Hermes 4 - Llama-3.1 70B vs. gpt-oss-20b: comparación de lanzamientos
Comparación de los lanzamientos Hermes 4 - Llama-3.1 70B y gpt-oss-20b: 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, gpt-oss-20b obtiene la puntuación más alta: gpt-oss-20b (low), con 10, frente a Hermes 4 - Llama-3.1 70B (Reasoning), con 8 de Hermes 4 - Llama-3.1 70B.
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-oss-20b (low) |  OpenAI | 10 | - | - | - | - | - | - | - | 0,1 US$ | $0.07 | $0.20 | - | - | - | - | - | 216 | 0.93s | 10.18s | 12.49s | - | 21B 3,6B activos en inferencia | 131k | ago 2025 | may 2025 | Sí | Admite: texto | Admite: texto |    +5 | |||
| gpt-oss-20b (high) | OpenAI | 9 | 7 | 5 | 7 | 7 | 12 | 11 | $0.01 | 0,1 US$ | $0.06 | $0.19 | - | 29 US$ | 18k | 16k | 70M | 170 | 0.83s | 12.57s | 15.51s | 102.10s | 21B 3,6B activos en inferencia | 131k | ago 2025 | may 2024 | Sí | Admite: texto | Admite: texto |    +6 | |||
| Hermes 4 - Llama-3.1 70B (Reasoning) |  Nous Research | 8 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | 70.6B | 128k | ago 2025 | - | Sí | Admite: texto | Admite: texto | - | |||
| Hermes 4 - Llama-3.1 70B (Non-reasoning) | Nous Research | 7 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | 70.6B | 128k | ago 2025 | - | No | Admite: texto | Admite: texto | - | |||