GPT-6.1 Terra vs. DeepSeek V4.1 Flash 1017: comparación de lanzamientos

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

Comparación de los lanzamientos GPT-6.1 Terra y DeepSeek V4.1 Flash 1017: 6 y 3 modelos respectivamente, cada uno con distintas características de inteligencia, rendimiento y precio. A continuación se comparan las métricas clave de los 9 modelos.

En inteligencia, GPT-6.1 Terra obtiene la puntuación más alta: GPT-6.1 Terra (Max), con 51, frente a DeepSeek V4.1 Flash 1017 (Max), con 33 de DeepSeek V4.1 Flash 1017.
En tiempo por tarea, GPT-6.1 Terra es el más rápido: GPT-6.1 Terra (Low), con 1.2 min, frente a DeepSeek V4.1 Flash 1017 (Non-reasoning), con 7.3 min de DeepSeek V4.1 Flash 1017.
En costo por tarea, GPT-6.1 Terra es el más económico: GPT-6.1 Terra (Low), con $0.0713, frente a DeepSeek V4.1 Flash 1017 (Non-reasoning), con $0.43 de DeepSeek V4.1 Flash 1017.

Playground de modelos

Lanzamientos comparados


	GPT-6.1 Terra (max)	GPT-6.1 Terra (xhigh)	GPT-6.1 Terra (high)	GPT-6.1 Terra (medium)	DeepSeek V4.1 Flash 1017 (max)	GPT-6.1 Terra (non-reasoning)	GPT-6.1 Terra (low)	DeepSeek V4.1 Flash 1017 (high)	DeepSeek V4.1 Flash 1017 (non-reasoning)
Intelligence Index	51	45	42	38	33	31	29	29	19
Finanzas y contabilidad	49	48	44	42	42	34	38	39	37
Estrategia y operaciones	50	49	47	45	49	40	42	48	40
Jurídico	46	44	42	40	38	28	37	34	32
Salud y medicina	45	--	--	--	41	--	--	--	--
Ingeniería	55	49	46	43	38	33	35	34	25
Economía	48	46	43	41	38	32	36	35	32
AA-Briefcase v1.1	1401	1334	1265	1191	1570	1226	1032	1416	1425
AutomationBench-AA	60.2%	59.9%	58.5%	57.8%	66.6%	51.0%	56.2%	68.5%	48.8%
Terminal-Bench 4.0	55.6%	46.5%	41.9%	32.3%	33.8%	26.8%	15.2%	28.8%	9.1%
FrontierCode-AA 2.0	42.3%	36.9%	37.5%	34.5%	28.5%	33.4%	24.5%	16.8%	6.1%
AA-Omniscience v1.1	30	29	28	27	1	−5	23	2	2
GDP.pdf	28.6%	26.6%	28.0%	28.4%	17.2%	23.2%	25.6%	14.2%	4.4%
HLE-Diamond	47.3%	42.3%	35.4%	31.3%	25.3%	14.5%	24.9%	20.8%	7.1%
CritPt v2 (Hard Subset)	68.0%	60.5%	61.5%	56.5%	25.0%	33.5%	50.5%	27.5%	1.0%
Terminal-Bench-Science 0.1	57.6%	41.9%	33.3%	24.8%	12.9%	24.3%	7.6%	10.5%	2.4%

Costo por tareaUSD	$0.96	$0.40	$0.26	$0.17	$0.60	$0.23	$0.0713	$0.46	$0.43
Precio de entradaUSD/1M tokens	$1.00	$1.00	$1.00	$1.00	$0.30	$1.00	$1.00	$0.30	$0.30
Precio de salidaUSD/1M tokens	$5.00	$5.00	$5.00	$5.00	$1.20	$5.00	$5.00	$1.20	$1.20
Precio de lectura de cachéUSD/1M tokens	$0.05	$0.05	$0.05	$0.05	$0.006	$0.05	$0.05	$0.006	$0.006
Precio de escritura de cachéUSD/1M tokens	$1.25	$1.25	$1.25	$1.25	--	$1.25	$1.25	--	--

Tiempo por tareaMinutos	14.1	6.4	4.3	2.8	13.5	2.4	1.2	10.7	7.3
Velocidad de salidatok/s	71	68	65	64	171	65	62	172	150
Tiempo hasta el primer token de respuestas	173.08	34.45	12.60	4.96	44.55	1.96	2.78	21.80	1.34
Tiempo hasta el primer tokens	173.08	34.45	12.60	4.96	1.25	1.96	2.78	1.31	1.34
Tiempo de extremo a extremoMedia de las cargas de solicitud única (s)	363.42	91.00	45.62	28.83	88.32	22.97	21.30	45.24	15.71

Ventana de contexto	1M	1M	1M	1M	1M	1M	1M	1M	1M
Creador	OpenAI	OpenAI	OpenAI	OpenAI	DeepSeek	OpenAI	OpenAI	DeepSeek	DeepSeek
Licencia	Propietario	Propietario	Propietario	Propietario	Abierto	Propietario	Propietario	Abierto	Abierto
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
Modalidad de salida	Admite: texto	Admite: texto	Admite: texto	Admite: texto	Admite: texto	Admite: texto	Admite: texto	Admite: texto	Admite: texto
Proveedores					+18				+3

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

Inteligencia

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-AA 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-AA 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

GPT-6.1 Terra

DeepSeek V4.1 Flash 1017

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

Rendimiento

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-AA 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-PersonalityBench

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

GPT-6.1 Terra vs. DeepSeek V4.1 Flash 1017: comparación de lanzamientos

Inteligencia

Tiempo por tarea

Costo por tarea

Inteligencia

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

Rendimiento

Tiempo por tarea del Intelligence Index

Time per Intelligence Index Task

Time Period

Puntuaciones de capacidades

Índices de capacidades

Benchmarks

AA-PersonalityBench

Índices de personalidad