Análise independente de IA

Entenda o cenário da IA para escolher o melhor modelo e provedor para seu caso de uso

Destaques

Inteligência

Artificial Analysis Intelligence Index · Higher is better

Velocidade

Output tokens per second · Higher is better

Custo por tarefa

Weighted average cost (USD) per Intelligence Index task · Lower is better

Recomendação personalizada de modelos

Receba recomendações personalizadas com base em suas prioridades de inteligência, velocidade e custo

Explore agentes para tarefas gerais, programação, atendimento ao cliente e muito mais.

Compare agentes de IA por capacidades, preços e compatibilidade com plataformas

Explore os planos Premium

Acesse dados ampliados de benchmarks, visualizações personalizadas, relatórios setoriais e muito mais

Histórico de alterações
Nova avaliação de modelo de linguagem · 3 de ago.
G9v3-39A5BG9v3-39A5B
Novo artigo publicado · 31 de jul.
DeepSeek V4 Flash 0731 scores 50 on the Artificial Analysis Intelligence Index, 10 points above previous DeepSeek V4 Flash
Nova avaliação de modelo de linguagem · 31 de jul.
Celeris-1Celeris-1
Nova avaliação de modelo de linguagem · 31 de jul.
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)DeepSeek V4 Flash 0731 (Reasoning, Max Effort)
Novo artigo publicado · 30 de jul.
Inkling Small lands within a point of Inkling on the Artificial Analysis Intelligence Index with less than a third of the parameters
Metodologia atualizada · 30 de jul.
Artificial AnalysisWe have updated our Cost per Task methodology, resulting in slight absolute increases in cost estimates but with minimal impact on relative positioning.
Nova avaliação de modelo de linguagem · 30 de jul.
Kimi K3 (low)Kimi K3 (low)
Nova avaliação de modelo de linguagem · 30 de jul.
Inkling SmallInkling Small
Novo artigo publicado · 29 de jul.
Agnes AI releases Agnes 2.5 Pro Alpha
Novo artigo publicado · 24 de jul.
Claude Opus 5: the new leader in agentic knowledge work
Novo artigo publicado · 24 de jul.
Opus 5: Fable 5 level intelligence at a lower cost per task
Nova avaliação de modelo de linguagem · 24 de jul.
Claude Opus 5 (Adaptive Reasoning, Low Effort)Claude Opus 5 (Adaptive Reasoning, Low Effort)
Nova avaliação de modelo de linguagem · 24 de jul.
Claude Opus 5 (Adaptive Reasoning, Medium Effort)Claude Opus 5 (Adaptive Reasoning, Medium Effort)
Nova avaliação de modelo de linguagem · 24 de jul.
Claude Opus 5 (Adaptive Reasoning, High Effort)Claude Opus 5 (Adaptive Reasoning, High Effort)
Nova avaliação de modelo de linguagem · 24 de jul.
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
Nova avaliação de modelo de linguagem · 24 de jul.
Claude Opus 5 (Adaptive Reasoning, Max Effort)Claude Opus 5 (Adaptive Reasoning, Max Effort)
Nova avaliação de modelo de linguagem · 23 de jul.
Agnes 2.5 Pro AlphaAgnes 2.5 Pro Alpha
Novo artigo publicado · 22 de jul.
How Thinking Machines Lab’s Inkling performs on agentic knowledge work
Nova avaliação de modelo de linguagem · 22 de jul.
G9v3-3BG9v3-3B
Novo artigo publicado · 21 de jul.
Kimi K3: second only to Fable 5 on AA-BriefcaseVer mais

Inteligência

Inteligência dos principais modelos de IA com base em nossas avaliações independentes

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. 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 v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. 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 the weights are available but commercial use is limited (typically requires obtaining a paid license).

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better
Reasoning models are indicated by a lightbulb icon

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
Reasoning models are indicated by a lightbulb icon

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 v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Inteligência dos modelos de linguagem de fronteira ao longo do tempo

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Coding Agent Index

Desempenho, custo e tempo de execução dos principais agentes de programação em tarefas de engenharia de software de ponta a ponta

Artificial Analysis Coding Agent Index

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

Imagem e vídeo

Principais modelos dos rankings da Image Arena e da Video Arena, com intervalos de confiança de 95%

Ranking de texto para imagem

Pontuações Elo calculadas com base em votos cegos de preferência na Image Arena. Veja o ranking completo.

Fala

Principais modelos da Arena de Texto para Fala e das avaliações de fala para texto e fala para fala

Text to Speech Arena Leaderboard

Elo scores from blind preference votes in our Text to Speech Arena · See the full leaderboard here.

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 capacidadeUpdated

Ver mais

Mede o desempenho dos modelos em capacidades e setores específicos

Artificial Analysis Agentic Index

Measures performance in agentic workflows, focusing on behaviors like tool use, planning, autonomy, and complex problem solving.
Reasoning models are indicated by a lightbulb icon

Avaliações

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
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

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR

Long context reasoning

AA-Briefcase

Agentic knowledge work, Elo

AutomationBench-AA

Agentic SaaS workflows

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AANew

Agentic business operations

IFBench

Instruction following

APEX-Agents-AA

Long-horizon agentic tasks

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

Reasoning models are indicated by a lightbulb icon

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

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

AA-Briefcase

O AA-Briefcase é uma avaliação agentiva avançada voltada para tarefas de conhecimento de longo prazo. Ela testa agentes em fluxos de trabalho empresariais realistas, que exigem a produção de entregáveis como planilhas, apresentações e 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
Reasoning models are indicated by a lightbulb icon

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-Omniscience

O AA-Omniscience é um benchmark de conhecimento e alucinações que recompensa a acurácia, penaliza palpites errados e oferece uma visão abrangente de quais modelos produzem resultados factualmente confiáveis em diferentes áreas

AA-Omniscience Index

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.
Reasoning models are indicated by a lightbulb icon

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

O GDPval-AA v2 avalia modelos de IA em tarefas reais e economicamente relevantes de uma ampla variedade de profissões

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)
Reasoning models are indicated by a lightbulb icon

Openness Index

O Artificial Analysis Openness Index avalia quanto os modelos são 'abertos' com base em sua disponibilidade e na transparência de diferentes componentes.

Artificial Analysis Openness Index: Components

Openness Index underlying score contribution by components, up to a maximum of 18 (higher is more open)
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Openness Index vs. Artificial Analysis Intelligence Index

Most attractive quadrant
Pareto line

Tokens de saída

Tokens de saída dos principais modelos de IA com base em nossas avaliações independentes

Output Tokens per Intelligence Index Task

Weighted average number of output tokens used to run one task in the Artificial Analysis Intelligence Index
Reasoning models are indicated by a lightbulb icon

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).

Custo

Preços e custos reais dos principais modelos de IA com base em nossas avaliações independentes

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better
Reasoning models are indicated by a lightbulb icon

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
Reasoning models are indicated by a lightbulb icon

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)
Reasoning models are indicated by a lightbulb icon

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.

Velocidade e latência

Comparação do desempenho das APIs oficiais

Output Speed

Output tokens per second · Higher is better
Reasoning models are indicated by a lightbulb icon

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
Reasoning models are indicated by a lightbulb icon

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.

Provedores

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
Reasoning models are indicated by a lightbulb icon

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

Preços (acerto de cache, entrada e saída): 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).