Sobre

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. The o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. Learn more in the [launch announcement](https://openai.com/o1).

Família do Modelo

OpenAI: o3 Deep Research2025-10-10 OpenAI: o4 Mini Deep Research2025-10-10 o3-pro2025-06-10 o32025-04-16 o4-mini (high)2025-04-16 OpenAI: o4 Mini High2025-04-16 o1-pro2025-03-19 o3-mini2025-01-31

Benchmarks

MMLU-Pro

84.1%

GPQA Diamond

74.7%

HLE

7.7%

LiveCodeBench

67.9%

SciCode

35.8%

TerminalBench Hard

12.9%

MATH-500

97.0%

AIME

72.3%

AIME 2025Não avaliado

IFBench

70.3%

Long Context Recall

59.3%

Tau2

62.6%

Média do MercadoMelhor Score

o1

Sobre

Família do Modelo

Posição no Mercado

Preços

Calculadora de Custo

vs. Modelos Similares

Desempenho

Benchmarks

Comparação Rápida

Modelos Similares