QwQ 32B
Intelligence
19.7
#260/521
Coding
—
Math
29
#189/265
Speed
33 tok/s
TTFT: 438.00s
Pricing
$0.66 / $1.00
per 1M tokens (in/out)
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.
QwQ 32B is Alibaba’s offering for advanced natural language processing tasks. It processes at 33.191 tokens per second and is priced at $0.66 per million input tokens, targeting professional users.
When to Use QwQ 32B
✓ Best For
- Text generation and completion
- Data analysis and summarization
- Chatbot and virtual assistant development
✗ Not Ideal For
- High-speed real-time applications
- Users needing extensive coding capabilities
How QwQ 32B Compares
Intelligence Index · Higher is better
AlibabaGoogleMistral
Benchmark Profile
Output Speed · tok/s
KimiAlibabaZ AIGoogle
Math Index
MistralAlibabaOpenAI
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (17)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 19.7 | |
| Math Index | 29 | |
| MMLU-Pro | 764% | |
| GPQA | 593% | |
| LiveCodeBench | 631% | |
| HLE | 82% | |
| SciCode | 35.8% | |
| IFBench | 38.8% | |
| LCR | 25% | |
| AIME | 78% | |
| AIME 2025 | 29% | |
| MATH 500 | 95.7% | |
| AIME 2024 | 79.5% | |
| BFCL | 66.4% | |
| IFEval | 83.9% | |
| LiveBench | 73.1% | |
| MATH-500 | 90.6% |
Data: Artificial Analysis · Updated: April 2, 2026
Frequently Asked Questions (15)
When was QwQ 32B released?
QwQ 32B was released on March 5, 2025.
Who created QwQ 32B?
QwQ 32B was created by Alibaba.
How intelligent is QwQ 32B?
QwQ 32B scores 20 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 15).
How much does QwQ 32B cost?
QwQ 32B costs $0.66 per 1M input tokens (at the higher end, median: $0.18) and $1.00 per 1M output tokens (somewhat higher than average, median: $0.58), based on the median across providers serving the model.
What is QwQ 32B API pricing?
QwQ 32B costs $0.66 per 1M input tokens and $1.00 per 1M output tokens (based on the median across providers serving the model). For a blended rate (3:1 input to output ratio), this is $0.74 per 1M tokens. Pricing may vary by provider.
How verbose is QwQ 32B?
When evaluated on the Intelligence Index, QwQ 32B generated 30M output tokens, which is somewhat higher than average compared to other open weight models of similar size (median: 20M).
Is QwQ 32B a reasoning model?
Yes, QwQ 32B is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
What input modalities does QwQ 32B support?
QwQ 32B supports text input.
What output modalities does QwQ 32B support?
QwQ 32B supports text output.
Can QwQ 32B process images?
No, QwQ 32B does not support image input. It can only process text.
Is QwQ 32B multimodal?
No, QwQ 32B is not multimodal. It only supports text input.
What is the context window of QwQ 32B?
QwQ 32B has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Is QwQ 32B open source?
Yes, QwQ 32B is open weights. The model weights are publicly available and can be downloaded for self-hosting.
How many parameters does QwQ 32B have?
QwQ 32B has 32.8 billion parameters.
What is the license for QwQ 32B?
QwQ 32B is released under the Apache 2.0 license. This license allows commercial use.
