Qwen3 235B A22B 2507 Instruct

AlibabaQwen오픈 웨이트Apache 2.0 · 상업적 사용 가능

설명

Qwen3-235B-A22B-Instruct-2507 is the updated instruct version of Qwen3-235B-A22B featuring significant improvements in general capabilities including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage. It provides substantial gains in long-tail knowledge coverage across multiple languages and markedly better alignment with user preferences in subjective and open-ended tasks.

출시일

2025-07-21

파라미터

235.0B

컨텍스트 길이

262K

모달리티

text

능력 레이더

general

coding

reasoning

science

agents

multimodal

랭킹

도메인	#순위	점수	소스
에이전트형 역량	53	52.0	LS
코딩 랭킹	292	40.0	AA
종합 랭킹	280	46.0	AA
과학	232	52.0	AA

벤치마크 점수 (LLM Stats)

(LLM Stats (zeroeval))

Agents

BFCL-v3

70.9%자체 보고

Biology

GPQANYU + Cohere + Anthropic (2023)

77.5%자체 보고

Chemistry

SuperGPQA

62.6%자체 보고

Code

Aider-Polyglot

57.3%자체 보고

Communication

WritingBench

85.2%자체 보고

Multi-IF

77.5%자체 보고

Tau2 Retail

71.3%자체 보고

Tau2 Airline

44.0%자체 보고

Creativity

Creative Writing v3

87.5%자체 보고

Arena-Hard v2

79.2%자체 보고

Factuality

SimpleQA

54.3%자체 보고

Finance

MMLU-Pro

83.0%자체 보고

MMLU-ProX

79.4%자체 보고

General

MMLU-Redux

93.1%자체 보고

IFEvalGoogle Research (2023)

88.7%자체 보고

MultiPL-E

87.9%자체 보고

CSimpleQA

84.3%자체 보고

Include

79.5%자체 보고

LiveBench 20241125

75.4%자체 보고

LiveCodeBench v6

51.8%자체 보고

Math

AIME 2025

70.3%자체 보고

HMMT25

55.4%자체 보고

PolyMATH

50.2%자체 보고

Reasoning

ZebraLogic

95.0%자체 보고

ARC-AGI

41.8%자체 보고

AA 평가 지수

(Artificial Analysis)

Math Index(Artificial Analysis)

71.7

Intelligence Index(Artificial Analysis)

18.4

Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))

1.0

Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))

0.8

Gpqa(NYU + Cohere + Anthropic (2023))

0.8

Aime(MAA (Mathematical Association of America))

0.7

Aime 25(MAA (Mathematical Association of America))

0.7

Livecodebench(UC Berkeley + MIT + Cornell (2024))

0.5

Ifbench(Google Research (2023))

0.5

Scicode(UIUC + Argonne National Lab (2024))

0.4

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

0.3

Lcr(Artificial Analysis)

0.3

Terminalbench Hard(Stanford × Laude Institute (2026))

0.2

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

0.1

LLM Stats 카테고리 점수

(LLM Stats (zeroeval))

Legal

Structured Output

Instruction Following

Language

Finance

Healthcare

Biology

Creativity

Writing

Math

Physics

Reasoning

General

Agents

Chemistry

Communication

Code

Economics

Tool Calling

Multimodal

Spatial Reasoning

Factuality

Vision

가격

입력 가격$0.7 / 1M 토큰

출력 가격$2.8 / 1M 토큰

혼합 가격 (3:1)$1.225 / 1M 토큰

속도

토큰/초0.0

첫 토큰 지연0.00s

첫 응답 지연0.00s

공급자 가격 순위

7개 공급자

최저가: Cortecs최고가: GreenPT

공급자입력출력

1Cortecs최저가

$0.069

$0.455

2LLM Gateway

$0.09

$0.58

3Venice AI

$0.15

$0.75

4302.AI

$0.29

$1.143

5Alibaba주요

$0.7

$2.8

6Scaleway

$0.75

$2.25

7GreenPT

$1.026

$3.078

이 모델의 다양한 API 공급자 간 가격 비교.

외부 링크

LLM Stats Artificial Analysis