o1

OpenAIProprietaryVerified

The o1 model series is trained with large-scale reinforcement learning to reason using chain-of-thought. OpenAI o1 is the next model in this series (previously OpenAI o1-preview), with advanced reasoning capabilities that provide new avenues for improving safety and robustness. The model can reason about safety policies in context when responding to potentially unsafe prompts, through deliberative alignment.

2024-09-12

Decoder-only Transformer

Proprietary

Compare with other models

Specifications

Architecture: Decoder-only Transformer
License: Proprietary
Context Window: 200,000 tokens
Max Output: 100,000 tokens
Training Data Cutoff: Sep 30, 2023
Type: multimodal
Modalities: textimage

Benchmark Scores

Codeforces1,673

Evaluates models on competitive programming problems from the Codeforces platform....

AIME-202483.3

American Invitational Mathematics Examination (AIME) 2024 problems....

MMLU92.3

Massive Multitask Language Understanding (MMLU) tests knowledge across 57 subjects including mathema...

MMMU78.2

Massive Multi-discipline Multimodal Understanding (MMMU) evaluates multimodal understanding across 3...

GPQA78

Graduate-level Problems in Quantitative Analysis (GPQA) evaluates advanced reasoning on graduate-lev...

MATH94.8

A dataset of 12,500 challenging competition mathematics problems requiring multi-step reasoning....

MathVista73.9

Evaluates mathematical reasoning in visual contexts, combining vision and mathematical problem-solvi...

See all benchmarks

Advanced Specifications

Model Family: o-series
API Access: Available
Chat Interface: Available
Multilingual Support: Yes

Capabilities & Limitations

Capabilities: reasoningcodemathsciencechain-of-thoughtdeliberative alignment
Known Limitations: potential risks from heightened intelligence
Notable Use Cases: complex reasoningscientific problem solvingadvanced mathematicscomplex coding taskssafety-critical applications
Function Calling Support: No
Tool Use Support: No

Related Models

Claude Opus 4

Anthropic

Claude Opus 4 is Anthropic's most powerful model and the best coding model in the world, leading on SWE-bench (72.5%) and Terminal-bench (43.2%). It delivers sustained performance on long-running tasks that require focused effort and thousands of steps, with the ability to work continuously for several hours. Features include extended thinking with tool use, parallel tool execution, improved memory capabilities, and significantly reduced shortcut behaviors.

Claude Sonnet 4

Anthropic

Claude Sonnet 4 significantly improves on Sonnet 3.7's capabilities, excelling in coding with a state-of-the-art 72.7% on SWE-bench. The model balances performance and efficiency, with enhanced steerability for greater control over implementations. Features include extended thinking with tool use, parallel tool execution, improved instruction following, and significantly reduced shortcut behaviors.

o3

OpenAI

OpenAI's most powerful reasoning model that pushes the frontier across coding, math, science, visual perception, and more. Sets new state-of-the-art on benchmarks including Codeforces, SWE-bench, and MMMU. Features full tool access and can agentically use and combine every tool within ChatGPT.