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
image, pdf, text
能力雷达图
8
general
32
coding
40
reasoning
35
science
50
agents
90
multimodal
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Biology
GPQANYU + Cohere + Anthropic (2023)
70.1%自报
Code
SWE-Bench Verified
33.2%自报
SWE-Lancer
32.6%自报
Aider-Polyglot
30.7%自报
Aider-Polyglot Edit
18.2%自报
SWE-Lancer (IC-Diamond subset)
12.4%自报
Communication
Tau2 Retail
63.4%自报
Multi-IF
60.9%自报
TAU-bench Retail
60.3%自报
Tau2 Airline
45.5%自报
TAU-bench Airline
42.8%自报
Multi-Challenge
40.3%自报
Tau2 Telecom
23.5%自报
Factuality
SimpleQA
38.2%自报
Finance
MMLU
85.7%自报
MMLU-Pro
74.7%自报
General
MMMLU
81.4%自报
IFEvalGoogle Research (2023)
81.0%自报
MMMU
72.2%自报
MMMU-Pro
59.9%自报
Internal API instruction following (hard)
29.2%自报
Healthcare
VideoMMMU
61.2%自报
Image To Text
DocVQADocVQA (2020)
92.8%自报
Language
COLLIE
61.0%自报
Long Context
EgoSchema
72.2%自报
ComplexFuncBench
66.5%自报
OpenAI-MRCR: 2 needle 128k
31.9%自报
Math
MathVista
61.4%自报
AIME 2024
13.1%自报
Humanity's Last Exam
5.3%自报
Multimodal
AI2D
94.2%自报
ChartQAMasry et al. (2022)
85.7%自报
CharXiv-D
85.3%自报
CharXiv-R
58.8%自报
Reasoning
Graphwalks BFS <128k
41.7%自报
Graphwalks parents <128k
35.4%自报
ERQA
35.2%自报
Video
ActivityNet
61.9%自报
AA 评测指数
(Artificial Analysis)Intelligence Index(Artificial Analysis)9.4
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))0.8
Gpqa(NYU + Cohere + Anthropic (2023))0.5
Lcr(Artificial Analysis)0.4
Ifbench(Google Research (2023))0.4
Scicode(UIUC + Argonne National Lab (2024))0.3
Livecodebench(UC Berkeley + MIT + Cornell (2024))0.3
Tau2(Sierra + U Toronto + Vector Institute (2025))0.3
Aime(MAA (Mathematical Association of America))0.1
Terminalbench Hard(Stanford × Laude Institute (2026))0.1
Hle(Center for AI Safety + Scale AI (2025))0.0
LLM Stats 分类评分
(LLM Stats (zeroeval))Image To Text90
Legal80
Finance80
Multimodal70
Physics70
Instruction Following70
Language70
Healthcare70
Biology70
Chemistry70
Vision70
Long Context60
Structured Output60
Writing60
Math50
Reasoning50
General50
Communication50
Tool Calling50
Spatial Reasoning40
Factuality40
Frontend Development30
Code30
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
缓存读取价格$1.25 / 1M tokens
速度
Tokens/秒0.0
首Token延迟0.00s
首回答延迟0.00s
供应商价格排行
供应商价格排行
2 个供应商
最便宜: OpenAI最贵: Azure
供应商输入输出
1OpenAI最便宜
$0
$0.00001
2Azure
$0
$0.00001
比较该模型在不同 API 供应商之间的定价。