Saltar al contenido principal
AITier

GPT-4o (Aug '24)

OpenAIGPTProprietary

Descripción

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.

Fecha de lanzamiento
2024-08-06
Parámetros
—
Longitud del contexto
128K
Modalidades
image, text

Radar de capacidades

7
general
32
coding
40
reasoning
37
science
50
agents
90
multimodal

Rankings

Dominio#PosiciónPuntuaciónFuente
Ranking de codificación432
31.0
AA
Ranking general579
20.0
AA
Ranking multimodal116
39.0
LS
Ciencia511
26.0
AA

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Chat

IFEvalGoogle Research (2023)81.0%Aut.
Multi-IF60.9%Aut.
TAU-bench Retail60.3%Aut.
Tau2 Airline45.5%Aut.
Multi-Challenge40.3%Aut.

Communication

Tau2 Retail63.4%Aut.
Tau2 Telecom23.5%Aut.

Factuality

SimpleQA38.2%Aut.

General

MMLU85.7%Aut.
Aider-Polyglot30.7%Aut.
Internal API instruction following (hard)29.2%Aut.
Aider-Polyglot Edit18.2%Aut.

Language

MMMLU81.4%Aut.
MMLU-Pro74.7%Aut.
COLLIE61.0%Aut.

Long Context

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

Math

MathVista61.4%Aut.
AIME 202413.1%Aut.

Multimodal

MMMU72.2%Aut.
VideoMMMU61.2%Aut.

Reasoning

ChartQAMasry et al. (2022)85.7%Aut.
CharXiv-D85.3%Aut.
GPQANYU + Cohere + Anthropic (2023)70.1%Aut.
CharXiv-R58.8%Aut.
TAU-bench Airline42.8%Aut.
Graphwalks BFS <128k41.7%Aut.
Graphwalks parents <128k35.4%Aut.
SWE-Bench Verified33.2%Aut.
SWE-Lancer32.6%Aut.
SWE-Lancer (IC-Diamond subset)12.4%Aut.
Humanity's Last Exam5.3%Aut.

Vision

AI2D94.2%Aut.
DocVQADocVQA (2020)92.8%Aut.
EgoSchema72.2%Aut.
ActivityNet61.9%Aut.
MMMU-Pro59.9%Aut.
ERQA35.2%Aut.

Índices de evaluación AA

(Artificial Analysis)
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
79.5
Gpqa(NYU + Cohere + Anthropic (2023))
52.1
Lcr(Artificial Analysis)
41.0
Ifbench(Google Research (2023))
36.0
Livecodebench(UC Berkeley + MIT + Cornell (2024))
31.7
Tau2(Sierra + U Toronto + Vector Institute (2025))
28.9
Aime(MAA (Mathematical Association of America))
11.7
Terminalbench Hard(Stanford × Laude Institute (2026))
8.3
Intelligence Index(Artificial Analysis)
7.7
Hle(Center for AI Safety + Scale AI (2025))
2.3

Puntuaciones por categoría LLM Stats

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

Precios

Precio de entrada$2.5 / 1M tokens
Precio de salida$10 / 1M tokens
Precio mixto (3:1)$4.375 / 1M tokens

Velocidad

Tokens/seg0.0
Retraso del primer token0.00s
Tiempo hasta la respuesta0.00s

Ranking de Precios por Proveedor

Ranking de Precios por Proveedor

2 proveedores

Más barato: OpenAIMás caro: Azure
ProveedorEntradaSalida
1OpenAIMás barato
$0
$0.00001
2Azure
$0
$0.00001

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas

LLM StatsArtificial Analysis