Análisis independiente de IA

Entiende el panorama de la IA para elegir el mejor modelo y proveedor para tu caso de uso

Destacados

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

Optima

de Artificial Analysis

Nuevo

Crea tu propio benchmark personalizado

Recomendador de modelos

Recibe recomendaciones de modelos personalizadas que optimizan según tus prioridades de inteligencia, velocidad y costo

Registro de cambios
Nuevo artículo publicado · 4 sept
Announcing Artificial Analysis Intelligence Index v4.2
Nuevo artículo publicado · 3 sept
Benchmarking GPT-6 Astra
Nueva evaluación de modelo de lenguaje · 3 sept
GPT-6 Astra (Non-reasoning)GPT-6 Astra (Non-reasoning)
Nueva evaluación de modelo de lenguaje · 3 sept
GPT-6 Astra (low)GPT-6 Astra (low)
Nueva evaluación de modelo de lenguaje · 3 sept
GPT-6 Astra (medium)GPT-6 Astra (medium)
Nueva evaluación de modelo de lenguaje · 3 sept
GPT-6 Astra (high)GPT-6 Astra (high)
Nueva evaluación de modelo de lenguaje · 3 sept
GPT-6 Astra (xhigh)GPT-6 Astra (xhigh)
Nueva evaluación de modelo de lenguaje · 3 sept
GPT-6 Astra (max)GPT-6 Astra (max)
Nueva evaluación de modelo de lenguaje · 3 sept
K2 Horizon 375B A23BK2 Horizon 375B A23B
Nuevo artículo publicado · 2 sept
Muse Spark 1.3: Meta reaches the frontier
Nuevo artículo publicado · 2 sept
Google has released Gemini 3.8 Flash, its fourth Flash model in under four months
Nueva evaluación de modelo de lenguaje · 2 sept
Muse Spark 1.3 (max)Muse Spark 1.3 (max)
Nueva evaluación de modelo de lenguaje · 2 sept
Muse Spark 1.3 (xhigh)Muse Spark 1.3 (xhigh)
Nueva evaluación de modelo de lenguaje · 2 sept
Gemini 3.8 Flash (low)Gemini 3.8 Flash (low)
Nueva evaluación de modelo de lenguaje · 2 sept
Gemini 3.8 Flash (medium)Gemini 3.8 Flash (medium)
Nueva evaluación de modelo de lenguaje · 2 sept
Gemini 3.8 Flash (high)Gemini 3.8 Flash (high)
Nuevo artículo publicado · 1 sept
Claude Fable 5.1 tops the Artificial Analysis Intelligence Index
Nueva evaluación de modelo de lenguaje · 1 sept
Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)
Nueva evaluación de modelo de lenguaje · 1 sept
Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)
Nueva evaluación de modelo de lenguaje · 1 sept
Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)Ver más

InteligenciaUpdated

Inteligencia de los principales modelos de IA según nuestras evaluaciones independientes

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.2 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Artificial Analysis Intelligence Index v4.2 includes: AA-Briefcase, GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, 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.

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index v4.2 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Artificial Analysis Intelligence Index v4.2 includes: AA-Briefcase, GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, 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.

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if commercial use is limited by conditions, and as 'Non-commercial' if the license prohibits commercial use.

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better

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.

Intelligence Index vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task
Most attractive quadrant
Pareto line

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.

Artificial Analysis Intelligence Index v4.2 includes: AA-Briefcase, GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, 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. Cost per Intelligence Index Task, by Model Release

All reasoning and effort variants of each selected release · Weighted average cost (USD) per Artificial Analysis Intelligence Index task
Most attractive quadrant
Pareto line

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.

Artificial Analysis Intelligence Index v4.2 includes: AA-Briefcase, GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, 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.

Inteligencia de modelos de lenguaje de frontera a lo largo del tiempo

Artificial Analysis Intelligence Index v4.2 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Artificial Analysis Intelligence Index v4.2 includes: AA-Briefcase, GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, 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.

Índice de agentes de programación

Rendimiento, costo y tiempo de ejecución de los principales agentes de programación en tareas integrales de ingeniería de software

Índice de agentes de programación de Artificial Analysis

Composite average pass@1 across DeepSWE, Terminal-Bench v2.1, and SWE-Atlas-QnA · Higher is better

Imagen y video

Mejores modelos de nuestros rankings Image Arena y Video Arena, con intervalos de confianza del 95%

Ranking de texto a imagen

Puntuaciones Elo a partir de votos ciegos de preferencia en nuestro Image Arena. Ver el ranking completo aquí.

Voz

Mejores modelos de nuestras evaluaciones Text to Speech Arena, Speech to Text y Speech to Speech

Provider Voice Arena Quality Elo

Arena Elo: average Elo rating of the model · Higher is better

Relative Elo score of the models as determined by responses from users in Artificial Analysis' Speech Arena. Some models may not be shown due to not yet having enough votes.

Índices de capacidades

Ver más

Miden el rendimiento de modelos en capacidades e industrias específicas

Artificial Analysis Finance & Accounting Index

Incorporates 5 evaluations: AA-Omniscience, GDPval-AA v2, Humanity's Last Exam, 𝜏³-Banking, AA-LCR v1.1 · Higher is better

Benchmarks

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
See more
AA-Briefcase

Agentic knowledge work, (Elo-500)/2000

GDPval-AA v2

Agentic real-world work tasks, (Elo-500)/2000

𝜏³-Banking

Agentic tool use

Terminal-Bench v2.1

Agentic coding & terminal use

SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GDP.pdfNew

Professional document reasoning, All-pass

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR v1.1

Long context reasoning

AutomationBench-AA

Agentic SaaS workflows

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AA

Agentic business operations

GPQA Diamond

Scientific reasoning

AA-AnalystAgent

Quantitative analysis on spreadsheets & documents

IFBench

Instruction following

APEX-Agents-AA

Long-horizon agentic tasks

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Artificial Analysis Intelligence Index v4.2 includes: AA-Briefcase, GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, 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.

AA-Briefcase

AA-Briefcase es una evaluación agéntica de vanguardia para trabajo cognitivo de largo plazo, que prueba agentes en flujos de trabajo empresariales realistas que requieren entregables como hojas de cálculo, presentaciones y memorandos

AA-Briefcase Elo

AA-Briefcase is an agentic knowledge work benchmark developed by Artificial Analysis. AA-Briefcase Elo is a combined metric that aggregates rubric pass rate, analytical quality Elo and presentation Elo · Higher is better

AA-Briefcase Elo is a combined metric that aggregates analytical quality Elo, presentation Elo, and rubric pass rate, with rubric performance converted into Elo via synthetic head-to-head matches. Elo and 95% confidence interval bounds are clamped at 0.

AA-AnalystAgent

AA-AnalystAgent es un benchmark de análisis cuantitativo de extremo a extremo sobre hojas de cálculo y documentos reales: el tipo de trabajo que los analistas de negocio y de datos realizan a diario

AA-AnalystAgent pass^5

Share of end-to-end quantitative analysis tasks solved on all five attempts · Higher is better

Share of AA-AnalystAgent questions answered correctly on all five attempts. AA-AnalystAgent is Artificial Analysis' benchmark for end-to-end quantitative analysis on real-world spreadsheets and documents; every question is run five independent times, so pass^5 measures how reliably a model reproduces a correct answer rather than how often it reaches one.

AA-Omniscience

AA-Omniscience es un benchmark de conocimiento y alucinaciones que premia la precisión, penaliza las respuestas incorrectas y ofrece una vista completa de qué modelos producen resultados fiables en distintos dominios

Índice AA-Omniscience

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.

GDPval-AA v2

GDPval-AA v2 evalúa modelos de IA en tareas reales de valor económico en una amplia gama de ocupaciones

GDPval-AA v2 Leaderboard

Elo rating for performance on real-world work tasks · Anchored to a human baseline of 1,000 · Higher is better
Human Baseline (1,000)

Índice de apertura

El índice de apertura de Artificial Analysis evalúa qué tan 'abiertos' son los modelos según su disponibilidad y transparencia en distintos componentes.

Artificial Analysis Openness Index: Components

Openness Index underlying score contribution by components, up to a maximum of 18 (higher is more open)

Artificial Analysis Openness Index vs. Artificial Analysis Intelligence Index

Most attractive quadrant
Pareto line

Tokens de salida

Tokens de salida de los principales modelos de IA según nuestras evaluaciones independientes

Output Tokens per Intelligence Index Task

Weighted average number of output tokens used to run one task in the Artificial Analysis Intelligence Index

The number of tokens required per Intelligence Index task. This is calculated by multiplying the output tokens per eval by the relative weights of each benchmark in the Intelligence Index, then dividing by task count (excluding repeats).

Costo

Precios y costos reales de los principales modelos de IA según nuestras evaluaciones independientes

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better

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.

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index

The cost to run the evaluations in the Artificial Analysis Intelligence Index, calculated using the model's input, cache hit, cache write, reasoning, and answer token prices and the number of tokens used across evaluations (excluding repeats).

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens)

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Velocidad y latencia

Comparación del rendimiento de API de primera parte

Output Speed

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 (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Time per Intelligence Index Task

Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better

The weighted average time (seconds) per Artificial Analysis Intelligence Index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the Intelligence Index.

Proveedores

Endpoint Accuracy Index: gpt-oss-120b (high)

v1.0 · Composite of BFCL v4-500, HLE-250 and AA-LCR-25 run against each provider endpoint · Percentage of the reference endpoint, with 95% confidence interval · Higher is better

Composite measure of how much of a model's accuracy a given provider endpoint preserves, from re-running BFCL v4-500, HLE-250 and AA-LCR-25 against that endpoint. Where a self-hosted reference endpoint exists, scores are expressed as a percentage of that reference (100 = matches reference); lower scores indicate accuracy lost to quantisation, sampling defaults, or other endpoint-side configuration. Scores are point-in-time snapshots. Methodology.

Output Speed vs. Price: gpt-oss-120b (high)

Output tokens per second · USD per 1M tokens (blended) · 10,000 input tokens
Most attractive quadrant
Pareto line

Smaller, emerging providers are offering high output speed and at competitive prices.

Precios (acierto de caché, entrada y salida): gpt-oss-120b (high)

Price (USD per M Tokens) · Lower is better · 10,000 input tokens

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Output Speed: gpt-oss-120b (high)

Output speed: output tokens per second · 10,000 input tokens

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 (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).