Claude Sonnet 5.5 vs. gpt-oss-120b: comparación de lanzamientos
Comparación de los lanzamientos Claude Sonnet 5.5 y gpt-oss-120b: 5 y 2 modelos respectivamente, cada uno con distintas características de inteligencia, rendimiento y precio. A continuación se comparan las métricas clave de los 7 modelos.
- En inteligencia, Claude Sonnet 5.5 obtiene la puntuación más alta: Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback), con 56, frente a gpt-oss-120b (high), con 12 de gpt-oss-120b.
- En costo por tarea, gpt-oss-120b es el más económico: gpt-oss-120b (high), con $0.11, frente a Claude Sonnet 5.5 (Adaptive Reasoning, Low Effort, Default Fallback), con $0.41 de Claude Sonnet 5.5.
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 | ||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback) |  Anthropic | 56 | 57 | 60 | 56 | - | 58 | 61 | $7.60 | 1,5 US$ | $2.00 | $10.00 | $0.20 | 8977 US$ | 193k | 142k | 411M | - | - | - | - | - | - | 1M | sept 2026 | - | Sí | Admite: texto e imágenes | Admite: texto | No disponible | - | | |
| Claude Sonnet 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback) | Anthropic | 52 | 52 | 56 | 52 | - | 54 | 56 | $2.74 | 1,5 US$ | $2.00 | $10.00 | $0.20 | 2738 US$ | 74k | 48k | 104M | - | - | - | - | - | - | 1M | sept 2026 | - | Sí | Admite: texto e imágenes | Admite: texto | No disponible | - | | |
| Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback) | Anthropic | 47 | 47 | 52 | 49 | - | 48 | 52 | $1.08 | 1,5 US$ | $2.00 | $10.00 | $0.20 | 1176 US$ | 34k | 18k | 50M | - | - | - | - | - | - | 1M | sept 2026 | - | Sí | Admite: texto e imágenes | Admite: texto | No disponible | - | | |
| Claude Sonnet 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback) | Anthropic | 41 | 41 | 45 | 44 | - | 42 | 47 | $0.59 | 1,5 US$ | $2.00 | $10.00 | $0.20 | 701 US$ | 19k | 8k | 29M | - | - | - | - | - | - | 1M | sept 2026 | - | Sí | Admite: texto e imágenes | Admite: texto | No disponible | - | | |
| Claude Sonnet 5.5 (Adaptive Reasoning, Low Effort, Default Fallback) | Anthropic | 36 | 37 | 41 | 40 | - | 38 | 44 | $0.41 | 1,5 US$ | $2.00 | $10.00 | $0.20 | 544 US$ | 14k | 5k | 23M | - | - | - | - | - | - | 1M | sept 2026 | - | Sí | Admite: texto e imágenes | Admite: texto | No disponible | - | | |
| gpt-oss-120b (high) |  OpenAI | 12 | 12 | 8 | 11 | 11 | 15 | 18 | $0.11 | 0,2 US$ | $0.15 | $0.595 | $0.125 | 122 US$ | 27k | 15k | 84M | 237 | 0.88s | 9.33s | 11.45s | 114.62s | 117B 5,1B activos en inferencia | 131k | ago 2025 | may 2024 | Sí | Admite: texto | Admite: texto |    +14 | |||
| gpt-oss-120b (low) | OpenAI | 10 | - | - | - | - | - | - | - | 0,2 US$ | $0.15 | $0.545 | $0.15 | - | - | - | - | 238 | 0.88s | 9.30s | 11.40s | - | 117B 5,1B activos en inferencia | 131k | ago 2025 | may 2025 | Sí | Admite: texto | Admite: texto |    +14 | |||