跳轉到主要內容

Qwen3 32B (Non-reasoning)

AlibabaQwen開源權重Apache 2.0 · 商用許可

描述

Qwen3-32B is a large language model from Alibaba's Qwen3 series. It features 32.8 billion parameters, a 128k token context window, support for 119 languages, and hybrid thinking modes allowing switching between deep reasoning and fast responses. It demonstrates strong performance in reasoning, instruction-following, and agent capabilities.

發布日期
2025-04-28
參數規模
32.8B
上下文長度
131K
支援模態
text

能力雷達圖

27
general
29
coding
36
reasoning
35
science
70
agents
0
multimodal

排行榜排名

領域#排名分數來源
程式碼能力榜463
16.0
AA
通用能力榜397
33.0
AA
科學能力387
35.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Code

LiveCodeBench65.7%自報
Aider50.2%自報

Creativity

Arena Hard93.8%自報

General

LiveBench74.9%自報
MultiLF73.0%自報
BFCL70.3%自報

Math

AIME 202481.4%自報
AIME 202572.9%自報
CodeForces0.66 / 3000自報

AA 評測指數

(Artificial Analysis)
Math Index(Artificial Analysis)
19.7
Intelligence Index(Artificial Analysis)
8.5
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
0.9
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.7
Gpqa(NYU + Cohere + Anthropic (2023))
0.5
Ifbench(Google Research (2023))
0.3
Aime(MAA (Mathematical Association of America))
0.3
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.3
Scicode(UIUC + Argonne National Lab (2024))
0.3
Aime 25(MAA (Mathematical Association of America))
0.2
Hle(Center for AI Safety + Scale AI (2025))
0.0
Lcr(Artificial Analysis)
0.0

LLM Stats 分類評分

(LLM Stats (zeroeval))
Creativity
90
Writing
90
Math
70
Reasoning
70
General
70
Tool Calling
70
Code
60

定價

輸入價格$0.7 / 1M tokens
輸出價格$2.8 / 1M tokens
混合價格(3:1)$1.225 / 1M tokens

速度

Tokens/秒0.0
首Token延遲0.00s
首回答延遲0.00s

供應商價格排行

供應商價格排行

9 個供應商

最便宜: Novita最貴: Alibaba
供應商輸入輸出
1Novita最便宜
$0
$0
2DeepInfra
$0
$0
3Sambanova
$0
$0
4OVHcloud AI Endpoints
$0.09
$0.25
5Cortecs
$0.099
$0.299
6LLM Gateway
$0.1
$0.3
7Alibaba (China)
$0.287
$1.147
8Helicone
$0.29
$0.59
9Alibaba主要
$0.7
$2.8

比較該模型在不同 API 供應商之間的定價。

外部連結