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
25
general
27
coding
61
reasoning
27
science
51
agents
0
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 307 | 37.0 | AA |
| General Ranking | 411 | 32.0 | AA |
| Science | 496 | 22.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Biology
GPQANYU + Cohere + Anthropic (2023)
65.2%SR
Code
LiveCodeBench
50.0%SR
Math
MATH-500
90.6%SR
AIME 2024
50.0%SR
AA Evaluation Indices
(Artificial Analysis)Intelligence Index(Artificial Analysis)9.1
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))0.9
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))0.6
Gpqa(NYU + Cohere + Anthropic (2023))0.6
Aime(MAA (Mathematical Association of America))0.5
Livecodebench(UC Berkeley + MIT + Cornell (2024))0.3
Hle(Center for AI Safety + Scale AI (2025))0.0
Scicode(UIUC + Argonne National Lab (2024))0.0
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
No provider data available