DeepSeek V4.1 Flash vs. Kimi K3: comparación de lanzamientos

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

Comparación de los lanzamientos DeepSeek V4.1 Flash y Kimi K3: 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, Kimi K3 obtiene la puntuación más alta: Kimi K3 (Max), con 44, frente a DeepSeek V4.1 Flash (Max), con 39 de DeepSeek V4.1 Flash.
En velocidad de salida, DeepSeek V4.1 Flash es el más rápido: DeepSeek V4.1 Flash (Max), con 179 tokens/s, frente a Kimi K3 (Low), con 46 tokens/s de Kimi K3.
En costo por tarea, DeepSeek V4.1 Flash es el más económico: DeepSeek V4.1 Flash (Non-reasoning), con $0.15, frente a Kimi K3 (Low), con $1.15 de Kimi K3.

Playground de modelos

Lanzamientos comparados


	Kimi K3 (max)	DeepSeek V4.1 Flash (max)	Kimi K3 (low)	DeepSeek V4.1 Flash (non-reasoning)
Intelligence Index	44	39	30	25
Finanzas y contabilidad	47	45	32	30
Estrategia y operaciones	50	52	39	36
Jurídico	49	41	34	30
Salud y medicina	45	41	--	--
Ingeniería	43	39	30	25
Economía	53	44	37	32
AA-Briefcase v1.1	1501	1422	986	1118
GDPval-AA v2.1	1533	1600	1126	1341
AutomationBench-AA	58.3%	68.9%	49.3%	47.8%
Terminal-Bench 4.0	12.6%	26.8%	12.6%	5.6%
SciCode	59.5%	51.9%	52.7%	35.5%
Humanity's Last Exam	46.9%	39.2%	25.0%	10.8%
GDP.pdf	22.0%	12.8%	18.6%	3.8%
CritPt	23.4%	14.3%	3.1%	0.3%
AA-Omniscience	20	−5	4	−10
AA-LCR v1.1	88.7%	84.0%	79.3%	55.3%

Costo por tareaUSD	$2.00	$0.27	$1.15	$0.15
Precio de entradaUSD/1M tokens	$3.00	$0.30	$3.00	$0.30
Precio de salidaUSD/1M tokens	$15.00	$1.20	$15.00	$1.20
Precio de lectura de cachéUSD/1M tokens	$0.30	$0.006	$0.30	$0.006
Precio de escritura de cachéUSD/1M tokens	--	--	--	--

Velocidad de salidaTokens/s	44	179	46	171
Tiempo hasta el primer tokens	3,23	1,12	3,38	1,08
Tiempo hasta el primer token de respuestas	48,91	12,28	46,79	1,08
Tiempo de respuesta de extremo a extremos	60,32	15,07	57,64	4,00
Tiempo por tareas	979,71	350,10	259,69	201,10

Ventana de contexto	1M	1M	1M	1M
Creador	Kimi	DeepSeek	Kimi	DeepSeek
Licencia	Abierto	Abierto	Abierto	Abierto
Modalidad de entrada	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
Proveedores	+10	+15	+2	+4

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

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

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. costo por tarea del Intelligence Index

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

Most attractive quadrant

DeepSeek V4.1 Flash

Kimi K3

Pareto line

AA-Briefcase v1.1

GDPval-AA v2.1

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 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: GDPval-AA v2.1, AA-Briefcase v1.1, AA-Omniscience, 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

DeepSeek V4.1 Flash vs. Kimi K3: comparación de lanzamientos

Inteligencia

Velocidad

Costo por tarea

Inteligencia

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Index vs. costo por tarea del Intelligence Index

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