This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.

Alibaba has launched a newer model, Qwen3 Max Thinking. We suggest considering it instead.

For more information, see comparison of Qwen3 Max Thinking to other models and API provider benchmarks for Qwen3 Max Thinking.

Qwen3 Max Thinking (Preview) logo
Alibaba
•

Proprietary model

•

Released November 2025

Qwen3 Max Thinking (Preview) 지능, 성능 및 가격 분석

API 제공업체 벤치마크

모델 요약

지능

25
Artificial Analysis Intelligence Index
지능: 4단계 중 2단계.

속도

62.0
초당 출력 토큰 수
속도: 4단계 중 2단계.

입력 가격

US$1.20
100만 토큰당 USD
입력 가격: 4단계 중 2단계.

출력 가격

US$6.00
100만 토큰당 USD
출력 가격: 4단계 중 2단계.

장황성

N/A
Intelligence Index의 출력 토큰 수
장황성: 4단계 중 알 수 없음.

가격이 비슷한 다른 모델과 비교하면 Qwen3 Max Thinking (Preview)의 지능은 평균보다 낮지만, 가격은 합리적인 수준입니다. 이 모델의 지원 입력은 텍스트, 출력은 텍스트이며, 컨텍스트 창은 262k토큰입니다.

Qwen3 Max Thinking (Preview)의 Artificial Analysis Intelligence Index 점수는 25점으로, 비교 가능한 모델 중 평균 이하입니다(중앙값: 32).

Qwen3 Max Thinking (Preview)의 입력 토큰 100만 개당 가격은 $1.20(보통 수준의 가격, 중앙값: $1.75)이며, 출력 토큰 100만 개당 가격은 $6.00(보통 수준의 가격, 중앙값: $10.00)입니다.

Qwen3 Max Thinking (Preview)의 속도는 초당 62토큰으로 평균보다 느립니다(72).

추론예

이 페이지에는 모델의 추론 버전이 표시됩니다.

비추론 버전도 있을 수 있습니다.

입력 모달리티

지원: 텍스트

출력 모달리티

지원: 텍스트

컨텍스트 창262k
Arial 12포인트 기준 A4 약 393페이지

동일한 등급의 모델과 지표를 비교합니다.

  • 비추론 모델 → 다른 비추론 모델과만 비교
  • 추론 모델 → 추론 및 비추론 모델 모두와 비교
  • 오픈 웨이트 모델 → 같은 크기 등급의 다른 오픈 웨이트 모델과만 비교:
    • 초소형: 파라미터 ≤4B
    • 소형: 파라미터 4B~40B
    • 중형: 파라미터 40B~150B
    • 대형: 파라미터 >150B
  • 독점 모델 → 입력/출력 가격을 3:1로 혼합해 같은 가격대의 독점 모델 및 오픈 웨이트 모델과 비교:
    • 100만 토큰당 <$0.15
    • 100만 토큰당 $0.15~$1
    • 100만 토큰당 >$1

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
Estimate (independent evaluation forthcoming)
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
Estimate (independent evaluation forthcoming)
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-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.

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.

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).

자주 묻는 질문

Qwen3 Max Thinking (Preview)에 관한 일반적인 질문

Qwen3 Max Thinking (Preview) 모델은 2025년 11월 3일에 출시되었습니다.

Qwen3 Max Thinking (Preview) 모델은 Alibaba에서 개발했습니다.

Qwen3 Max Thinking (Preview)의 Artificial Analysis Intelligence Index 추정 점수는 25점으로, 가격대가 비슷한 다른 추론 모델 중 평균 이하입니다(중앙값: 32).

Qwen3 Max Thinking (Preview) 모델은 초당 62.0개의 출력 토큰을 생성하며(Alibaba API 기준), 가격대가 비슷한 다른 추론 모델과 비교하면 평균보다 낮습니다(중앙값: 72.2 t/s).

Qwen3 Max Thinking (Preview)의 첫 토큰까지 걸린 시간(TTFT)은 4.03초이며(Alibaba API 기준), 가격대가 비슷한 다른 추론 모델과 비교하면 평균보다 다소 높습니다(중앙값: 2.83초).

Qwen3 Max Thinking (Preview)의 입력 토큰 100만 개당 가격은 $1.20(평균보다 낮음, 중앙값: $1.75)이며, 출력 토큰 100만 개당 가격은 $6.00(평균보다 낮음, 중앙값: $10.00)입니다(Alibaba API 기준).

Qwen3 Max Thinking (Preview)의 입력 토큰 100만 개당 가격은 $1.20, 출력 토큰 100만 개당 가격은 $6.00입니다(Alibaba API 기준). 캐시 적중/입력/출력 비율을 7:2:1로 가정한 혼합 가격은 100만 토큰당 $1.68입니다. 가격은 제공업체마다 다를 수 있습니다. 제공업체 가격 비교

예. Qwen3 Max Thinking (Preview) 모델은 추론 모델입니다. 답변하기 전에 확장 사고 또는 연쇄적 사고 추론으로 복잡한 문제를 해결합니다.

Qwen3 Max Thinking (Preview) 모델은 텍스트 입력을 지원합니다.

Qwen3 Max Thinking (Preview) 모델은 텍스트 출력을 지원합니다.

아니요. Qwen3 Max Thinking (Preview) 모델은 이미지 입력을 지원하지 않으며 텍스트만 처리할 수 있습니다.

아니요. Qwen3 Max Thinking (Preview) 모델은 멀티모달 모델이 아니며 텍스트 입력만 지원합니다.

Qwen3 Max Thinking (Preview)의 컨텍스트 창은 260k토큰입니다. 모델이 단일 요청에서 처리할 수 있는 텍스트와 대화 기록의 양을 결정합니다.

아니요. Qwen3 Max Thinking (Preview) 모델은 독점 모델이며 모델 웨이트가 공개되어 있지 않습니다.

Qwen3 Max Thinking (Preview) 모델은 독점 모델이며 Alibaba에서 모델 크기나 파라미터 수를 공개하지 않았습니다.

Qwen3 Max Thinking (Preview)의 Artificial Analysis Intelligence Index 점수는 25점입니다. 이 종합 벤치마크는 추론, 지식, 수학, 코딩 전반에서 모델을 평가합니다.

예. Qwen3 Max Thinking (Preview) 모델은 API 제공업체 1곳을 통해 제공됩니다. API 제공업체 비교

Qwen3 Max Thinking (Preview) 모델은 API 제공업체 1곳을 통해 제공됩니다. 제공업체 비교