모델 비교: 지능, 성능 및 가격 분석

Microevals Playground
AI 모델을 품질, 가격, 출력 속도, 지연 시간, 컨텍스트 창 등 주요 성능 지표로 비교하고 분석합니다. 모델을 클릭하면 상세 지표를 볼 수 있습니다. 방법론을 비롯한 자세한 내용은 FAQ에서 확인하세요.

지능

Claude Opus 5 (max) 로고 Claude Opus 5 (max)과 Claude Opus 5 (xhigh) 로고 Claude Opus 5 (xhigh)이 지능이 가장 높은 모델이며 Claude Fable 5 (with fallback) 로고 Claude Fable 5 (with fallback)과 GPT-5.6 Sol (max) 로고 GPT-5.6 Sol (max)이 뒤를 잇습니다.

출력 속도(토큰/초)

Celeris-1 로고 Celeris-1 (2034 t/s)과 Mercury 2 로고 Mercury 2 (742 t/s)이 가장 빠른 모델이며 LFM2.5-VL-1.6B 로고 LFM2.5-VL-1.6B과 Step 3.7 Flash 로고 Step 3.7 Flash이 뒤를 잇습니다.

지연 시간(초)

Gemini 2.5 Flash-Lite 로고 Gemini 2.5 Flash-Lite (0.33s)과 Command A+ 로고 Command A+ (0.44s)이 지연 시간이 가장 짧은 모델이며 Gemini 2.5 Flash 로고 Gemini 2.5 Flash과 Grok Build 0.1 0616 로고 Grok Build 0.1 0616이 뒤를 잇습니다.

가격(토큰 100만 개당 $)

Devstral 2 로고 Devstral 2 ($0.00)과 North Mini Code 로고 North Mini Code ($0.00)이 가장 저렴한 모델이며 Gemma 3 4B 로고 Gemma 3 4B과 Gemma 3 27B 로고 Gemma 3 27B이 뒤를 잇습니다.

컨텍스트 창

Llama 4 Scout 로고 Llama 4 Scout (10M)과 Grok 4.20 0309 로고 Grok 4.20 0309 (2M)이 컨텍스트 창이 가장 큰 모델이며 Gemini 1.5 Pro (May) 로고 Gemini 1.5 Pro (May)과 Grok 4.1 Fast 로고 Grok 4.1 Fast이 뒤를 잇습니다.

주요 내용

지능

Artificial Analysis Intelligence Index · Higher is better

속도

Output tokens per second · Higher is better

작업당 비용

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

지능

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).

벤치마크

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.

Openness Index

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 비교

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.

토큰 사용량

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).

비용

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.

컨텍스트 창

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).

속도

출력 속도(초당 토큰 수)로 측정

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.

지연 시간

첫 토큰까지 걸린 시간(초)으로 측정

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.

종단 간 응답 시간

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).

모델 크기(오픈 웨이트 모델만 해당)

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.

자주 묻는 질문

Claude Opus 5 (Adaptive Reasoning, Max Effort)은 Artificial Analysis Intelligence Index에서 61점으로, 평가된 모델 175개 중 선두입니다.

Intelligence Index 기준 상위 AI 모델: 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) 및 5. Claude Opus 5 (Adaptive Reasoning, High Effort)(59).

Celeris-1이 초당 2,033.7토큰으로 가장 빠르며, Mercury 2(741.8 t/s)과 LFM2.5-VL-1.6B(474.5 t/s)이 뒤를 잇습니다.

Nova Micro이 혼합 가격 기준 토큰 100만 개당 $0.03로 가장 저렴하며, Sarvam 30B (high)($0.03)과 Gemma 4 E4B (Non-reasoning)($0.03)이 뒤를 잇습니다.

Gemini 2.5 Flash-Lite (Non-reasoning)의 첫 토큰까지 걸린 시간이 0.33초로 가장 짧으며, Command A+(0.44초)과 Gemini 2.5 Flash (Non-reasoning)(0.47초)이 뒤를 잇습니다.

Kimi K3 (max)이 Intelligence Index 점수 57점으로 가장 높은 순위의 오픈 웨이트 모델입니다. 평가한 전체 모델 175개 중 오픈 웨이트 모델은 99개입니다.

Intelligence Index 기준 상위 오픈 웨이트 AI 모델: 1. Kimi K3 (max)(57), 2. GLM-5.2 (max)(51) 및 3. DeepSeek V4 Flash 0731 (Reasoning, Max Effort)(50).

Claude Opus 5 (Adaptive Reasoning, Max Effort)이 Intelligence Index 점수 61점으로 추론 모델 130개 중 선두입니다. 추론 모델은 답변하기 전에 확장 사고를 사용해 복잡한 문제를 해결합니다.

지능(품질), 가격, 출력 속도(초당 토큰 수), 지연 시간(첫 토큰까지 걸린 시간), 종단 간 응답 시간, 컨텍스트 창 크기 등 여러 차원에서 모델을 비교합니다. 표준화된 프롬프트를 사용해 모델 591개의 성능 지표를 직접 측정합니다.

차트에서 모델 이름이나 행을 클릭하면 상세 지표와 비슷한 모델과의 직접 비교가 있는 전용 페이지를 볼 수 있습니다. 모델 선택기를 사용해 각 차트에 표시할 모델을 직접 정할 수도 있습니다. 리더보드 보기