73.5
avg score
Rank #32
Better than 86% of all models
Context
1.0M tokens (~524 books)
Input $/1M
$1.25
Output $/1M
$10.00
Type
multimodal
License
Proprietary
Benchmarks
4 tested
Data updated today
About
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...
Tested on 4 benchmarks with 50.9% average. Top scores: Aider polyglot (83.1%), TutorBench (55.6%), VISTA (54.6%).
Looking for similar performance at lower cost?
gpt-oss-120b (free) scores 74.2 (101% as good) at $0.00/1M input · 100% cheaper
gpt-oss-120b (free) scores 74.2 (101% as good) at $0.00/1M input · 100% cheaper
Capabilities
coding
83.1
#3 globally
knowledge
55.1
#76 globally
agentic
10.1
#27 globally
Benchmark Scores
Compare AllTested on 4 benchmarks · Ranked across 3 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
codingCompare coding →
Aider polyglot
83.1—Multi-language code editing from Aider. Tests editing ability across Python, JavaScript, TypeScript, Java, C++, Go, Rust, and more.
knowledgeCompare knowledge →
TutorBench
55.6—SEAL TutorBench. Evaluates ability to explain concepts clearly for educational purposes.
agenticCompare agentic →
SWE-Bench Pro (Private)
10.1—SEAL SWE-bench Pro (Private). Harder private set of software engineering tasks.
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Research
Documentation
Community
BenchGecko API
gemini-2-5-pro-preview
Specifications
- Typemultimodal
- Context1.0M tokens (~524 books)
- ReleasedJun 2025
- LicenseProprietary
- Statuspreview
- Cost / Message~$0.013
Available On
Learn More
Share & Export
Frequently Asked Questions
Gemini 2.5 Pro Preview 06-05 is a proprietary multimodal AI model by Google DeepMind, released in June 2025. It has an average benchmark score of 73.5. Context window: 1M tokens.