GPT-5.4 mini (Non-Reasoning)
OpenAIGPTProprietary
Descripción
GPT-5.4 mini is OpenAI's strongest mini model yet for coding, computer use, and subagents. It brings many of the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads, with strong coding, reasoning, multimodal understanding, and tool use.
Fecha de lanzamiento
2026-03-17
Parámetros
—
Longitud del contexto
400K
Modalidades
image, text
Radar de capacidades
10
general
60
coding
61
reasoning
44
science
60
agents
85
multimodal
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Capacidad agéntica | 69 | 44.0 | LS |
| Ranking de codificación | 399 | 35.0 | AA |
| Ranking general | 549 | 23.0 | AA |
| Razonamiento matemático | 53 | 78.0 | LB |
| Ranking multimodal | 96 | 47.0 | LS |
| Razonamiento | 52 | 71.0 | LB |
| Ciencia | 431 | 34.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Agents
Finance Agent v2
45.4%
Toolathlon
42.9%Aut.
Communication
Tau2 Telecom
93.4%Aut.
Legal
Legal Agent Benchmark
0.0%
Long Context
MRCR v2 (8-needle)
33.6%Aut.
Multimodal
OSWorld-Verified
72.1%Aut.
Reasoning
GPQANYU + Cohere + Anthropic (2023)
88.0%Aut.
Graphwalks BFS <128k
76.3%Aut.
Graphwalks parents <128k
71.5%Aut.
Terminal-Bench 2.0Stanford × Laude Institute (2026)
60.0%Aut.
MCP Atlas
57.7%Aut.
SWE-Bench ProPrinceton NLP (2024)
54.4%Aut.
Humanity's Last Exam
28.2%Aut.
Vision
OmniDocBench 1.5
87.4%Aut.
MMMU-Pro
76.6%Aut.
Índices de evaluación AA
(Artificial Analysis)Gpqa(NYU + Cohere + Anthropic (2023))60.6
Ifbench(Google Research (2023))38.8
Lcr(Artificial Analysis)37.0
Tau2(Sierra + U Toronto + Vector Institute (2025))23.4
Terminalbench Hard(Stanford × Laude Institute (2026))18.2
Intelligence Index(Artificial Analysis)11.1
Hle(Center for AI Safety + Scale AI (2025))5.9
Puntuaciones por categoría LLM Stats
(LLM Stats (zeroeval))Physics90
Structured Output90
Biology90
Chemistry90
Communication90
Multimodal80
Spatial Reasoning70
Vision70
Code60
Tool Calling60
Reasoning50
Finance50
General50
Agents50
Math30
Long Context20
Healthcare20
Legal0
Precios
Precio de entrada$0.75 / 1M tokens
Precio de salida$4.5 / 1M tokens
Precio mixto (3:1)$1.688 / 1M tokens
Precio de lectura caché$0.075 / 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
15 proveedores
Más barato: OpenAIMás caro: Opper
ProveedorEntradaSalida
1OpenAIMás barato
$0
$0
2Xpersona
$0.375
$4
3302.AI
$0.75
$4.5
4Abacus
$0.75
$4.5
5Vivgrid
$0.75
$4.5
6GitHub Copilot
$0.75
$4.5
7OpenCode Zen
$0.75
$4.5
8AIHubMix
$0.75
$4.5
9Azure Cognitive Services
$0.75
$4.5
10Requesty
$0.75
$4.5
11DevPass (LLM Gateway)
$0.75
$4.5
12Azure
$0.75
$4.5
13FreeModel
$0.75
$4.5
14Pioneer
$0.75
$4.5
15Opper
$0.75
$4.5
Comparar precios entre diferentes proveedores de API para este modelo.