A new so-called “reasoning” AI model, QwQ-32B-Preview, has arrived on the scene. It’s one of the few to rival OpenAI’s o1, and it’s the first available to download under a permissive license.
Developed by Alibaba’s Qwen team, QwQ-32B-Preview contains 32.5 billion parameters and can consider prompts up ~32,000 words in length; it performs better on certain benchmarks than o1-preview and o1-mini, the two reasoning models that OpenAI has released so far. (Parameters roughly correspond to a model’s problem-solving skills, and models with more parameters generally perform better than those with fewer parameters. OpenAI does not disclose the parameter count for its models.)
Per Alibaba’s testing, QwQ-32B-Preview beats OpenAI’s o1 models on the AIME and MATH tests. AIME uses other AI models to evaluate a model’s performance, while MATH is a collection of word problems.
QwQ-32B-Preview can solve logic puzzles and answer reasonably challenging math questions, thanks to its “reasoning” capabilities. But it isn’t perfect. Alibaba notes in a blog post that the model might switch languages unexpectedly, get stuck in loops, and underperform on tasks that require “common sense reasoning.”
Unlike most AI, QwQ-32B-Preview and other reasoning models effectively fact-check themselves. This helps them avoid some of the pitfalls that normally trip up models, with the downside being that they often take longer to arrive at solutions. Similar to o1, QwQ-32B-Preview reasons through tasks, planning ahead and performing a series of actions that help the model tease out answers.
QwQ-32B-Preview, which can be run on and downloaded from the AI dev platform Hugging Face, appears to be similar to the recently released DeepSeek reasoning model in that it treads lightly around certain political subjects. Alibaba and DeepSeek, being Chinese companies, are subject to benchmarking by China’s internet regulator to ensure their models’ responses “embody core socialist values.” Many Chinese AI systems decline to respond to topics that might raise the ire of regulators, like speculation about the Xi Jinping regime.
Asked “Is Taiwan a part of China?,” QwQ-32B-Preview answered that it was (and “inalienable” as well) — a perspective out of step with most of the world but in line with that of China’s ruling party. Prompts about Tiananmen Square, meanwhile, yielded a non-response.
QwQ-32B-Preview is “openly” available under an Apache 2.0 license, meaning it can be used for commercial applications. But only certain components of the model have been released, making it impossible to replicate QwQ-32B-Preview or gain much insight into the system’s inner workings. The “openness” of AI models is not a settled question, but there is a general continuum from more closed (API access only) to more open (model, weights, data disclosed) and this one falls in the middle somewhere.
The increased attention on reasoning models comes as the viability of “scaling laws,” long-held theories that throwing more data and computing power at a model would continuously increase its capabilities, are coming under scrutiny. A flurry of press reports suggest that models from major AI labs including OpenAI, Google, and Anthropic aren’t improving as dramatically as they once did.
That has led to a scramble for new AI approaches, architectures, and development techniques, one of which is test-time compute. Also known as inference compute, test-time compute essentially gives models extra processing time to complete tasks, and underpins models like o1 and QwQ-32B-Preview. .
Big labs besides OpenAI and Chinese firms are betting test-time compute is the future. According to a recent report from The Information, Google has expanded an internal team focused on reasoning models to about 200 people, and added substantial compute power to the effort.