Claude Haiku 5.5 vs. Gemini 3.8 Flash: 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 Gemini 3.8 Flash: 5 y 3 modelos respectivamente, cada uno con distintas características de inteligencia, rendimiento y precio. A continuación se comparan las métricas clave de los 8 modelos.

En inteligencia, Claude Haiku 5.5 obtiene la puntuación más alta: Claude Haiku 5.5 (Max), con 36, frente a Gemini 3.8 Flash (High), con 31 de Gemini 3.8 Flash.
En velocidad de salida, Claude Haiku 5.5 es el más rápido: Claude Haiku 5.5 (Max), con 241 tokens/s, frente a Gemini 3.8 Flash (High), con 133 tokens/s de Gemini 3.8 Flash.
En costo por tarea, Claude Haiku 5.5 es el más económico: Claude Haiku 5.5 (Low), con $0.04, frente a Gemini 3.8 Flash (Medium), con $6.26 de Gemini 3.8 Flash.

Playground de modelos

Lanzamientos comparados


	Claude Haiku 5.5 (max)	Claude Haiku 5.5 (xhigh)	Gemini 3.8 Flash (high)	Gemini 3.8 Flash (medium)	Claude Haiku 5.5 (high)	Claude Haiku 5.5 (medium)	Gemini 3.8 Flash (low)	Claude Haiku 5.5 (low)
Intelligence Index	36	34	31	30	30	25	22	19
Finanzas y contabilidad	44	41	42	42	38	35	34	29
Estrategia y operaciones	39	39	47	47	37	33	35	27
Jurídico	39	37	42	42	35	33	33	27
Salud y medicina	37	34	38	38	32	31	31	25
Ingeniería	42	40	38	37	36	32	31	27
Economía	44	43	41	40	39	36	34	30
AA-Briefcase v1.1	1575	1524	1202	1182	1440	1369	1062	1114
AutomationBench-AA	35.4%	36.0%	59.9%	60.9%	33.7%	28.6%	36.5%	22.9%
Terminal-Bench 4.0	32.8%	29.3%	19.7%	19.7%	21.7%	15.2%	10.1%	12.6%
FrontierCode 2.0	34.9%	29.9%	18.7%	16.5%	23.2%	16.1%	8.1%	8.0%
AA-Omniscience v1.1	12	8	23	24	5	4	13	2
GDP.pdf	20.8%	18.2%	21.0%	22.8%	17.2%	15.2%	18.6%	11.2%
HLE-Diamond	29.6%	28.8%	33.1%	29.1%	23.7%	16.8%	24.3%	14.1%
CritPt v2 (Hard Subset)	41.0%	44.5%	43.5%	44.0%	42.5%	30.0%	31.5%	21.5%
Terminal-Bench-Science 0.1	20.0%	18.1%	10.0%	10.5%	10.0%	7.1%	8.1%	1.9%

Costo por tareaUSD	$0.41	$0.25	$7.77	$6.26	$0.16	$0.09	--	$0.04
Precio de entradaUSD/1M tokens	$0.10	$0.10	$0.75	$0.75	$0.10	$0.10	$0.75	$0.10
Precio de salidaUSD/1M tokens	$0.50	$0.50	$3.75	$3.75	$0.50	$0.50	$3.75	$0.50
Precio de lectura de cachéUSD/1M tokens	$0.01	$0.01	$0.075	$0.075	$0.01	$0.01	$0.075	$0.01
Precio de escritura de cachéUSD/1M tokens	$0.125	$0.125	$0.75	$0.75	$0.125	$0.125	$0.75	$0.125

Velocidad de salidaTokens/s	241	196	133	--	187	175	--	185
Tiempo hasta el primer tokens	310,72	67,20	27,26	--	24,31	10,36	--	7,51
Tiempo hasta el primer token de respuestas	310,72	67,20	27,26	--	24,31	10,36	--	7,51
Tiempo de respuesta de extremo a extremos	312,80	69,75	31,03	--	26,99	13,21	--	10,22
Tiempo por tareas	593,47	441,28	724,41	--	298,26	192,95	--	97,99

Ventana de contexto	1M	1M	1M	1M	1M	1M	1M	1M
Creador	Anthropic	Anthropic	Google	Google	Anthropic	Anthropic	Google	Anthropic
Licencia	Propietario	Propietario	Propietario	Propietario	Propietario	Propietario	Propietario	Propietario
Modalidad de entrada	Admite: texto e imágenes	Admite: texto e imágenes	Admite: texto, imágenes, voz y video	Admite: texto, imágenes, voz y video	Admite: texto e imágenes	Admite: texto e imágenes	Admite: texto, imágenes, voz y video	Admite: texto e imágenes
Modalidad de salida	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

Gemini 3.8 Flash

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. Gemini 3.8 Flash (high)

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)

Gemini 3.8 Flash (high)

Metaphorical

6 %

94 %

Natural Sounding

93 %

7 %

Eloquent

20 %

80 %

Literate

74 %

26 %

Lexically Varied

74 %

26 %

Claude Haiku 5.5 vs. Gemini 3.8 Flash: 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. Gemini 3.8 Flash (high)