o1-preview

OpenAI Released September 2024

OpenAI's advanced reasoning model trained with reinforcement learning

o1-preview

OpenAISeptember 2024

Training Data

Up to October 2023

o1-preview

September 2024

Parameters

~175 billion

Training Method

Reinforcement Learning

Context Window

128,000 tokens

Knowledge Cutoff

October 2023

Key Features

Chain of Thought • Advanced Reasoning • Problem Solving

Capabilities

Reasoning: Outstanding

Math: Excellent

Science: Excellent

What's New in This Version

Significant improvements in complex reasoning and problem-solving

OpenAI's advanced reasoning model trained with reinforcement learning

What's New in This Version

Significant improvements in complex reasoning and problem-solving

Technical Specifications

Parameters ~175 billion
Context Window 128,000 tokens
Training Method Reinforcement Learning
Knowledge Cutoff October 2023
Training Data Up to October 2023

Key Features

Chain of Thought Advanced Reasoning Problem Solving

Capabilities

Reasoning: Outstanding
Math: Excellent
Science: Excellent

Other OpenAI Models

Explore more models from OpenAI