Microsoft continues so as to add to the dialog by unveiling its latest fashions, Phi-4-reasoning, Phi-4-reasoning-plus, and Phi-4-mini-reasoning.
A brand new period of AI
One yr in the past, Microsoft launched small language fashions (SLMs) to clients with the discharge of Phi-3 on Azure AI Foundry, leveraging analysis on SLMs to broaden the vary of environment friendly AI fashions and instruments out there to clients.
At present, we’re excited to introduce Phi-4-reasoning, Phi-4-reasoning-plus, and Phi-4-mini-reasoning—marking a brand new period for small language fashions and as soon as once more redefining what is feasible with small and environment friendly AI.
Reasoning fashions, the following step ahead
Reasoning fashions are skilled to leverage inference-time scaling to carry out advanced duties that demand multi-step decomposition and inner reflection. They excel in mathematical reasoning and are rising because the spine of agentic functions with advanced, multi-faceted duties. Such capabilities are sometimes discovered solely in massive frontier fashions. Phi-reasoning fashions introduce a brand new class of small language fashions. Utilizing distillation, reinforcement studying, and high-quality knowledge, these fashions steadiness dimension and efficiency. They’re sufficiently small for low-latency environments but keep sturdy reasoning capabilities that rival a lot larger fashions. This mix permits even resource-limited gadgets to carry out advanced reasoning duties effectively.
Phi-4-reasoning and Phi-4-reasoning-plus
Phi-4-reasoning is a 14-billion parameter open-weight reasoning mannequin that rivals a lot bigger fashions on advanced reasoning duties. Educated by way of supervised fine-tuning of Phi-4 on rigorously curated reasoning demonstrations from OpenAI o3-mini, Phi-4-reasoning generates detailed reasoning chains that successfully leverage further inference-time compute. The mannequin demonstrates that meticulous knowledge curation and high-quality artificial datasets permit smaller fashions to compete with bigger counterparts.
Phi-4-reasoning-plus builds upon Phi-4-reasoning capabilities, additional skilled with reinforcement studying to make the most of extra inference-time compute, utilizing 1.5x extra tokens than Phi-4-reasoning, to ship greater accuracy.
Regardless of their considerably smaller dimension, each fashions obtain higher efficiency than OpenAI o1-mini and DeepSeek-R1-Distill-Llama-70B at most benchmarks, together with mathematical reasoning and Ph.D. stage science questions. They obtain efficiency higher than the total DeepSeek-R1 mannequin (with 671-billion parameters) on the AIME 2025 take a look at, the 2025 qualifier for the USA Math Olympiad. Each fashions can be found on Azure AI Foundry and HuggingFace, right here and right here.
Phi-4-reasoning fashions introduce a serious enchancment over Phi-4, surpass bigger fashions like DeepSeek-R1-Distill-70B and method Deep-Search-R1 throughout numerous reasoning and normal capabilities, together with math, coding, algorithmic downside fixing, and planning. The technical report gives in depth quantitative proof of those enhancements by means of numerous reasoning duties.
Phi-4-mini-reasoning
Phi-4-mini-reasoning is designed to satisfy the demand for a compact reasoning mannequin. This transformer-based language mannequin is optimized for mathematical reasoning, offering high-quality, step-by-step downside fixing in environments with constrained computing or latency. Tremendous-tuned with artificial knowledge generated by Deepseek-R1 mannequin, Phi-4-mini-reasoning balances effectivity with superior reasoning potential. It’s very best for academic functions, embedded tutoring, and light-weight deployment on edge or cellular techniques, and is skilled on over a million numerous math issues spanning a number of ranges of problem from center college to Ph.D. stage. Check out the mannequin on Azure AI Foundry or HuggingFace right now.
For extra details about the mannequin, learn the technical report that gives further quantitative insights.
Phi’s evolution over the past yr has frequently pushed this envelope of high quality vs. dimension, increasing the household with new options to deal with numerous wants. Throughout the size of Home windows 11 gadgets, these fashions can be found to run regionally on CPUs and GPUs.
As Home windows works in direction of creating a brand new sort of PC, Phi fashions have develop into an integral a part of Copilot+ PCs with the NPU-optimized Phi Silica variant. This extremely environment friendly and OS-managed model of Phi is designed to be preloaded in reminiscence, and out there with blazing quick time to first token responses, and energy environment friendly token throughput so it may be concurrently invoked with different functions working in your PC.
It’s utilized in core experiences like Click on to Do, offering helpful textual content intelligence instruments for any content material in your display, and is out there as developer APIs to be readily built-in into functions—already being utilized in a number of productiveness functions like Outlook, providing its Copilot abstract options offline. These small however mighty fashions have already been optimized and built-in for use throughout a number of functions throughout the breadth of our PC ecosystem. The Phi-4-reasoning and Phi-4-mini-reasoning fashions leverage the low-bit optimizations for Phi Silica and might be out there to run quickly on Copilot+ PC NPUs.
Security and Microsoft’s method to accountable AI
At Microsoft, accountable AI is a elementary precept guiding the event and deployment of AI techniques, together with our Phi fashions. Phi fashions are developed in accordance with Microsoft AI ideas: accountability, transparency, equity, reliability and security, privateness and safety, and inclusiveness.
The Phi household of fashions has adopted a strong security post-training method, leveraging a mixture of Supervised Tremendous-Tuning (SFT), Direct Desire Optimization (DPO), and Reinforcement Studying from Human Suggestions (RLHF) methods. These strategies make the most of numerous datasets, together with publicly out there datasets targeted on helpfulness and harmlessness, in addition to numerous safety-related questions and solutions. Whereas the Phi household of fashions is designed to carry out a variety of duties successfully, it is very important acknowledge that every one AI fashions could exhibit limitations. To higher perceive these limitations and the measures in place to deal with them, please seek advice from the mannequin playing cards beneath, which offer detailed data on accountable AI practices and tips.
Study extra right here:
