NOUMENOpen app
NOUMEN

Google · Balanced

Gemini 2.5 Pro Experimental 0325

Added Mar 25, 2025

Compare models

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

Loading models…

Use in the app

Gemini 2.5 Pro Exp 0325. Google's experimental model from March 2025.

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

Pricing

USD per 1M tokens
Input
$2.50
Output
$10.00
Cache read
$0.25

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
65.5K

Side by side

Gemini 2.5 Pro Experimental 0325 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 Pro Experimental 0325GoogleThis modelGemma 4 12B Starry OceanGoogleRemove
ProviderGoogleGoogle
Discovery tierBalancedOpen weights
AddedMar 25, 2025Oct 15, 2026
Limits
Context window1.05MBest131.07K
Max output65.54K—
Pricing, USD per 1M tokens
Input$2.50$0.05Best
Output$10.00$0.25Best
Cache read$0.25$0.025Best
Performance
Request success (24h)—99.4%
Benchmark indexes
Intelligence Index16.1—
Coding Index33.3—
Math Index87.7—
Capabilities
ReasoningYesYes
ToolsNoYes
VisionYesYes
Audio inputYesNo
Reasoning effortlow, medium, highnone, high

Public evaluations

Benchmarks

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

  • Gemini 2.5 Pro Experimental 0325
  • Gemma 4 12B Starry Ocean

Intelligence Index

  • Gemini 2.5 Pro Experimental 032516.1
  • Gemma 4 12B Starry Ocean—

Gemini 2.5 Pro Experimental 0325: Better than 41% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Gemini 2.5 Pro Experimental 0325: 33.3
    • Gemma 4 12B Starry Ocean: —

  • Math Index

    Composite of the math evaluations

    • Gemini 2.5 Pro Experimental 0325: 87.7
    • Gemma 4 12B Starry Ocean: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Gemini 2.5 Pro Experimental 0325: 2.2%
    • Gemma 4 12B Starry Ocean: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Gemini 2.5 Pro Experimental 0325: 0.0%
    • Gemma 4 12B Starry Ocean: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Gemini 2.5 Pro Experimental 0325: 302 Elo
    • Gemma 4 12B Starry Ocean: —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Gemini 2.5 Pro Experimental 0325: 455 Elo
    • Gemma 4 12B Starry Ocean: —

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Gemini 2.5 Pro Experimental 0325: 10.2%
    • Gemma 4 12B Starry Ocean: —

  • AA-LCRv1.1

    Reasoning across long documents

    • Gemini 2.5 Pro Experimental 0325: 69.0%
    • Gemma 4 12B Starry Ocean: —

  • MLCR-AA

    Long-context reasoning over medical records

    • Gemini 2.5 Pro Experimental 0325: 12.2%
    • Gemma 4 12B Starry Ocean: —

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Gemini 2.5 Pro Experimental 0325: 22.5%
    • Gemma 4 12B Starry Ocean: —

  • GPQA Diamond

    Graduate-level science questions

    • Gemini 2.5 Pro Experimental 0325: 84.4%
    • Gemma 4 12B Starry Ocean: —

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Gemini 2.5 Pro Experimental 0325: 86.2%
    • Gemma 4 12B Starry Ocean: —

  • IFBench

    Following precise output instructions

    • Gemini 2.5 Pro Experimental 0325: 48.7%
    • Gemma 4 12B Starry Ocean: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Gemini 2.5 Pro Experimental 0325: 0.0%
    • Gemma 4 12B Starry Ocean: —

  • SciCode

    Scientific computing in Python

    • Gemini 2.5 Pro Experimental 0325: 46.3%
    • Gemma 4 12B Starry Ocean: —

  • LiveCodeBench

    Recent competitive programming problems

    • Gemini 2.5 Pro Experimental 0325: 80.1%
    • Gemma 4 12B Starry Ocean: —

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Gemini 2.5 Pro Experimental 0325: 87.7%
    • Gemma 4 12B Starry Ocean: —

  • AIME

    Competition mathematics

    • Gemini 2.5 Pro Experimental 0325: 88.7%
    • Gemma 4 12B Starry Ocean: —

  • MATH-500

    Competition math problems

    • Gemini 2.5 Pro Experimental 0325: 96.7%
    • Gemma 4 12B Starry Ocean: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Gemini 2.5 Pro Experimental 0325: 26.5%
    • Gemma 4 12B Starry Ocean: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Gemini 2.5 Pro Experimental 0325: 54.1%
    • Gemma 4 12B Starry Ocean: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Gemini 2.5 Pro Experimental 0325: 69.0%
    • Gemma 4 12B Starry Ocean: —

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

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-pro-exp-03-25",
    "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-pro-exp-03-25",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Google

Other Google models, starting with the same family.