Gemini 2.5 Pro
Active Parameters
Undisclosed
Context Length
2.1M
Modality
Multimodal
Architecture
Mixture of Experts (MoE)
License
Proprietary
Release Date
25 Sept 2025
Knowledge Cutoff
Jan 2025
API Pricing (per 1M)
Input: $1.25 · Output: $10.00
Evaluation Benchmarks
Rank
#108
| Benchmark | Score | Rank |
|---|---|---|
Software Engineering | 0.54 | 26 |
Graduate-Level QA | 0.864 | 36 |
General Text | 1446 | 59 |
Web Development | 1226 | 90 |
Agentic Index | 0.07 | 91 |
Coding Index | 0.33 | 109 |
Intelligence Index | 0.19 | 159 |
Coding Archived | 0.83 | 🥇 1 |
QA Assistant Archived | 0.975 | 🥉 3 |
Summarization Archived | 0.863 | 6 |
Rankings
Overall Rank
#108
Coding Rank
#93
About Gemini 2.5 Pro
Gemini 2.5 Pro is an advanced multimodal Mixture-of-Experts model from Google engineered for deep analytical reasoning and scientific inquiry. It features transparent chain-of-thought budgeting across a massive 2M token context window.
Technical Specifications
Architecture specifications are undisclosed for proprietary models.
About Gemini 2.5
Google's advanced multimodal models with native understanding of text, images, audio, and video. Features massive context windows up to 2.1M tokens, max thinking modes for complex reasoning, and optimized variants for different performance/cost tradeoffs. Includes Pro, Flash, and Flash Lite variants with configurable thinking capabilities for transparent reasoning.