o1-pro
Multimodal
Zero-eval
by OpenAI
About
o1-pro is a multimodal language model developed by OpenAI. This model demonstrates exceptional performance with an average score of 82.5% across 2 benchmarks. It excels particularly in AIME 2024 (86.0%), GPQA (79.0%). The model shows particular specialization in general tasks with an average performance of 82.5%. As a multimodal model, it can process and understand text, images, and other input formats seamlessly. Released in 2024, it represents OpenAI's latest advancement in AI technology.
Timeline
AnnouncedDec 17, 2024
ReleasedDec 17, 2024
Knowledge CutoffSep 30, 2023
Specifications
Capabilities
Multimodal
License & Family
License
Proprietary
Benchmark Performance Overview
Performance metrics and category breakdown
Overall Performance
2 benchmarks
Average Score
82.5%
Best Score
86.0%
High Performers (80%+)
1Top Categories
general
82.5%
Benchmark Performance
Top benchmark scores with normalized values (0-100%)
Ranking Across Benchmarks
Position relative to other models on each benchmark
AIME 2024
Rank #11 of 41
#8DeepSeek R1 Zero
86.7%
#9DeepSeek R1 Distill Llama 70B
86.7%
#10o3-mini
87.3%
#11o1-pro
86.0%
#12Qwen3 235B A22B
85.7%
#13DeepSeek R1 Distill Qwen 7B
83.3%
#14DeepSeek R1 Distill Qwen 32B
83.3%
GPQA
Rank #15 of 115
#12Claude Opus 4
79.6%
#13DeepSeek-R1-0528
81.0%
#14o4-mini
81.4%
#15o1-pro
79.0%
#16o1
78.0%
#17Qwen3-235B-A22B-Instruct-2507
77.5%
#18o3-mini
77.2%
All Benchmark Results for o1-pro
Complete list of benchmark scores with detailed information
AIME 2024 AIME 2024 benchmark | general | text | 0.86 | 86.0% | Self-reported |
GPQA GPQA benchmark | general | text | 0.79 | 79.0% | Self-reported |