AIbase
EN
Home
AI Models Finder
O3
O

O3

OpenAI 最强大的推理模型。o3 是一个在各个领域都表现均衡且强大的模型。它为数学、科学、编程和视觉推理任务设定了新标准。它在技术写作和遵循指令方面也表现出色。可用于解决涉及文本、代码和图像分析的多步骤问题。
Intelligence(Relatively Strong)
Speed(Relatively Fast)
Input Supported Modalities
Yes
Is Reasoning Model
200,000
Context Window
100,000
Maximum Output Tokens
2024-05-31
Knowledge Cutoff
Go Compare

Pricing

￥14.4 /M tokens
Input
￥57.6 /M tokens
Output
￥25.2 /M tokens
Blended Price

Quick Simple Comparison

Input

Output

GPT-5‑pro
GPT-4.1 nano
￥0.1
GPT-4.1
￥2

Basic Parameters

o3Technical Parameters
Parameter Count
Not Announced
Context Length
200.00k tokens
Training Data Cutoff
2024-05-31
Open Source Category
Proprietary
Multimodal Support
Text, Image
Throughput
50
Release Date
2025-04-16
Response Speed
170.97,778 tokens/s

Benchmark Scores

Below is the performance of o3 in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
69.97
Large Language Model Intelligence Level
Coding Index
59.69
Indicator of AI model performance on coding tasks
Math Index
94.77
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
85.3
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
82.7
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
20
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
78.4
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
41
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
99.1
Score achieved by the AI model on the specific HumanEval benchmark test set
Math 500 Score
99.2
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
90.3
An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase