQA Diamond

    84.4%

    Graduate-level science questions

    Better than 57% of 291 scored models

  • MMLU-Pro

    86.2%

    Multi-subject knowledge and reasoning

    Better than 92% of 132 scored models

  • IFBench

    48.7%

    Following precise output instructions

    Better than 45% of 215 scored models

Coding

  • Terminal-Benchv4.0

    0.0%

    Practical software engineering in a terminal

    Better than 0% of 171 scored models

  • SciCode

    46.3%

    Scientific computing in Python

    Better than 35% of 174 scored models

  • LiveCodeBench

    80.1%

    Recent competitive programming problems

    Better than 83% of 129 scored models

Math

  • AIME 2025

    87.7%

    Competition mathematics, 2025 problems

    Better than 79% of 118 scored models

  • AIME

    88.7%

    Competition mathematics

    Better than 86% of 72 scored models

  • MATH-500

    96.7%

    Competition math problems

    Better than 68% of 73 scored models

Legacy evaluations

  • Terminal-Bench Hard

    26.5%

    Earlier terminal task suite

    Better than 49% of 212 scored models

  • τ²-Bench Telecom

    54.1%

    Tool use in a customer-support simulation

    Better than 41% of 214 scored models

  • AA-LCR (unversioned)

    69.0%

    Long-context reasoning, earlier grading

    Better than 45% 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.

Prompt cache hits
80.1%
About $0.52 per 1M input tokens with caching

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.

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-2.0-pro-reasoner",
    "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-2.0-pro-reasoner",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Google

Other Google models, starting with the same family.