模型比较：智能、性能与价格分析

Microevals 体验区
从质量、价格、输出速度、延迟、上下文窗口等关键性能指标比较和分析 AI 模型。点击任意模型可查看详细指标。如需了解包括方法论在内的更多详情，请参阅我们的常见问题。

智能

Claude Opus 5 (max) 标志 Claude Opus 5 (max) 和 Claude Opus 5 (xhigh) 标志 Claude Opus 5 (xhigh) 是智能得分最高的模型，其次是 Claude Fable 5 (with fallback) 标志 Claude Fable 5 (with fallback) 和 GPT-5.6 Sol (max) 标志 GPT-5.6 Sol (max)。

输出速度（token/秒）

Celeris-1 标志 Celeris-1 (2034 t/s) 和 Mercury 2 标志 Mercury 2 (742 t/s) 是速度最快的模型，其次是 LFM2.5-VL-1.6B 标志 LFM2.5-VL-1.6B 和 Step 3.7 Flash 标志 Step 3.7 Flash。

延迟（秒）

Gemini 2.5 Flash-Lite 标志 Gemini 2.5 Flash-Lite (0.33s) 和 Command A+ 标志 Command A+ (0.44s) 是延迟最低的模型，其次是 Gemini 2.5 Flash 标志 Gemini 2.5 Flash 和 Grok Build 0.1 0616 标志 Grok Build 0.1 0616。

价格（美元/100 万 token）

Devstral 2 标志 Devstral 2 ($0.00) 和 North Mini Code 标志 North Mini Code ($0.00) 是最便宜的模型，其次是 Gemma 3 4B 标志 Gemma 3 4B 和 Gemma 3 27B 标志 Gemma 3 27B。

上下文窗口

Llama 4 Scout 标志 Llama 4 Scout (10M) 和 Grok 4.20 0309 标志 Grok 4.20 0309 (2M) 的上下文窗口最大，其次是 Gemini 1.5 Pro (May) 标志 Gemini 1.5 Pro (May) 和 Grok 4.1 Fast 标志 Grok 4.1 Fast。

亮点

智能

Artificial Analysis Intelligence Index · Higher is better

速度

Output tokens per second · Higher is better

每任务成本

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

智能

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).

基准测试

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

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

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.

开放性指数

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)
Reasoning models are indicated by a lightbulb icon

Intelligence Index 比较

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.

Token 使用量

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).

成本

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.

上下文窗口

Context Window

Context window: tokens limit · Higher is better
Reasoning models are indicated by a lightbulb icon

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

速度

按输出速度（每秒 token 数）衡量

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.

延迟

按首 Token 延迟（秒）衡量

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time
Reasoning models are indicated by a lightbulb icon

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

端到端响应时间

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better
Reasoning models are indicated by a lightbulb icon

Seconds to receive a 500 token response. Key components:

  • Input time: Time to receive the first response token
  • Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
  • Answer time: Time to generate 500 output tokens, based on output speed

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).

模型规模（仅开放权重模型）

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference
Reasoning models are indicated by a lightbulb icon

The total number of trainable weights and biases in the model, expressed in billions. These parameters are learned during training and determine the model's ability to process and generate responses.

The number of parameters actually executed during each inference forward pass, expressed in billions. For Mixture of Experts (MoE) models, a routing mechanism selects a subset of experts per token, resulting in fewer active than total parameters. Dense models use all parameters, so active equals total.

常见问题

在已评测的 175 个模型中，Claude Opus 5 (Adaptive Reasoning, Max Effort) 目前以 61 分领跑 Artificial Analysis Intelligence Index。

按 Intelligence Index 排名，顶尖 AI 模型是：1. Claude Opus 5 (Adaptive Reasoning, Max Effort)（61）、2. Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)（60）、3. Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)（60）、4. GPT-5.6 Sol (max)（59）和5. Claude Opus 5 (Adaptive Reasoning, High Effort)（59）。

Celeris-1 最快，输出速度为每秒 2,033.7 个 token，其次是 Mercury 2（741.8 t/s）和 LFM2.5-VL-1.6B（474.5 t/s）。

Nova Micro 最实惠，混合价格为每 100 万 token $0.03，其次是 Sarvam 30B (high)（$0.03）和 Gemma 4 E4B (Non-reasoning)（$0.03）。

Gemini 2.5 Flash-Lite (Non-reasoning) 的首 Token 延迟最低，为 0.33 秒，其次是 Command A+（0.44 秒）和 Gemini 2.5 Flash (Non-reasoning)（0.47 秒）。

Kimi K3 (max) 是排名最高的开放权重模型，Intelligence Index 得分为 57。总计评测的 175 个模型中，有 99 个开放权重模型。

按 Intelligence Index 排名，顶尖开放权重 AI 模型是：1. Kimi K3 (max)（57）、2. GLM-5.2 (max)（51）和3. DeepSeek V4 Flash 0731 (Reasoning, Max Effort)（50）。

在 130 个推理模型中，Claude Opus 5 (Adaptive Reasoning, Max Effort) 以 61 的 Intelligence Index 得分领先。推理模型会先通过扩展思考来解决复杂问题，再给出回答。

模型会在多个维度上进行比较，包括智能（质量）、价格、输出速度（每秒 token 数）、延迟（首 Token 延迟）、端到端响应时间和上下文窗口大小。性能指标通过标准化提示词，在 591 个模型上直接测量。

点击图表中的任意模型名称或行，即可打开该模型的专属页面，查看详细指标并与类似模型直接比较。您还可以使用模型选择器，自定义每张图表中显示的模型。 查看排行榜