Claude Haiku 5.5 vs. Claude Sonnet 5.5: comparación de lanzamientos

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

Comparación de los lanzamientos Claude Haiku 5.5 y Claude Sonnet 5.5: 5 y 5 modelos respectivamente, cada uno con distintas características de inteligencia, rendimiento y precio. A continuación se comparan las métricas clave de los 10 modelos.

En inteligencia, Claude Sonnet 5.5 obtiene la puntuación más alta: Claude Sonnet 5.5 (Max, Default Fallback), con 54, frente a Claude Haiku 5.5 (Max), con 36 de Claude Haiku 5.5.
En velocidad de salida, Claude Haiku 5.5 es el más rápido: Claude Haiku 5.5 (Max), con 241 tokens/s, frente a Claude Sonnet 5.5 (Max, Default Fallback), con 140 tokens/s de Claude Sonnet 5.5.
En costo por tarea, Claude Haiku 5.5 es el más económico: Claude Haiku 5.5 (Low), con $0.04, frente a Claude Sonnet 5.5 (Low, Default Fallback), con $0.51 de Claude Sonnet 5.5.

Playground de modelos

Lanzamientos comparados


	Claude Sonnet 5.5 (max with fallback)	Claude Sonnet 5.5 (xhigh with fallback)	Claude Sonnet 5.5 (high with fallback)	Claude Haiku 5.5 (max)	Claude Haiku 5.5 (xhigh)	Claude Sonnet 5.5 (medium with fallback)	Claude Haiku 5.5 (high)	Claude Sonnet 5.5 (low with fallback)	Claude Haiku 5.5 (medium)	Claude Haiku 5.5 (low)
Intelligence Index	54	50	41	36	34	30	30	25	25	19
Finanzas y contabilidad	56	49	44	44	41	41	38	36	35	29
Estrategia y operaciones	58	54	51	39	39	47	37	42	33	27
Jurídico	52	47	44	39	37	39	35	37	33	27
Salud y medicina	54	47	44	37	34	40	32	37	31	25
Ingeniería	58	53	46	42	40	37	36	33	32	27
Economía	56	50	46	44	43	41	39	36	36	30
AA-Briefcase v1.1	1812	1743	1634	1575	1524	1438	1440	1268	1369	1114
AutomationBench-AA	71.8%	65.5%	59.4%	35.4%	36.0%	54.9%	33.7%	49.4%	28.6%	22.9%
Terminal-Bench 4.0	63.6%	57.1%	43.9%	32.8%	29.3%	29.8%	21.7%	20.7%	15.2%	12.6%
FrontierCode 2.0	41.7%	35.6%	25.7%	34.9%	29.9%	11.0%	23.2%	7.1%	16.1%	8.0%
AA-Omniscience v1.1	30	21	19	12	8	19	5	20	4	2
GDP.pdf	25.8%	24.6%	25.2%	20.8%	18.2%	20.2%	17.2%	16.0%	15.2%	11.2%
HLE-Diamond	53.3%	44.1%	33.8%	29.6%	28.8%	23.8%	23.7%	20.6%	16.8%	14.1%
CritPt v2 (Hard Subset)	56.0%	54.0%	47.5%	41.0%	44.5%	28.5%	42.5%	22.5%	30.0%	21.5%
Terminal-Bench-Science 0.1	53.3%	52.4%	34.3%	20.0%	18.1%	16.2%	10.0%	10.5%	7.1%	1.9%

Costo por tareaUSD	$10.02	$4.09	$1.64	$0.41	$0.25	$0.78	$0.16	$0.51	$0.09	$0.04
Precio de entradaUSD/1M tokens	$2.00	$2.00	$2.00	$0.10	$0.10	$2.00	$0.10	$2.00	$0.10	$0.10
Precio de salidaUSD/1M tokens	$10.00	$10.00	$10.00	$0.50	$0.50	$10.00	$0.50	$10.00	$0.50	$0.50
Precio de lectura de cachéUSD/1M tokens	$0.10	$0.10	$0.10	$0.01	$0.01	$0.10	$0.01	$0.10	$0.01	$0.01
Precio de escritura de cachéUSD/1M tokens	$2.50	$2.50	$2.50	$0.125	$0.125	$2.50	$0.125	$2.50	$0.125	$0.125

Velocidad de salidaTokens/s	140	113	115	241	196	109	187	109	175	185
Tiempo hasta el primer tokens	455,03	28,63	11,08	310,72	67,20	3,02	24,31	1,29	10,36	7,51
Tiempo hasta el primer token de respuestas	455,03	28,63	11,08	310,72	67,20	3,02	24,31	1,29	10,36	7,51
Tiempo de respuesta de extremo a extremos	458,60	33,06	15,42	312,80	69,75	7,62	26,99	5,86	13,21	10,22
Tiempo por tareas	1325,71	690,72	331,57	593,47	441,28	177,64	298,26	120,54	192,95	97,99

Ventana de contexto	1M	1M	1M	1M	1M	1M	1M	1M	1M	1M
Creador	Anthropic	Anthropic	Anthropic	Anthropic	Anthropic	Anthropic	Anthropic	Anthropic	Anthropic	Anthropic
Licencia	Propietario	Propietario	Propietario	Propietario	Propietario	Propietario	Propietario	Propietario	Propietario	Propietario
Modalidad de entrada	Admite: texto e imágenes	Admite: texto e imágenes	Admite: texto e imágenes	Admite: texto e imágenes	Admite: texto e imágenes	Admite: texto e imágenes	Admite: texto e imágenes	Admite: texto e imágenes	Admite: texto e imágenes	Admite: texto e imágenes
Modalidad de salida	Admite: texto	Admite: texto	Admite: texto	Admite: texto	Admite: texto	Admite: texto	Admite: texto	Admite: texto	Admite: texto	Admite: texto
Proveedores

Updated

Inteligencia

Artificial Analysis Intelligence Index · Higher is better

Velocidad

Output tokens per second · Higher is better

Costo por tarea

Weighted average cost (USD) per Intelligence Index task · Lower is better

InteligenciaUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v5.0 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

Artificial Analysis Intelligence Index v5.0 includes: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Index vs. costo por tarea

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

Most attractive quadrant

Claude Haiku 5.5

Claude Sonnet 5.5

Pareto line

AA-Briefcase v1.1

AutomationBench-AA

Costo por tarea (USD, escala logarítmica)

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

Costo por tarea del Intelligence Index

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

Velocidad y latencia

Velocidad de salida

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 5 evaluations: AA-Briefcase v1.1, AA-Omniscience v1.1, HLE-Diamond, AutomationBench-AA, GDP.pdf · Higher is better

Strategy & Ops Index

Incorporates 4 evaluations: AutomationBench-AA, AA-Briefcase v1.1, AA-Omniscience v1.1, GDP.pdf · Higher is better

Legal Index

Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf, AutomationBench-AA · Higher is better

Healthcare & Medical Index

Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, MLCR-AA, AutomationBench-AA, HLE-Diamond · Higher is better

Engineering Index

Incorporates 7 evaluations: AA-Omniscience v1.1, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1, HLE-Diamond, Terminal-Bench 4.0, FrontierCode 2.0, AA-Briefcase v1.1 · Higher is better

Economics Index

Incorporates 4 evaluations: AA-Briefcase v1.1, AA-Omniscience v1.1, HLE-Diamond, GDP.pdf · Higher is better

Benchmarks

AA-PersonalityBenchNew

Modelo Avs.Modelo B

AA-PersonalityBench: índice Expressiveness, Claude Haiku 5.5 (max) vs. Claude Sonnet 5.5 (max with fallback)

Probabilidad de que la respuesta de cada modelo sea juzgada como la que muestra más cada rasgo, según su diferencia de Elo · 50 % es un empate

Claude Haiku 5.5 (max)

Claude Sonnet 5.5 (max with fallback)

Natural Sounding

79 %

21 %

Metaphorical

36 %

64 %

Literate

61 %

39 %

Lexically Varied

57 %

43 %

Eloquent

51 %

49 %

Claude Haiku 5.5 vs. Claude Sonnet 5.5: comparación de lanzamientos

Inteligencia

Velocidad

Costo por tarea

InteligenciaUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Index vs. costo por tarea

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

Costo

Costo por tarea del Intelligence Index

Cost per Intelligence Index Task

Velocidad y latencia

Velocidad de salida

Output Speed

Model Performance Representation

Puntuaciones de capacidades

Índices de capacidades

Benchmarks

AA-PersonalityBenchNew

AA-PersonalityBench: índice Expressiveness, Claude Haiku 5.5 (max) vs. Claude Sonnet 5.5 (max with fallback)