NishMath

Alibaba has recently launched Qwen-32B, a new reasoning model, which demonstrates performance levels on par with DeepMind's R1 model. This development signifies a notable achievement in the field of AI, particularly for smaller models. The Qwen team showcased that reinforcement learning on a strong base model can unlock reasoning capabilities for smaller models that enhances their performance to be on par with giant models.

Qwen-32B not only matches but also surpasses models like DeepSeek-R1 and OpenAI's o1-mini across key industry benchmarks, including AIME24, LiveBench, and BFCL. This is significant because Qwen-32B achieves this level of performance with only approximately 5% of the parameters used by DeepSeek-R1, resulting in lower inference costs without compromising on quality or capability. Groq is offering developers the ability to build FAST with Qwen QwQ 32B on GroqCloud™, running the 32B parameter model at ~400 T/s. This model is proving to be very competitive in reasoning benchmarks and is one of the top open source models being used.

The Qwen-32B model was explicitly designed for tool use and adapting its reasoning based on environmental feedback, which is a huge win for AI agents that need to reason, plan, and adapt based on context (outperforms R1 and o1-mini on the Berkeley Function Calling Leaderboard). With these capabilities, Qwen-32B shows that RL on a strong base model can unlock reasoning capabilities for smaller models that enhances their performance to be on par with giant models.

ImgSrc: i0.wp.com

References :

• Last Week in AI: LWiAI Podcast #202 - Qwen-32B, Anthropic's $3.5 billion, LLM Cognitive Behaviors
• Groq: A Guide to Reasoning with Qwen QwQ 32B
• Last Week in AI: #202 - Qwen-32B, Anthropic's $3.5 billion, LLM Cognitive Behaviors
• Sebastian Raschka, PhD: This article explores recent research advancements in reasoning-optimized LLMs, with a particular focus on inference-time compute scaling that have emerged since the release of DeepSeek R1.
• Analytics Vidhya: China is rapidly advancing in AI, releasing models like DeepSeek and Qwen to rival global giants.
• Last Week in AI: Alibaba’s New QwQ 32B Model is as Good as DeepSeek-R1
• Maginative: Despite having far fewer parameters, Qwen’s new QwQ-32B model outperforms DeepSeek-R1 and OpenAI’s o1-mini in mathematical benchmarks and scientific reasoning, showcasing the power of reinforcement learning.

Classification:

• HashTags: #AI #LargeLanguageModels #OpenSourceAI
• Company: Alibaba
• Target: AI community
• Product: Qwen-32B
• Feature: reasoning model
• Type: AI
• Severity: Informative