o3

OpenAI

O3 is a cutting-edge research model designed for superior reasoning and problem-solving, especially in math, coding, and science. It excels at complex reasoning challenges, maintains robust general skills, and shows improved performance when tackling problems that require multiple steps.

Model Specifications

Technical details and capabilities of o3

Core Specifications

128.0K / 4.1K

Input / Output tokens

November 30, 2023

Knowledge cutoff date

December 19, 2024

Release date

Capabilities & License

Multimodal Support
Not Supported
Web Hydrated
No
License
Proprietary

Resources

API Reference
https://platform.openai.com/docs/models

Performance Insights

Check out how o3 handles various AI tasks through comprehensive benchmark results.

100
75
50
25
0
96.7
AIME 2024
96.7
(97%)
88
ARC-AGI
88
(88%)
87.7
GPQA
87.7
(88%)
68
Codeforces
68
(68%)
25.2
Frontier Math
25.2
(25%)
AIME 2024
ARC-AGI
GPQA
Codeforces
Frontier Math

Detailed Benchmarks

Dive deeper into o3's performance across specific task categories. Expand each section to see detailed metrics and comparisons.

Math

AIME 2024

Current model
Other models
Avg (89.3%)

Coding

Codeforces

90.0%
79.0%
68.0%
47.0%
41.3%
11.0%
Current model
Other models
Avg (57.0%)

Knowledge

GPQA

Current model
Other models
Avg (82.8%)

Providers Pricing Coming Soon

We're working on gathering comprehensive pricing data from all major providers for o3. Compare costs across platforms to find the best pricing for your use case.

OpenAI
Anthropic
Google
Mistral AI
Cohere

Share your feedback

Hi, I'm Charlie Palars, the founder of Deepranking.ai. I'm always looking for ways to improve the site and make it more useful for you. You can write me through this form or directly through X at @palarsio.

Your feedback helps us improve our service

Stay Ahead with AI Updates

Get insights on Gemini Pro 2.5, Sonnet 3.7 and more top AI models