GPT-5.6 Luna vs. K2-V2: comparación de lanzamientos
Comparación de los lanzamientos GPT-5.6 Luna y K2-V2: 6 y 3 modelos respectivamente, cada uno con distintas características de inteligencia, rendimiento y precio. A continuación se comparan las métricas clave de los 9 modelos.
- En inteligencia, GPT-5.6 Luna obtiene la puntuación más alta: GPT-5.6 Luna (max), con 37, frente a K2-V2 (high), con 10 de K2-V2.
Lanzamientos comparados
Inteligencia
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Intelligence Index Task
Cost per Task (USD, Log Scale)
Costo
Cost per Intelligence Index Task
Velocidad y latencia
Output Speed
Puntuaciones de capacidades
Índices de capacidades
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2.1, AA-Briefcase v1.1, Terminal-Bench 4.0 · Higher is better
Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2.1, AA-Briefcase v1.1, AA-LCR v1.1 · Higher is better
Más detalles
Modalidad de entrada | Modalidad de salida | Pesos | Benchmarks de proveedores | ||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5.6 Luna (max) |  OpenAI | 37 | 40 | 44 | 37 | 36 | 36 | 43 | $0.18 | 0,2 US$ | $0.20 | $1.20 | $0.02 | 320 US$ | 41k | 28k | 154M | 159 | 123.28s | 123.28s | 126.43s | 257.03s | - | 1M | jul 2026 | - | Sí | Admite: texto e imágenes | Admite: texto | No disponible | - |  | |
| GPT-5.6 Luna (xhigh) | OpenAI | 35 | 37 | 41 | 35 | 33 | 34 | 41 | $0.09 | 0,2 US$ | $0.20 | $1.20 | $0.02 | 179 US$ | 24k | 15k | 85M | 160 | 34.56s | 34.56s | 37.68s | 147.36s | - | 1M | jul 2026 | - | Sí | Admite: texto e imágenes | Admite: texto | No disponible | - |  | |
| GPT-5.6 Luna (high) | OpenAI | 32 | 34 | 37 | 33 | 30 | 32 | 38 | $0.04 | 0,2 US$ | $0.20 | $1.20 | $0.02 | 108 US$ | 14k | 7k | 50M | 140 | 9.68s | 9.68s | 13.24s | 96.87s | - | 1M | jul 2026 | - | Sí | Admite: texto e imágenes | Admite: texto | No disponible | - | | |
| GPT-5.6 Luna (medium) | OpenAI | 25 | 27 | 28 | 28 | 24 | 26 | 32 | $0.02 | 0,2 US$ | $0.20 | $1.20 | $0.02 | 44 US$ | 4k | 2k | 18M | 148 | 2.31s | 2.31s | 5.68s | 31.67s | - | 1M | jul 2026 | - | Sí | Admite: texto e imágenes | Admite: texto | No disponible | - | | |
| GPT-5.6 Luna (low) | OpenAI | 21 | 23 | 22 | 24 | 20 | 23 | 28 | $0.01 | 0,2 US$ | $0.20 | $1.20 | $0.02 | 27 US$ | 3k | 559 | 10M | 145 | 1.75s | 1.75s | 5.20s | 17.31s | - | 1M | jul 2026 | - | Sí | Admite: texto e imágenes | Admite: texto | No disponible | - | | |
| GPT-5.6 Luna (Non-reasoning) | OpenAI | 16 | 16 | 15 | 17 | - | 18 | 22 | $0.01 | 0,2 US$ | $0.20 | $1.20 | $0.02 | 23 US$ | 2k | 0 | 5M | 151 | 0.83s | 0.83s | 4.14s | 13.41s | - | 1M | jul 2026 | - | No | Admite: texto e imágenes | Admite: texto | No disponible | - | | |
| K2-V2 (high) |  Institute of Foundation Models | 10 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | 70B | 512k | dic 2025 | - | Sí | Admite: texto | Admite: texto | - | |||
| K2-V2 (medium) | Institute of Foundation Models | 9 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | 70B | 512k | dic 2025 | - | Sí | Admite: texto | Admite: texto | - | |||
| K2-V2 (low) | Institute of Foundation Models | 7 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | 70B | 512k | dic 2025 | - | Sí | Admite: texto | Admite: texto | - | |||