QwQ 32B-Preview
AlibabaQwen開源權重Apache 2.0 · 商用許可
描述
An experimental research model focused on advancing AI reasoning capabilities, particularly excelling in mathematics and programming. Features deep introspection and self-questioning abilities while having some limitations in language mixing and recursive reasoning patterns.
發布日期
2024-11-27
參數規模
32.5B
上下文長度
131K
支援模態
text
能力雷達圖
24
general
34
coding
61
reasoning
40
science
53
agents
0
multimodal
排行榜排名
基準測試分數 (LLM Stats)
(LLM Stats (zeroeval))Math
MATH-500
90.6%自報
AIME 2024
50.0%自報
Reasoning
GPQANYU + Cohere + Anthropic (2023)
65.2%自報
LiveCodeBench
50.0%自報
AA 評測指數
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))91.0
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))64.8
Gpqa(NYU + Cohere + Anthropic (2023))55.7
Aime(MAA (Mathematical Association of America))45.3
Livecodebench(UC Berkeley + MIT + Cornell (2024))33.7
Intelligence Index(Artificial Analysis)7.6
Hle(Center for AI Safety + Scale AI (2025))3.9
LLM Stats 分類評分
(LLM Stats (zeroeval))Math70
Physics70
Biology70
Chemistry70
Reasoning60
General60
Code50
定價
輸入價格免費
輸出價格免費
混合價格(3:1)免費
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
1 個供應商
供應商輸入輸出
1Alibaba (China)
$0.287
$0.861
比較該模型在不同 API 供應商之間的定價。