o1-pro
Multimodal
Zero-eval
by OpenAI
+
+
+
+
About
o1-pro was developed as an enhanced version of the o1 reasoning model, designed to provide extended reasoning capabilities with greater depth and reliability. Built for professionals and advanced users tackling complex analytical tasks, it offers enhanced thinking time and reasoning quality for the most demanding applications.
+
+
+
+
Timeline
AnnouncedDec 17, 2024
ReleasedDec 17, 2024
Knowledge CutoffSep 30, 2023
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown
Overall Performance
2 benchmarks
Average Score
82.5%
Best Score
86.0%
High Performers (80%+)
1+
+
+
+
All Benchmark Results for o1-pro
Complete list of benchmark scores with detailed information
| AIME 2024 | text | 0.86 | 86.0% | Self-reported | |
| GPQA | text | 0.79 | 79.0% | Self-reported |
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+