QwQ 32B-Preview
AlibabaQwenOpen WeightApache 2.0 · Commercial OK
Description
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.
Release Date
2024-11-27
Parameters
32.5B
Context Length
131K
Modalities
text
Capability Radar
24
general
34
coding
61
reasoning
40
science
53
agents
0
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 386 | 37.0 | AA |
| General Ranking | 488 | 29.0 | AA |
| Science | 483 | 29.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Math
MATH-500
90.6%SR
AIME 2024
50.0%SR
Reasoning
GPQANYU + Cohere + Anthropic (2023)
65.2%SR
LiveCodeBench
50.0%SR
AA Evaluation Indices
(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 Category Scores
(LLM Stats (zeroeval))Math70
Physics70
Biology70
Chemistry70
Reasoning60
General60
Code50
Pricing
Input PriceFree
Output PriceFree
Blended Price (3:1)Free
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
Provider Price Ranking
1 providers
ProviderInputOutput
1Alibaba (China)
$0.287
$0.861
Compare pricing across different API providers for this model.