GPT-5.4 (xhigh)
OpenAIGPT
Descripción
GPT-5.4 is OpenAI's most capable and efficient frontier model for professional work. It combines industry-leading coding capabilities with native computer-use, up to 1M tokens of context, full-resolution vision processing, tool search for large tool ecosystems, and improved reasoning across spreadsheets, presentations, and documents. It is the most token-efficient reasoning model in the GPT-5 series.
Fecha de lanzamiento
2026-03-05
Parámetros
—
Longitud del contexto
1.1M
Modalidades
image, pdf, text
Radar de capacidades
49
general
69
coding
92
reasoning
70
scienceest.
70
agents
85
multimodal
Science usa un proxy de razonamiento cuando los benchmarks científicos dedicados no están disponibles.
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Capacidad agéntica | 43 | 58.0 | LS |
| Ranking de codificación | 6 | 94.0 | AA |
| Ranking general | 7 | 87.0 | AA |
| Ranking multimodal | 12 | 89.0 | LS |
| Razonamiento | 15 | 87.0 | LS |
| Ciencia | 6 | 90.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
Agents
GDPval-AA
1429.00 / 3000Aut.
BrowseComp
82.7%Aut.
Terminal-Bench 2.0
75.1%Aut.
OSWorld-Verified
75.0%Aut.
MCP Atlas
67.2%Aut.
SWE-Bench Pro
57.7%Aut.
Finance Agent
56.0%Aut.
Toolathlon
54.6%Aut.
FrontierSWE
54.0%Aut.
Legal Agent Benchmark
0.4%Aut.
Biology
GPQA
92.8%Aut.
Communication
Tau2 Telecom
98.9%Aut.
General
MMMU-Pro
81.2%Aut.
LiveBench
80.3%Aut.
Long Context
Graphwalks parents >128k
32.4%Aut.
Graphwalks BFS >128k
21.4%Aut.
Math
FrontierMath
47.6%Aut.
Humanity's Last Exam
39.8%Aut.
Multimodal
OmniDocBench 1.5
89.1%Aut.
Reasoning
ARC-AGI
93.7%Aut.
Graphwalks BFS <128k
93.0%Aut.
Graphwalks parents <128k
89.8%Aut.
ARC-AGI v2
73.3%Aut.
Índices de evaluación AA
Coding Index71.1
Intelligence Index51.4
Gpqa0.9
Tau20.9
Terminalbench V2 10.8
Lcr0.7
Ifbench0.7
Terminalbench Hard0.6
Scicode0.6
Hle0.4
Tau Banking0.3
Puntuaciones por categoría LLM Stats
Finance100
Legal100
General100
Agents100
Reasoning63
Communication100
Physics90
Structured Output90
Biology90
Chemistry90
Multimodal80
Search80
Vision80
Spatial Reasoning70
Tool Calling70
Math60
Code60
Long Context40
Healthcare30
Precios
Precio de entrada$2.5 / 1M tokens
Precio de salida$15 / 1M tokens
Precio mixto (3:1)$5.625 / 1M tokens
Precio de lectura caché$0.25 / 1M tokens
Velocidad
Tokens/seg169.1
Retraso del primer token111.73s
Tiempo hasta la respuesta111.73s
Ranking de Precios por Proveedor
Ranking de Precios por Proveedor
13 proveedores
Más barato: OpenAIMás caro: Cortecs
ProveedorEntradaSalida
1OpenAIPRINCIPAL
$2.5
$15
2302.AI
$2.5
$15
3Abacus
$2.5
$15
4Vivgrid
$2.5
$15
5SAP AI Core
$2.5
$15
6GitHub Copilot
$2.5
$15
7OpenCode Zen
$2.5
$15
8AIHubMix
$2.5
$15
9Azure Cognitive Services
$2.5
$15
10LLM Gateway
$2.5
$15
11Azure
$2.5
$15
12FreeModel
$2.5
$15
13Cortecs
$3
$16.13
Comparar precios entre diferentes proveedores de API para este modelo.