DeepSeek V4 Pro 0813 vs. Claude 4.5 Haiku: comparación de lanzamientos
Comparación de los lanzamientos DeepSeek V4 Pro 0813 y Claude 4.5 Haiku: 2 y 2 modelos respectivamente, cada uno con distintas características de inteligencia, rendimiento y precio. A continuación se comparan las métricas clave de los 4 modelos.
- En inteligencia, DeepSeek V4 Pro 0813 obtiene la puntuación más alta: DeepSeek V4 Pro 0813 (Reasoning, Max Effort), con 36, frente a Claude 4.5 Haiku (Reasoning), con 17 de Claude 4.5 Haiku.
- En velocidad de salida, DeepSeek V4 Pro 0813 es el más rápido: DeepSeek V4 Pro 0813 (Non-reasoning), con 211 tokens/s, frente a Claude 4.5 Haiku (Reasoning), con 89 tokens/s de Claude 4.5 Haiku.
- En costo por tarea, Claude 4.5 Haiku es el más económico: Claude 4.5 Haiku (Reasoning), con $0.28, frente a DeepSeek V4 Pro 0813 (Non-reasoning), con $0.48 de DeepSeek V4 Pro 0813.
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 | ||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro 0813 (Reasoning, Max Effort) |  DeepSeek | 36 | 41 | 46 | 41 | 38 | 37 | 44 | $0.67 | 0,7 US$ | $1.32 | $3.96 | $0.044 | 1122 US$ | 55k | 38k | 163M | 81 | 1.67s | 26.35s | 32.52s | 540.27s | 1.6T 49B activos en inferencia | 1M | ago 2026 | - | Sí | Admite: texto | Admite: texto |   +8 | |||
| DeepSeek V4 Pro 0813 (Non-reasoning) | DeepSeek | 20 | 26 | 32 | 27 | - | 22 | 26 | $0.48 | 0,7 US$ | $1.32 | $3.96 | $0.044 | 566 US$ | 29k | 0 | 40M | 211 | 2.18s | 2.18s | 4.54s | 137.84s | 1.6T 49B activos en inferencia | 1M | ago 2026 | - | No | Admite: texto | Admite: texto |   | |||
| Claude 4.5 Haiku (Reasoning) |  Anthropic | 17 | 15 | 10 | 19 | 16 | 19 | 26 | $0.28 | 0,8 US$ | $1.00 | $5.00 | $0.10 | 594 US$ | 18k | 8k | 78M | 89 | 14.79s | 14.79s | 20.39s | 167.98s | - | 200k | oct 2025 | jul 2025 | Sí | Admite: texto e imágenes | Admite: texto | No disponible | - |    | |
| Claude 4.5 Haiku (Non-reasoning) | Anthropic | 15 | - | - | - | - | - | - | - | 0,8 US$ | $1.00 | $5.00 | $0.10 | - | - | - | - | 83 | 0.67s | 0.67s | 6.69s | - | - | 200k | oct 2025 | jul 2025 | No | Admite: texto e imágenes | Admite: texto | No disponible | - | | |