跳转到主要内容
AITier

GPT-4o (Aug '24)

OpenAIGPTProprietary

描述

GPT-4o ('o' for 'omni') is a multimodal AI model that accepts text, audio, image, and video inputs, and generates text, audio, and image outputs. It matches GPT-4 Turbo performance on text and code, with improvements in non-English languages, vision, and audio understanding.

发布日期
2024-08-06
参数规模
—
上下文长度
128K
支持模态
file, image, text

能力雷达图

15
general
24
coding
40
reasoning
36
science估算
50
agents
90
multimodal

Science 在缺少专门科学评测时使用推理能力代理估算。

排行榜排名

领域#排名分数来源
代码能力榜265
30.0
AA
通用能力榜377
28.0
AA
数学推理196
46.0
AA
多模态榜27
81.0
LS
推理能力94
37.0
LS
科学能力290
37.0
AA

基准测试分数 (LLM Stats)

Biology

GPQA70.1%自报

Code

SWE-Bench Verified33.2%自报
SWE-Lancer32.6%自报
Aider-Polyglot30.7%自报
Aider-Polyglot Edit18.2%自报
SWE-Lancer (IC-Diamond subset)12.4%自报

Communication

Tau2 Retail63.4%自报
Multi-IF60.9%自报
TAU-bench Retail60.3%自报
Tau2 Airline45.5%自报
TAU-bench Airline42.8%自报
Multi-Challenge40.3%自报
Tau2 Telecom23.5%自报

Factuality

SimpleQA38.2%自报

Finance

MMLU85.7%自报
MMLU-Pro74.7%自报

General

MMMLU81.4%自报
IFEval81.0%自报
MMMU72.2%自报
MMMU-Pro59.9%自报
Internal API instruction following (hard)29.2%自报

Healthcare

VideoMMMU61.2%自报

Image To Text

DocVQA92.8%自报

Language

COLLIE61.0%自报

Long Context

EgoSchema72.2%自报
ComplexFuncBench66.5%自报
OpenAI-MRCR: 2 needle 128k31.9%自报

Math

MathVista61.4%自报
AIME 202413.1%自报
Humanity's Last Exam5.3%自报

Multimodal

AI2D94.2%自报
ChartQA85.7%自报
CharXiv-D85.3%自报
CharXiv-R58.8%自报

Reasoning

Graphwalks BFS <128k41.7%自报
Graphwalks parents <128k35.4%自报
ERQA35.2%自报

Video

ActivityNet61.9%自报

AA 评测指数

Intelligence Index
18.6
Coding Index
16.6
Math 500
0.8
Gpqa
0.5
Ifbench
0.4
Lcr
0.3
Scicode
0.3
Livecodebench
0.3
Tau2
0.3
Aime
0.1
Terminalbench Hard
0.1
Hle
0.0

LLM Stats 分类评分

Image To Text
90
Finance
80
Legal
80
Vision
70
Biology
70
Chemistry
70
Healthcare
70
Instruction Following
70
Language
70
Multimodal
70
Physics
70
Structured Output
60
Writing
60
General
60
Long Context
60
Tool Calling
50
Communication
50
Math
50
Reasoning
50
Spatial Reasoning
40
Factuality
40
Code
30
Frontend Development
30

定价

输入价格$2.5 / 1M tokens
输出价格$10 / 1M tokens
混合价格(3:1)$4.375 / 1M tokens

速度

Tokens/秒102.1 tokens/s
首Token延迟0.65s
首回答延迟0.65s

可用提供商

(LS 内部计价单位)
提供商输入价格输出价格
OpenAI2.5M10.0M
Azure2.5M10.0M

外部链接

LLM Stats