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, pdf, text
Radar de capacidades
8
general
32
coding
40
reasoning
36
scienceest.
50
agents
90
multimodal
Science usa un proxy de razonamiento cuando los benchmarks científicos dedicados no están disponibles.
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Ranking de codificación | 287 | 31.0 | AA |
| Ranking general | 425 | 23.0 | AA |
| Razonamiento matemático | 196 | 46.0 | AA |
| Ranking multimodal | 30 | 81.0 | LS |
| Razonamiento | 99 | 37.0 | LS |
| Ciencia | 315 | 36.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
Biology
GPQA
70.1%Aut.
Code
SWE-Bench Verified
33.2%Aut.
SWE-Lancer
32.6%Aut.
Aider-Polyglot
30.7%Aut.
Aider-Polyglot Edit
18.2%Aut.
SWE-Lancer (IC-Diamond subset)
12.4%Aut.
Communication
Tau2 Retail
63.4%Aut.
Multi-IF
60.9%Aut.
TAU-bench Retail
60.3%Aut.
Tau2 Airline
45.5%Aut.
TAU-bench Airline
42.8%Aut.
Multi-Challenge
40.3%Aut.
Tau2 Telecom
23.5%Aut.
Factuality
SimpleQA
38.2%Aut.
Finance
MMLU
85.7%Aut.
MMLU-Pro
74.7%Aut.
General
MMMLU
81.4%Aut.
IFEval
81.0%Aut.
MMMU
72.2%Aut.
MMMU-Pro
59.9%Aut.
Internal API instruction following (hard)
29.2%Aut.
Healthcare
VideoMMMU
61.2%Aut.
Image To Text
DocVQA
92.8%Aut.
Language
COLLIE
61.0%Aut.
Long Context
EgoSchema
72.2%Aut.
ComplexFuncBench
66.5%Aut.
OpenAI-MRCR: 2 needle 128k
31.9%Aut.
Math
MathVista
61.4%Aut.
AIME 2024
13.1%Aut.
Humanity's Last Exam
5.3%Aut.
Multimodal
AI2D
94.2%Aut.
ChartQA
85.7%Aut.
CharXiv-D
85.3%Aut.
CharXiv-R
58.8%Aut.
Reasoning
Graphwalks BFS <128k
41.7%Aut.
Graphwalks parents <128k
35.4%Aut.
ERQA
35.2%Aut.
Video
ActivityNet
61.9%Aut.
Índices de evaluación AA
Intelligence Index9.6
Math 5000.8
Gpqa0.5
Ifbench0.4
Lcr0.3
Scicode0.3
Livecodebench0.3
Tau20.3
Aime0.1
Terminalbench Hard0.1
Hle0.0
Puntuaciones por categoría LLM Stats
Image To Text90
Legal80
Finance80
Instruction Following70
Language70
Multimodal70
Physics70
Healthcare70
Biology70
Chemistry70
Vision70
Long Context60
Structured Output60
General60
Writing60
Math50
Reasoning50
Communication50
Tool Calling50
Spatial Reasoning40
Factuality40
Frontend Development30
Code30
Precios
Precio de entrada$2.5 / 1M tokens
Precio de salida$10 / 1M tokens
Precio mixto (3:1)$4.375 / 1M tokens
Precio de lectura caché$1.25 / 1M tokens
Velocidad
Tokens/seg113.3
Retraso del primer token0.56s
Tiempo hasta la respuesta0.56s
Ranking de Precios por Proveedor
Ranking de Precios por Proveedor
12 proveedores
Más barato: OpenAIMás caro: Venice AI
ProveedorEntradaSalida
1OpenAIMás barato
$0
$0.00001
2Azure
$0
$0.00001
3NanoGPT
$2.499
$9.996
4Abacus
$2.5
$10
5OpenRouter
$2.5
$10
6Kilo Gateway
$2.5
$10
7Cloudflare AI Gateway
$2.5
$10
8DigitalOcean
$2.5
$10
9Vercel AI Gateway
$2.5
$10
10OrcaRouter
$2.5
$10
11Merge Gateway
$2.5
$10
12Venice AI
$3.125
$12.5
Comparar precios entre diferentes proveedores de API para este modelo.