GPT-6 Luna vs. Mistral Small 4: comparación de lanzamientos
Comparación de los lanzamientos GPT-6 Luna y Mistral Small 4: 6 y 2 modelos respectivamente, cada uno con distintas características de inteligencia, rendimiento y precio. A continuación se comparan las métricas clave de los 8 modelos.
- En inteligencia, GPT-6 Luna obtiene la puntuación más alta: GPT-6 Luna (max), con 37, frente a Mistral Small 4 (Reasoning), con 11 de Mistral Small 4.
- En velocidad de salida, Mistral Small 4 es el más rápido: Mistral Small 4 (Reasoning), con 166 tokens/s, frente a GPT-6 Luna (max), con 157 tokens/s de GPT-6 Luna.
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-6 Luna (max) |  OpenAI | 37 | 39 | 45 | 39 | - | 37 | 45 | - | 0,1 US$ | $0.10 | $0.50 | $0.01 | - | 51k | 39k | 145M | 157 | 152.68s | 152.68s | 155.86s | 318.47s | - | 1M | sept 2026 | - | Sí | Admite: texto e imágenes | Admite: texto | No disponible | - | | |
| GPT-6 Luna (xhigh) | OpenAI | 34 | 37 | 42 | 37 | - | 33 | 41 | - | 0,1 US$ | $0.10 | $0.50 | $0.01 | - | 27k | 19k | 68M | 153 | 28.52s | 28.52s | 31.80s | 208.46s | - | 1M | sept 2026 | - | Sí | Admite: texto e imágenes | Admite: texto | No disponible | - | | |
| GPT-6 Luna (high) | OpenAI | 32 | 36 | 41 | 35 | - | 32 | 40 | - | 0,1 US$ | $0.10 | $0.50 | $0.01 | - | 20k | 13k | 47M | 127 | 6.69s | 6.69s | 10.62s | 153.17s | - | 1M | sept 2026 | - | Sí | Admite: texto e imágenes | Admite: texto | No disponible | - | | |
| GPT-6 Luna (medium) | OpenAI | 29 | 32 | 37 | 33 | - | 29 | 37 | - | 0,1 US$ | $0.10 | $0.50 | $0.01 | - | 11k | 6k | 28M | 143 | 5.28s | 5.28s | 8.78s | 79.51s | - | 1M | sept 2026 | - | Sí | Admite: texto e imágenes | Admite: texto | No disponible | - | | |
| GPT-6 Luna (low) | OpenAI | 21 | 24 | 22 | 25 | - | 23 | 30 | - | 0,1 US$ | $0.10 | $0.50 | $0.01 | - | 2k | 515 | 8M | 152 | 1.59s | 1.59s | 4.89s | 13.89s | - | 1M | sept 2026 | - | Sí | Admite: texto e imágenes | Admite: texto | No disponible | - | | |
| GPT-6 Luna (Non-reasoning) | OpenAI | 18 | 20 | 20 | 19 | - | 21 | 24 | - | 0,1 US$ | $0.10 | $0.50 | $0.01 | - | 4k | 0 | 7M | 131 | 0.74s | 0.74s | 4.57s | 28.01s | - | 1M | sept 2026 | - | No | Admite: texto e imágenes | Admite: texto | No disponible | - | | |
| Mistral Small 4 (Reasoning) |  Mistral | 11 | 10 | 7 | 13 | - | 16 | 18 | $0.05 | 0,2 US$ | $0.15 | $0.60 | - | 79 US$ | 14k | 9k | 54M | 166 | 0.73s | 12.80s | 15.82s | 93.03s | 119B 6,5B activos en inferencia | 256k | mar 2026 | - | Sí | Admite: texto e imágenes | Admite: texto | | |||
| Mistral Small 4 (Non-reasoning) | Mistral | 9 | - | - | - | - | - | - | - | 0,2 US$ | $0.15 | $0.60 | - | - | - | - | - | 151 | 0.73s | 0.73s | 4.04s | - | 119B 6,5B activos en inferencia | 256k | mar 2026 | - | No | Admite: texto e imágenes | Admite: texto | | |||