Qwen3.7 Max

AlibabaQwenProprietary

설명

Qwen3.7 Max is Alibaba Cloud Qwen Team's proprietary flagship model for agent-driven workflows. It is designed for coding agents, office automation, MCP and multi-agent orchestration, and long-horizon autonomous execution, with a 1 million token context window and up to 65,536 output tokens. Qwen reports strong agentic coding results including 69.7 on Terminal-Bench 2.0-Terminus, 80.4 on SWE-bench Verified, 60.6 on SWE-Pro, and 78.3 on SWE-Multilingual, alongside 92.4 on GPQA Diamond and 97.1 on HMMT 2026 Feb.

출시일

2026-05-19

파라미터

—

컨텍스트 길이

1.0M

모달리티

text

능력 레이더

general

coding

reasoning

science

agents

multimodal

랭킹

도메인	#순위	점수	소스
에이전트형 역량	12	65.0	LS
코딩 랭킹	66	82.0	AA
종합 랭킹	35	73.0	AA
수학 추론	44	85.0	LB
과학	55	77.0	AA

벤치마크 점수 (LLM Stats)

(LLM Stats (zeroeval))

Agents

QwenSVG

1608.00 / 2000자체 보고

Kernel Bench L3

96.0%자체 보고

SpreadSheetBench-v1

87.0%자체 보고

CoWorkBench

67.2%자체 보고

MCP-Mark

60.8%자체 보고

QwenWorldBench

57.3%자체 보고

Finance Agent v2

48.4%

VITA-Bench

47.9%자체 보고

Chat

IFEvalGoogle Research (2023)

94.3%자체 보고

Code

QwenWebBench

1568.00 / 2000자체 보고

Claw-Eval

65.2%자체 보고

ZClawBench

64.3%자체 보고

SkillsBench

59.2%자체 보고

NL2Repo

47.2%자체 보고

General

MAXIFE

89.2%자체 보고

Include

86.2%자체 보고

NOVA-63

59.0%자체 보고

Instruction Following

IFBench

79.1%자체 보고

Language

MMLU-Redux

95.0%자체 보고

MMMLU

90.3%자체 보고

MMLU-Pro

89.6%자체 보고

MMLU-ProX

87.0%자체 보고

WMT24++

85.8%자체 보고

Long Context

MRCR 128K (8-needle)

90.4%자체 보고

Math

HMMT Feb 26

97.1%자체 보고

IMO-AnswerBench

90.0%자체 보고

PolyMATH

86.5%자체 보고

LiveBench

74.3%

MathArena Apex

44.5%자체 보고

Reasoning

GPQANYU + Cohere + Anthropic (2023)

92.4%자체 보고

LiveCodeBench v6

91.6%자체 보고

Global PIQA

91.4%자체 보고

SWE-Bench Verified

80.4%자체 보고

SWE-bench Multilingual

78.3%자체 보고

MCP Atlas

76.4%자체 보고

SuperGPQA

73.6%자체 보고

Terminal-Bench 2.0Stanford × Laude Institute (2026)

69.7%자체 보고

SWE-Bench ProPrinceton NLP (2024)

60.6%자체 보고

SciCode

53.5%자체 보고

Humanity's Last Exam

41.4%자체 보고

CritPT

11.4%자체 보고

Tool Calling

BFCL-V4

75.0%자체 보고

AA 평가 지수

(Artificial Analysis)

Tau2(Sierra + U Toronto + Vector Institute (2025))

94.7

Gpqa(NYU + Cohere + Anthropic (2023))

92.3

Ifbench(Google Research (2023))

80.5

Lcr(Artificial Analysis)

79.0

Terminalbench V2 1

74.5

Coding Index(Artificial Analysis)

66.0

Terminalbench Hard(Stanford × Laude Institute (2026))

50.8

Scicode(UIUC + Argonne National Lab (2024))

49.5

Hle(Center for AI Safety + Scale AI (2025))

40.5

Intelligence Index(Artificial Analysis)

29.5

Tau Banking

11.8

Terminalbench V4 0

1.5

LLM Stats 카테고리 점수

(LLM Stats (zeroeval))

Chat

Instruction Following

Language

Multimodal

Spatial Reasoning

Structured Output

Legal

Physics

Productivity

Frontend Development

Healthcare

Math

Reasoning

Finance

General

Biology

Chemistry

Code

Economics

Tool Calling

Agents

Vision

가격

입력 가격$2.5 / 1M 토큰

출력 가격$7.5 / 1M 토큰

혼합 가격 (3:1)$3.75 / 1M 토큰

캐시 읽기 가격$0.5 / 1M 토큰

캐시 쓰기 가격$3.125 / 1M 토큰

속도

토큰/초0.0

첫 토큰 지연0.00s

첫 응답 지연0.00s

공급자 가격 순위

25개 공급자

최저가: Novita최고가: Modelis

공급자입력출력

1Novita최저가

2DeepInfra

$0.00001

3Together

$0.00001

4AIHubMix

$0.0282

$0.1128

5Alibaba (China)

$0.02962

$0.1185

6Alibaba

$0.03

$0.13

7NanoGPT

$0.03

$0.13

8OpenRouter

$0.03

$0.13

9Kilo Gateway

$0.03

$0.13

10DevPass (LLM Gateway)

$0.03

$0.13

11OrcaRouter

$0.03

$0.13

12Standard Compute

$0.03

$0.13

13CrossModel

$0.04

$0.13

14Charm Hyper

$0.2

$0.8

15Merge Gateway

$0.825

$2.4755

16ZenMux

$1.25

$3.75

17Novita AI

$1.25

$3.75

18Ofox

$1.71

$5.14

19302.AI

$1.8

$5.3

20Abacus

$2.5

$7.5

21Requesty

$2.5

$7.5

22EmpirioLabs AI

$2.5

$7.5

23Impossibl

$2.5

$7.5

24NEAR AI Cloud

$2.8

$7.5

25Modelis

이 모델의 다양한 API 공급자 간 가격 비교.

외부 링크

LLM Stats Artificial Analysis