QwQ 32B
AlibabaQwenOpen WeightApache 2.0 · Commercial OK
Description
A 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/endless reasoning patterns.
Release Date
2025-03-05
Parameters
32.5B
Context Length
—
Modalities
—
Capability Radar
35
general
57
coding
54
reasoning
41
scienceest.
70
agents
0
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 147 | 51.0 | AA |
| General Ranking | 236 | 44.0 | AA |
| Math Reasoning | 171 | 53.0 | AA |
| Science | 233 | 45.0 | AA |
Benchmark Scores (LLM Stats)
Biology
GPQA
65.2%SR
Code
LiveCodeBench
63.4%SR
General
IFEval
83.9%SR
LiveBench
73.1%SR
BFCL
66.4%SR
Math
MATH-500
90.6%SR
AIME 2024
79.5%SR
AA Evaluation Indices
Math Index29.0
Intelligence Index19.7
Math 5001.0
Aime0.8
Mmlu Pro0.8
Livecodebench0.6
Gpqa0.6
Ifbench0.4
Scicode0.4
Aime 250.3
Lcr0.3
Hle0.1
LLM Stats Category Scores
Structured Output80
Instruction Following80
Math80
Tool Calling70
Biology70
Chemistry70
General70
Physics70
Reasoning70
Code60
Pricing
Input Price$0.66 / 1M tokens
Output Price$1 / 1M tokens
Blended Price (3:1)$0.745 / 1M tokens
Speed
Tokens/sec31.7 tokens/s
Time to First Token0.40s
Time to Answer79.07s
Available Providers
(LS internal units)No provider data available