Saltar al contenido principal

GPT-5.6 Luna (max)

OpenAIGPTProprietary

Descripción

GPT-5.6 Luna is the fastest and most cost-efficient tier of OpenAI's GPT-5.6 family, designed for cost-sensitive, high-volume workloads. It brings strong capability at OpenAI's lowest GPT-5.6 price, supports max reasoning effort, and has a 1.05M-token context window.

Fecha de lanzamiento
2026-07-09
Parámetros
Longitud del contexto
1.1M
Modalidades
image, pdf, text

Radar de capacidades

50
general
68
coding
91
reasoning
67
science
70
agents
85
multimodal

Rankings

Dominio#PosiciónPuntuaciónFuente
Capacidad agéntica50
52.0
LS
Ranking de codificación20
92.0
AA
Ranking general34
83.0
AA
Ranking multimodal70
43.0
LS
Ciencia38
85.0
AA

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

Connectors99.9%Aut.
Search and Function-Calling89.7%Aut.
Capture-the-Flag Challenges (Internal)85.2%Aut.
Toolathlon53.4%Aut.
LifeSciBench51.2%Aut.
Internal Research Debugging Evaluation50.8%Aut.
Agents' Last Exam50.3%Aut.
SEC-bench Pro48.9%Aut.
RSI Index41.9%Aut.
Big Finance Bench36.0%Aut.
Management Consulting Tasks (Internal)35.4%Aut.
PostTrainBench Lite29.6%Aut.
KernelGen 1P22.4%Aut.
AutomationBench14.9%Aut.
ExploitGym12.4%Aut.
GeneBench-Pro10.8%Aut.
NanoGPT1.7%Aut.

Code

BenchCAD (with Python tool)73.9%Aut.
DeepSWE67.2%Aut.
DeepSWE 1.167.0%
BenchCAD63.1%Aut.
ExploitBench33.2%Aut.

General

Artificial Analysis51.0%
GDP.pdf22.7%Aut.

Healthcare

HealthBench Consensus95.1%Aut.
HealthBench55.8%Aut.
HealthBench Professional55.7%Aut.
HealthBench Hard32.0%Aut.

Long Context

MRCR v2 (8-needle, 512K-1M)41.3%Aut.
MRCR v2 (8-needle)41.3%Aut.

Math

FrontierMath78.6%Aut.
FrontierMath Tier 4 (v2)58.5%Aut.

Multimodal

OSWorld 2.045.6%Aut.

Reasoning

GPQANYU + Cohere + Anthropic (2023)92.3%Aut.
Terminal-Bench 2.184.7%Aut.
BrowseCompOpenAI (2025)83.3%Aut.
Graphwalks BFS >128k81.3%Aut.
SWE-Bench ProPrinceton NLP (2024)62.7%Aut.
Graphwalks BFS 1M51.2%Aut.
FrontierCode 1.139.8%
MedChemBench (Internal)30.4%Aut.
ARC-AGI-30.2%Aut.

Vision

MMMU-Pro (with tools)79.5%Aut.
MMMU-Pro78.4%Aut.

Índices de evaluación AA

(Artificial Analysis)
Coding Index(Artificial Analysis)
71.4
Intelligence Index(Artificial Analysis)
52.3
Gpqa(NYU + Cohere + Anthropic (2023))
0.9
Terminalbench V2 1
0.8
Lcr(Artificial Analysis)
0.8
Scicode(UIUC + Argonne National Lab (2024))
0.5
Hle(Center for AI Safety + Scale AI (2025))
0.4
Tau Banking
0.3

Puntuaciones por categoría LLM Stats

(LLM Stats (zeroeval))
Physics
90
Biology
90
Chemistry
90
Search
80
Math
70
Spatial Reasoning
70
Tool Calling
70
Multimodal
60
Vision
60
Long Context
50
Reasoning
50
General
50
Healthcare
50
Agents
50
Code
50
Safety
40
Finance
40
Science
30
Systems
20

Precios

Precio de entrada$0.2 / 1M tokens
Precio de salida$1.2 / 1M tokens
Precio mixto (3:1)$0.45 / 1M tokens
Precio de lectura caché$0.02 / 1M tokens
Precio de escritura caché$0.25 / 1M tokens

Velocidad

Tokens/seg132.4
Retraso del primer token86.96s
Tiempo hasta la respuesta86.96s

Ranking de Precios por Proveedor

Ranking de Precios por Proveedor

2 proveedores

Más barato: OpenAIMás caro: Neon
ProveedorEntradaSalida
1OpenAIMás barato
$0
$0
2Neon
$1
$6

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas