Qwen3 30B A3B 2507 (Reasoning)

AlibabaQwen오픈 웨이트Apache 2.0 · 상업적 사용 가능

설명

Qwen3-30B-A3B is a smaller Mixture-of-Experts (MoE) model from the Qwen3 series by Alibaba, with 30.5 billion total parameters and 3.3 billion activated parameters. Features hybrid thinking/non-thinking modes, support for 119 languages, and enhanced agent capabilities. It aims to outperform previous models like QwQ-32B while using significantly fewer activated parameters.

출시일

2025-07-30

파라미터

30.5B

컨텍스트 길이

131K

모달리티

text

능력 레이더

general

coding

reasoning

science

agents

multimodal

랭킹

도메인	#순위	점수	소스
코딩 랭킹	301	37.0	AA
종합 랭킹	297	43.0	AA
과학	265	48.0	AA

벤치마크 점수 (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)

65.8%자체 보고

Code

LiveCodeBench

62.6%자체 보고

Communication

Multi-IF

72.2%자체 보고

Creativity

Arena Hard

91.0%자체 보고

General

LiveBench

74.3%자체 보고

BFCL

69.1%자체 보고

Math

AIME 2024

80.4%자체 보고

AIME 2025

70.9%자체 보고

AA 평가 지수

(Artificial Analysis)

Math Index(Artificial Analysis)

56.3

Intelligence Index(Artificial Analysis)

14.6

Coding Index(Artificial Analysis)

12.1

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

1.0

Aime(MAA (Mathematical Association of America))

0.9

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

0.8

Gpqa(NYU + Cohere + Anthropic (2023))

0.7

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

0.7

Lcr(Artificial Analysis)

0.6

Aime 25(MAA (Mathematical Association of America))

0.6

Ifbench(Google Research (2023))

0.5

Scicode(UIUC + Argonne National Lab (2024))

0.3

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

0.3

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

0.1

Tau Banking

0.1

Terminalbench Hard(Stanford × Laude Institute (2026))

0.1

Terminalbench V2 1

0.0

LLM Stats 카테고리 점수

(LLM Stats (zeroeval))

Creativity

Writing

Math

Instruction Following

Language

Physics

Reasoning

Structured Output

General

Biology

Chemistry

Communication

Tool Calling

Code

가격

입력 가격$0.2 / 1M 토큰

출력 가격$2.4 / 1M 토큰

혼합 가격 (3:1)$0.75 / 1M 토큰

속도

토큰/초0.0

첫 토큰 지연0.00s

첫 응답 지연0.00s

공급자 가격 순위

4개 공급자

최저가: DeepInfra최고가: Alibaba

공급자입력출력

1DeepInfra최저가

2Novita

3Fireworks

4Alibaba주요

$0.2

$2.4

이 모델의 다양한 API 공급자 간 가격 비교.

외부 링크

LLM Stats Artificial Analysis