← Models
Gemini 2.5 Pro
Google · proprietary · gemini-2.5-pro
A highly capable AI model from Google, designed for the agentic era. Gemini 2.5 Pro performs well on common benchmarks with enhanced reasoning, multimodal capabilities (text, image, video, audio input), and a 1M token context window.
Benchmark scores
| Benchmark | Score |
|---|---|
| MRCR | 0.93 |
| AIME 2024 | 0.92 |
| AIME 2025 | 0.83 |
| GPQA | 0.83 |
| MMMU | 0.80 |
| Aider-Polyglot | 0.77 |
| Aider-Polyglot Edit | 0.73 |
| SWE-Bench Verified | 0.63 |
| Humanity's Last Exam | 0.18 |
Pricing
- Google$1.25 / $10.00
- DeepInfra$1.25 / $10.00
Input / output per 1M tokens
AA metrics
No Artificial Analysis link yet.
Arena Elo
- No Arena snapshot linked.