Gemini 2.5 Pro
Multimodal
Zero-eval
#1MRCR
#1Video-MME
#1MRCR 1M (pointwise)
+4 more
by Google
+
+
+
+
About
Gemini 2.5 Pro was developed as Google's most intelligent AI model, designed to comprehend vast datasets and challenging problems from diverse information sources including text, audio, images, and video. Built to handle complex reasoning and multi-step problem solving, it represents Google's flagship offering for enterprise and advanced applications.
+
+
+
+
Pricing Range
Input (per 1M)$1.25 -$1.25
Output (per 1M)$10.00 -$10.00
Providers2
+
+
+
+
Timeline
AnnouncedMay 20, 2025
ReleasedMay 20, 2025
Knowledge CutoffJan 31, 2025
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown
Overall Performance
16 benchmarks
Average Score
69.6%
Best Score
93.0%
High Performers (80%+)
7Performance Metrics
Max Context Window
1.1MAvg Throughput
85.0 tok/sAvg Latency
1ms+
+
+
+
All Benchmark Results for Gemini 2.5 Pro
Complete list of benchmark scores with detailed information
| MRCR | text | 0.93 | 93.0% | Self-reported | |
| AIME 2024 | text | 0.92 | 92.0% | Self-reported | |
| Global-MMLU-Lite | text | 0.89 | 88.6% | Self-reported | |
| Video-MME | multimodal | 0.85 | 84.8% | Self-reported | |
| GPQA | text | 0.83 | 83.0% | Self-reported | |
| AIME 2025 | text | 0.83 | 83.0% | Self-reported | |
| MRCR 1M (pointwise) | text | 0.83 | 82.9% | Self-reported | |
| MMMU | multimodal | 0.80 | 79.6% | Self-reported | |
| Aider-Polyglot | text | 0.77 | 76.5% | Self-reported | |
| LiveCodeBench v5 | text | 0.76 | 75.6% | Self-reported |
Showing 1 to 10 of 16 benchmarks
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+