Modelos de Nous Research: inteligencia, rendimiento y precio
Hermes 4 70BHermes 4 405BHermes 4 405B (Non-reasoning)Hermes 4 70B (Non-reasoning)DeepHermes 3 - Mistral 24BÍndice de inteligencia de Artificial Analysis
* Estimado
Hermes 4 405BHermes 4 405B (Non-reasoning)Hermes 4 70B (Non-reasoning)Hermes 4 70BDeepHermes 3 - Mistral 24BVelocidad de salida
Hermes 4 70B (Non-reasoning)Hermes 4 70BHermes 4 405BDeepHermes 3 - Mistral 24BDeepHermes 3 - Llama-3.1 8BPor tarea del Índice de inteligencia
Artificial Analysis ha evaluado 7 modelos de Nous Research. A continuación se comparan las métricas clave de estos modelos.
- En inteligencia, el modelo líder de Nous Research es Hermes 4 - Llama-3.1 70B (Reasoning), con 8 (estimado).
- En velocidad de salida, el modelo más rápido es Hermes 4 - Llama-3.1 405B (Reasoning), con 43 tokens/s.
- En latencia, Hermes 4 - Llama-3.1 405B (Non-reasoning), con 2,31 s ofrece el menor tiempo hasta el primer token de respuesta.
Inteligencia
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Intelligence Index Task
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
Todos los lanzamientos de Nous Research
Más detalles
Pesos | Benchmarks de proveedores | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Hermes 4 - Llama-3.1 70B (Reasoning) | Nous Research | 8 | 70.6B | 128k | - | - | - | ||
| Hermes 4 - Llama-3.1 405B (Reasoning) | Nous Research | 7 | 406B | 128k | 1,2 US$ | 43 |  | ||
| Hermes 4 - Llama-3.1 405B (Non-reasoning) | Nous Research | 7 | 406B | 128k | 1,2 US$ | 43 | | ||
| Hermes 4 - Llama-3.1 70B (Non-reasoning) | Nous Research | 7 | 70.6B | 128k | - | - | - | ||
| DeepHermes 3 - Mistral 24B Preview (Non-reasoning) | Nous Research | 6 | 24B | 32k | - | - | - | ||
| Hermes 3 - Llama-3.1 70B | Nous Research | 6 | 70.6B | 128k | 0,7 US$ | 30 |  | ||
| DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning) | Nous Research | 5 | 8B | 128k | - | - | - |