Get the latest tech news

Alibaba releases Qwen with Questions, an open reasoning model that beats o1-preview


QwQ uses inference-time scaling to solve complex reasoning and planning questions, besting OpenAI's o1 in several benchmarks.

According to a blog post that was published along with the model’s release, “Through deep exploration and countless trials, we discovered something profound: when given time to ponder, to question, and to reflect, the model’s understanding of mathematics and programming blossoms like a flower opening to the sun… This process of careful reflection and self-questioning leads to remarkable breakthroughs in solving complex problems.” Marco-o1 uses Monte Carlo Tree Search(MCTS) and self-reflection at inference time to create different branches of reasoning and choose the best answers. Reports indicate that AI labs such as OpenAI, Google DeepMind, and Anthropic are getting diminishing returns on training larger models.

Get the Android app

Or read this on Venture Beat

Read more on:

Photo of preview

preview

Photo of questions

questions

Photo of Alibaba

Alibaba

Related news:

News photo

Alibaba-Backed Trendyol Is Said to Consider $1 Billion Fundraise

News photo

Alibaba's OpenAI Challenger: The New AI Reasoning Titan

News photo

QwQ: Alibaba's O1-like reasoning LLM