Gemini 2.5 Pro
Multimodal
Zero-eval
#1MRCR
#1Video-MME
#1MRCR 1M (pointwise)
+4 more
by Google
+
+
+
+
About
Gemini 2.5 Pro is a multimodal language model developed by Google. It achieves strong performance with an average score of 69.6% across 16 benchmarks. It excels particularly in MRCR (93.0%), AIME 2024 (92.0%), Global-MMLU-Lite (88.6%). With a 1.1M token context window, it can handle extensive documents and complex multi-turn conversations. The model is available through 2 API providers. As a multimodal model, it can process and understand text, images, and other input formats seamlessly. Released in 2025, it represents Google's latest advancement in AI technology.
+
+
+
+
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