Microsoft launches Phi-4-Reasoning-Plus, a small, powerful, open weights reasoning model!

Microsoft launches Phi-4-Reasoning-Plus, a small, powerful, open weights reasoning model!

The release demonstrates that with carefully curated data and training techniques, small models can deliver strong reasoning performance.

Microsoft launches Phi-4-Reasoning-Plus, a small, powerful, open weights reasoning model! – RamaOnHealthcare

Microsoft Research has announced the release of Phi-4-reasoning-plus, an open-weight language model built for tasks requiring deep, structured reasoning.Building on the architecture of the previously released Phi-4, the new model integrates supervised fine-tuning and reinforcement learning to deliver improved performance on benchmarks in mathematics, science, coding, and logic-based tasks.Phi-4-reasoning-plus is a 14-billion parameter dense deco…

Microsoft: Our Phi-4-reasoning takes on larger models, matches DeepSeek-R1 performance

Microsoft has released Phi-4-reasoning and Phi-4-reasoning-plus, 14B-parameter small language models fine-tuned for complex reasoning tasks. Read more...

Microsoft’s Phi-4 Reasoning Models Push the Limits of Small AI

For businesses looking to adopt AI without breaking the compute bank—or shipping their data to the cloud—Microsoft's Phi family is very compelling. On Wednesday, the company released three new open-weight small language models: Phi-4-reasoning, Phi-4-reasoning-plus, and Phi-4-mini-reasoning. Key Points:The Phi-4-reasoning models mark a new era for small language models with impressive reasoning capabilitiesDespite being only 14B parameters, Phi-…

One year of Phi: Small language models making big leaps in AI

Microsoft continues to add to the conversation by unveiling its newest models, Phi-4-reasoning, Phi-4-reasoning-plus, and Phi-4-mini-reasoning. Learn more.