GPT-5.3 Codex (xhigh)
OpenAIGPTProprietary
Descripción
GPT-5.3-Codex is OpenAI's most capable coding model, combining frontier agentic coding capabilities, improvements in aesthetics, and context compaction. It sets new state-of-the-art results on Terminal-Bench 2.0 (77.3%), OSWorld-Verified (64.7%), and SWE-Lancer IC Diamond (81.4%). First model classified as High capability for cybersecurity under OpenAI's Preparedness Framework. Available in the Codex app and API.
Fecha de lanzamiento
2026-02-05
Parámetros
—
Longitud del contexto
400K
Modalidades
image, pdf, text
Radar de capacidades
35
general
70
coding
92
reasoning
76
science
80
agents
85
multimodal
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Ranking de codificación | 78 | 87.0 | AA |
| Ranking general | 61 | 71.0 | AA |
| Ranking multimodal | 110 | 41.0 | LS |
| Ciencia | 48 | 82.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Math
LiveBench
72.8%
Multimodal
OSWorld-Verified
64.7%Aut.
Reasoning
SWE-Lancer (IC-Diamond subset)
81.4%Aut.
Terminal-Bench 2.0Stanford × Laude Institute (2026)
77.3%Aut.
SWE-Bench ProPrinceton NLP (2024)
56.8%Aut.
Safety
Cybersecurity CTFs
77.6%Aut.
Índices de evaluación AA
(Artificial Analysis)Gpqa(NYU + Cohere + Anthropic (2023))91.5
Tau2(Sierra + U Toronto + Vector Institute (2025))86.0
Lcr(Artificial Analysis)83.3
Ifbench(Google Research (2023))75.4
Terminalbench Hard(Stanford × Laude Institute (2026))53.0
Hle(Center for AI Safety + Scale AI (2025))42.5
Intelligence Index(Artificial Analysis)32.5
Puntuaciones por categoría LLM Stats
(LLM Stats (zeroeval))Safety80
Tool Calling80
Math70
Reasoning70
General70
Agents70
Code70
Multimodal60
Vision60
Precios
Precio de entrada$1.75 / 1M tokens
Precio de salida$14 / 1M tokens
Precio mixto (3:1)$4.813 / 1M tokens
Precio de lectura caché$0.175 / 1M tokens
Velocidad
Tokens/seg113.8
Retraso del primer token35.09s
Tiempo hasta la respuesta35.09s
Ranking de Precios por Proveedor
Ranking de Precios por Proveedor
27 proveedores
Más barato: OpenAIMás caro: Opper
ProveedorEntradaSalida
1OpenAIMás barato
$0
$0.00001
2Ofox
$1.4
$11.2
3Poe
$1.6
$13
4NanoGPT
$1.75
$14
5Abacus
$1.75
$14
6OpenRouter
$1.75
$14
7ZenMux
$1.75
$14
8Vivgrid
$1.75
$14
9Kilo Gateway
$1.75
$14
10GitHub Copilot
$1.75
$14
11OpenCode Zen
$1.75
$14
12FrogBot
$1.75
$14
13AIHubMix
$1.75
$14
14Azure Cognitive Services
$1.75
$14
15Requesty
$1.75
$14
16Vercel AI Gateway
$1.75
$14
17DevPass (LLM Gateway)
$1.75
$14
18Azure
$1.75
$14
19FastRouter
$1.75
$14
20OrcaRouter
$1.75
$14
21FreeModel
$1.75
$14
22Neon
$1.75
$14
23Pioneer
$1.75
$14
24Impossibl
$1.75
$14
25Eden AI
$1.75
$14
26LLM Gateway
$1.75
$14
27Opper
$1.75
$14
Comparar precios entre diferentes proveedores de API para este modelo.