53 modelos

Modelos de Anthropic: inteligencia, rendimiento y precio

Name: Artificial Analysis Intelligence Index
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

Anthropic

Inteligencia

Claude Opus 5.5 (max with fallback)

Claude Opus 5.5 (xhigh with fallback)

Claude Opus 5.5 (high with fallback)

Claude Fable 5.1 (max with fallback)

Claude Fable 5.1 (xhigh with fallback)

Índice de inteligencia de Artificial Analysis

Velocidad

Claude Opus 5.5 (max with fallback)

95 tokens/s

Claude Opus 5.5 (xhigh with fallback)

88 tokens/s

Claude 4.5 Haiku

82 tokens/s

Claude Opus 5.5 (medium with fallback)

82 tokens/s

Claude 4.5 Haiku (Non-reasoning)

81 tokens/s

Velocidad de salida

Costo

Claude 4.5 Haiku

$0.28

Claude Sonnet 5 (low)

$0.51

Claude Opus 5.5 (low with fallback)

$0.55

Claude Sonnet 5 (medium)

$1.00

Claude Opus 5.5 (medium with fallback)

$1.34

Por tarea del Índice de inteligencia

Artificial Analysis ha evaluado 53 modelos de Anthropic. A continuación se comparan las métricas clave de estos modelos.

En inteligencia, el modelo líder de Anthropic es Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback), con 58.
En velocidad de salida, el modelo más rápido es Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback), con 95 tokens/s.
En latencia, Claude 4.5 Haiku (Non-reasoning), con 0,68 s ofrece el menor tiempo hasta el primer token de respuesta.
En precio, Claude 4.5 Haiku (Reasoning), con $0.28 ofrece el menor costo por tarea. Los precios varían hasta 28 veces entre modelos.

Inteligencia

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Estimate (independent evaluation forthcoming)

Artificial Analysis Intelligence Index v4.3.2 includes: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Index vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task

Most attractive quadrant

Pareto line

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Costo

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better

Velocidad y latencia

Output Speed

Output tokens per second · Higher is better

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API or the median across providers where a first-party API is not available.

Puntuaciones de capacidades

Índices de capacidades

Mide el rendimiento de los modelos en capacidades e industrias específicas

Finance & Accounting Index

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

Strategy & Ops Index

Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Legal Index

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

Healthcare & Medical Index

Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better

Engineering Index

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

Economics Index

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 Anthropic

Más detalles

							Pesos		Benchmarks de proveedores
Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)	Anthropic	58	-	1M	2,9 US$	95	No disponible		Ver
Claude Opus 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback)	Anthropic	56	-	1M	2,9 US$	88	No disponible		Ver
Claude Opus 5.5 (Adaptive Reasoning, High Effort, Default Fallback)	Anthropic	54	-	1M	2,9 US$	81	No disponible		Ver
Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)	Anthropic	53	-	1M	7,2 US$	70	No disponible		Ver
Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)	Anthropic	53	-	1M	7,2 US$	66	No disponible		Ver
Claude Opus 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback)	Anthropic	51	-	1M	2,9 US$	82	No disponible		Ver
Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)	Anthropic	51	-	1M	7,2 US$	57	No disponible		Ver
Claude Opus 5 (Adaptive Reasoning, Max Effort)	Anthropic	51	-	1M	3,9 US$	60	No disponible		Ver
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)	Anthropic	50	-	1M	3,9 US$	59	No disponible		Ver
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)	Anthropic	50	-	1M	7,7 US$	64	No disponible		Ver
Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)	Anthropic	49	-	1M	7,2 US$	58	No disponible		Ver
Claude Opus 5 (Adaptive Reasoning, High Effort)	Anthropic	48	-	1M	3,9 US$	59	No disponible		Ver
Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)	Anthropic	47	-	1M	7,2 US$	58	No disponible		Ver
Claude Opus 5 (Adaptive Reasoning, Medium Effort)	Anthropic	45	-	1M	3,9 US$	62	No disponible		Ver
Claude Opus 5.5 (Adaptive Reasoning, Low Effort, Default Fallback)	Anthropic	42	-	1M	2,9 US$	79	No disponible		Ver
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)	Anthropic	42	-	1M	3,9 US$	52	No disponible		Ver
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)	Anthropic	41	-	1M	3,9 US$	52	No disponible		Ver
Claude Opus 5 (Adaptive Reasoning, Low Effort)	Anthropic	39	-	1M	3,9 US$	63	No disponible		Ver
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)	Anthropic	38	-	1M	1,5 US$	75	No disponible		Ver
Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)	Anthropic	34	-	1M	1,5 US$	69	No disponible		Ver
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)	Anthropic	32	-	1M	3,9 US$	39	No disponible		Ver
Claude Sonnet 5 (Adaptive Reasoning, High Effort)	Anthropic	32	-	1M	1,5 US$	65	No disponible		Ver
Claude Opus 4.7 (Non-reasoning, High Effort)	Anthropic	31	-	1M	3,9 US$	48	No disponible		Ver
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)	Anthropic	30	-	1M	2,3 US$	48	No disponible		Ver
Claude Opus 4.5 (Reasoning)	Anthropic	29	-	200k	3,9 US$	49	No disponible		Ver
Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)	Anthropic	28	-	1M	1,5 US$	63	No disponible		Ver
Claude Opus 4.6 (Non-reasoning, High Effort)	Anthropic	26	-	1M	3,9 US$	38	No disponible		Ver
Claude Sonnet 4.6 (Non-reasoning, High Effort)	Anthropic	25	-	1M	2,3 US$	42	No disponible		Ver
Claude Sonnet 5 (Adaptive Reasoning, Low Effort)	Anthropic	24	-	1M	1,5 US$	58	No disponible		Ver
Claude Opus 4.5 (Non-reasoning)	Anthropic	24	-	200k	3,9 US$	46	No disponible		Ver
Claude Sonnet 4.6 (Non-reasoning, Low Effort)	Anthropic	23	-	1M	2,3 US$	44	No disponible		Ver
Claude Sonnet 5 (Non-reasoning, High Effort)	Anthropic	23	-	1M	1,5 US$	66	No disponible		Ver
Claude 4.1 Opus (Reasoning)	Anthropic	23	-	200k	11,6 US$	-	No disponible		Ver
Claude 4.5 Sonnet (Reasoning)	Anthropic	21	-	1M	2,3 US$	40	No disponible		Ver
Claude 4 Opus (Reasoning)	Anthropic	21	-	200k	11,6 US$	-	No disponible		Ver
Claude 4.5 Sonnet (Non-reasoning)	Anthropic	19	-	1M	2,3 US$	39	No disponible		Ver
Claude 4 Sonnet (Reasoning)	Anthropic	19	-	1M	-	-	No disponible	-	Ver
Claude 4.1 Opus (Non-reasoning)	Anthropic	19	-	200k	11,6 US$	-	No disponible		Ver
Claude 3.7 Sonnet (Reasoning)	Anthropic	18	-	200k	-	-	No disponible	-	Ver
Claude 4.5 Haiku (Reasoning)	Anthropic	17	-	200k	0,8 US$	82	No disponible		Ver
Claude 4 Opus (Non-reasoning)	Anthropic	17	-	200k	11,6 US$	-	No disponible		Ver
Claude 4 Sonnet (Non-reasoning)	Anthropic	17	-	1M	-	-	No disponible	-	Ver
Claude 4.5 Haiku (Non-reasoning)	Anthropic	15	-	200k	0,8 US$	81	No disponible		Ver
Claude 3.7 Sonnet (Non-reasoning)	Anthropic	15	-	200k	2,3 US$	-	No disponible		Ver
Claude 3.5 Haiku	Anthropic	9	-	200k	-	-	No disponible	-	Ver
Claude 3 Opus	Anthropic	9	-	200k	11,6 US$	-	No disponible		Ver
Claude 3.5 Sonnet (Oct '24)	Anthropic	8	-	200k	2,3 US$	-	No disponible		Ver
Claude 3.5 Sonnet (June '24)	Anthropic	7	-	200k	2,3 US$	-	No disponible		Ver
Claude 3 Sonnet	Anthropic	6	-	200k	-	-	No disponible	-	Ver
Claude 2.1	Anthropic	6	-	200k	-	-	No disponible	-	Ver
Claude 3 Haiku	Anthropic	6	-	200k	0,4 US$	-	No disponible		Ver
Claude 2.0	Anthropic	6	-	100k	-	-	No disponible	-	Ver
Claude Instant	Anthropic	5	-	100k	-	-	No disponible	-	Ver

Modelos de Anthropic: inteligencia, rendimiento y precio

Inteligencia

Velocidad

Costo

Inteligencia

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Index vs. Cost per Intelligence Index Task

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

Costo

Cost per Intelligence Index Task

Cost per Intelligence Index Task

Velocidad y latencia

Output Speed

Output Speed

Model Performance Representation

Puntuaciones de capacidades

Índices de capacidades

Todos los lanzamientos de Anthropic

Más detalles