Qwen3.8 27B vs. DeepSeek V4 Pro 0813: comparación de lanzamientos

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

Comparación de los lanzamientos Qwen3.8 27B y DeepSeek V4 Pro 0813: 4 y 2 modelos respectivamente, cada uno con distintas características de inteligencia, rendimiento y precio. A continuación se comparan las métricas clave de los 6 modelos.

En inteligencia, DeepSeek V4 Pro 0813 obtiene la puntuación más alta: DeepSeek V4 Pro 0813 (Max), con 23, frente a Qwen3.8 27B (Xhigh), con 20 de Qwen3.8 27B.
En tiempo por tarea, DeepSeek V4 Pro 0813 es el más rápido: DeepSeek V4 Pro 0813 (Non-reasoning), con 16.9 min, frente a Qwen3.8 27B (Non-reasoning), con 18.9 min de Qwen3.8 27B.
En costo por tarea, DeepSeek V4 Pro 0813 es el más económico: DeepSeek V4 Pro 0813 (Non-reasoning), con $0.98, frente a Qwen3.8 27B (Low), con $1.91 de Qwen3.8 27B.

Playground de modelos

Lanzamientos comparados


	DeepSeek V4 Pro 0813 (max)	Qwen3.8 27B (xhigh)	Qwen3.8 27B (medium)	Qwen3.8 27B (low)	DeepSeek V4 Pro 0813 (non-reasoning)	Qwen3.8 27B (non-reasoning)
Intelligence Index	23	20	17	16	13	10
Finanzas y contabilidad	30	36	29	28	20	22
Estrategia y operaciones	41	39	34	29	28	16
Jurídico	28	33	26	27	19	22
Salud y medicina	--	35	24	23	--	19
Ingeniería	30	28	22	21	18	17
Economía	29	34	27	27	19	22
AA-Briefcase v1.1	1253	1391	1372	1270	928	901
AutomationBench-AA	56.7%	48.2%	40.3%	30.1%	34.9%	12.4%
Terminal-Bench 4.0	14.1%	5.6%	5.1%	2.5%	1.5%	0.0%
FrontierCode 2.0	17.1%	14.9%	11.5%	12.4%	10.3%	3.7%
AA-Omniscience v1.1	−6	−6	−36	−21	−19	−7
GDP.pdf	11.4%	16.4%	12.8%	10.4%	3.6%	5.2%
HLE-Diamond	19.5%	15.3%	6.7%	6.8%	7.2%	4.2%
CritPt v2 (Hard Subset)	23.5%	4.0%	16.5%	5.5%	8.5%	2.0%
Terminal-Bench-Science 0.1	5.7%	0.5%	1.0%	0.5%	0.0%	0.0%

Costo por tareaUSD	$1.77	$3.53	$2.16	$1.91	$0.98	$3.77
Precio de entradaUSD/1M tokens	$1.32	$0.50	$0.50	$0.50	$1.32	$0.50
Precio de salidaUSD/1M tokens	$3.96	$3.00	$3.00	$3.00	$3.96	$3.00
Precio de lectura de cachéUSD/1M tokens	$0.044	$0.10	$0.10	$0.10	$0.044	$0.10
Precio de escritura de cachéUSD/1M tokens	--	--	--	--	--	--

Tiempo por tareaMinutos	24.6	41.1	33.3	28.2	16.9	18.9
Velocidad de salidatok/s	67	44	43	47	70	40
Tiempo hasta el primer token de respuestas	73.53	119.19	33.19	18.02	3.42	5.45
Tiempo hasta el primer tokens	2.50	5.90	6.95	5.44	3.42	5.45
Tiempo de extremo a extremoMedia de las cargas de solicitud única (s)	153.41	262.83	148.98	105.01	31.31	41.49

Ventana de contexto	1M	256k	256k	256k	1M	256k
Creador	DeepSeek	Alibaba	Alibaba	Alibaba	DeepSeek	Alibaba
Licencia	Abierto	Abierto	Abierto	Abierto	Abierto	Abierto
Modalidad de entrada	Admite: texto	Admite: texto, imágenes y video	Admite: texto, imágenes y video	Admite: texto, imágenes y video	Admite: texto	Admite: texto, imágenes y video
Modalidad de salida	Admite: texto	Admite: texto	Admite: texto	Admite: texto	Admite: texto	Admite: texto
Proveedores	+5	+7				+4

Updated

Inteligencia

Artificial Analysis Intelligence Index · Higher is better

Tiempo por tarea

Inference time (minutes) per Intelligence Index task · Lower 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 v5.0.1 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 v5.0.1 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

Qwen3.8 27B

DeepSeek V4 Pro 0813

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

Tiempo por tarea del Intelligence Index

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Speed at the model's own endpoint or the median across providers · Lower is better

The weighted average time (minutes) per Artificial Analysis Intelligence Index task: output tokens per task divided by output speed, weighted by each benchmark's weight in the Intelligence Index.

Speed and latency metrics average each endpoint's runs over the past 5 days, and the error rate pools them. We run the benchmark every 6 hours, and endpoints of deprecated models every 18 hours.

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

Benchmarks

AA-PersonalityBenchNew

Índices de personalidad

Cada eje es uno de los 8 índices de personalidad: la media de las puntuaciones z de Elo de sus rasgos, convertida en un rango percentil de 1 a 100 entre todos los modelos evaluados en el benchmark

Qwen3.8 27B vs. DeepSeek V4 Pro 0813: comparación de lanzamientos

Inteligencia

Tiempo por tarea

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

Tiempo por tarea del Intelligence Index

Time per Intelligence Index Task

Time Period

Puntuaciones de capacidades

Índices de capacidades

Benchmarks

AA-PersonalityBenchNew

Índices de personalidad