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 prospects 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 accessible to prospects.
At this time, 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 usually discovered solely in giant frontier fashions. Phi-reasoning fashions introduce a brand new class of small language fashions. Utilizing distillation, reinforcement studying, and high-quality information, these fashions steadiness measurement and efficiency. They’re sufficiently small for low-latency environments but preserve 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 through supervised fine-tuning of Phi-4 on fastidiously curated reasoning demonstrations from OpenAI o3-mini, Phi-4-reasoning generates detailed reasoning chains that successfully leverage extra inference-time compute. The mannequin demonstrates that meticulous information curation and high-quality artificial datasets enable 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 larger accuracy.
Regardless of their considerably smaller measurement, 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. degree science questions. They obtain efficiency higher than the complete 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 significant enchancment over Phi-4, surpass bigger fashions like DeepSeek-R1-Distill-70B and method Deep-Search-R1 throughout varied reasoning and basic capabilities, together with math, coding, algorithmic drawback fixing, and planning. The technical report gives in depth quantitative proof of those enhancements by way of numerous reasoning duties.
Phi-4-mini-reasoning
Phi-4-mini-reasoning is designed to fulfill the demand for a compact reasoning mannequin. This transformer-based language mannequin is optimized for mathematical reasoning, offering high-quality, step-by-step drawback fixing in environments with constrained computing or latency. High quality-tuned with artificial information generated by Deepseek-R1 mannequin, Phi-4-mini-reasoning balances effectivity with superior reasoning skill. It’s superb for instructional functions, embedded tutoring, and light-weight deployment on edge or cell methods, and is skilled on over a million numerous math issues spanning a number of ranges of issue from center college to Ph.D. degree. Check out the mannequin on Azure AI Foundry or HuggingFace at this time.
For extra details about the mannequin, learn the technical report that gives extra quantitative insights.
Phi’s evolution over the past yr has regularly pushed this envelope of high quality vs. measurement, 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 domestically on CPUs and GPUs.
As Home windows works in the direction of creating a brand new sort of PC, Phi fashions have turn out to be 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 accessible with blazing quick time to first token responses, and energy environment friendly token throughput so it may be concurrently invoked with different functions operating 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 screen, and is accessible 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 will probably be accessible to run quickly on Copilot+ PC NPUs.
Security and Microsoft’s method to accountable AI
At Microsoft, accountable AI is a basic precept guiding the event and deployment of AI methods, 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 sturdy security post-training method, leveraging a mix of Supervised High quality-Tuning (SFT), Direct Choice Optimization (DPO), and Reinforcement Studying from Human Suggestions (RLHF) strategies. These strategies make the most of varied datasets, together with publicly accessible datasets centered on helpfulness and harmlessness, in addition to varied 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 each one AI fashions might exhibit limitations. To higher perceive these limitations and the measures in place to deal with them, please confer with the mannequin playing cards beneath, which give detailed info on accountable AI practices and tips.
