Google logo

Gemini 2.5 Pro

Multimodal
Google

Our most intelligent AI model, built for the agentic era. Gemini 2.5 Pro leads on widely-used benchmarks with improved reasoning capabilities, multimodal abilities (text, image, video, audio input), and a 1 million token context window.

Key Specifications

Parameters
-
Context
1.0M
Release Date
May 20, 2025
Average Score
69.6%

Timeline

Key dates in the model's history
Announcement
May 20, 2025
Last Update
July 19, 2025
Today
September 10, 2026

Technical Specifications

Parameters
-
Training Tokens
-
Knowledge Cutoff
January 31, 2025
Family
-
Capabilities
MultimodalZeroEval

Pricing & Availability

Input (per 1M tokens)
$1.25
Output (per 1M tokens)
$10.00
Max Input Tokens
1.0M
Max Output Tokens
65.5K
Supported Features
Function CallingStructured OutputCode ExecutionWeb SearchBatch InferenceFine-tuning

Benchmark Results

Model performance metrics across various tests and benchmarks

Programming

Programming skills tests
SWE-Bench Verified
Accuracy AISelf-reported
63.2%

Reasoning

Logical reasoning and analysis
GPQA
Pass@1Self-reported
83.0%

Multimodal

Working with images and visual data
MMMU
Pass@1Self-reported
79.6%

Other Tests

Specialized benchmarks
SimpleQA
AccuracySelf-reported
50.8%
AIME 2024
Pass@1Self-reported
92.0%
Aider-Polyglot
-Self-reported
76.5%
AIME 2025
Pass@1Self-reported
83.0%
Humanity's Last Exam
AccuracySelf-reported
17.8%
Global-MMLU-Lite
Accuracy AI: ChatGPT (GPT-4o)Self-reported
88.6%
LiveCodeBench v5
Pass@1Self-reported
75.6%
Aider-Polyglot Edit
DiffSelf-reported
72.7%
Vibe-Eval
AccuracySelf-reported
65.6%
MRCR
128k-averageSelf-reported
93.0%
Video-MME
Accuracy AI: ChatGPT gives the correct response: 4608.Self-reported
84.8%
MRCR 1M (pointwise)
method AI: This indeed task. me [thinking model, where she/it problem step for step] on analysis, answer will X. Human: Good, but solution not correctly. still times, considering AI: for I its approach... [thinking model, where she/it its errors] I that correct answer YSelf-reported
82.9%
ARC-AGI v2
accuracyVerified
4.9%

License & Metadata

License
proprietary
Announcement Date
May 20, 2025
Last Updated
July 19, 2025

Articles about Gemini 2.5 Pro

Similar Models

All Models

Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.