@article{abdin2025phi-,
author = {Abdin, Marah and Agarwal, Sahaj and Agarwal, Sahaj and Awadallah, Ahmed and Balachandran, Vidhisha and Behl, Harkirat and Chen, Lingjiao and Rosa, Gustavo de and Gunasekar, Suriya and Javaheripi, Mojan and Joshi, Neel and Kauffmann, Piero and Lara, Yash and Mendes, Caio César Teodoro and Mitra, Arindam and Nushi, Besmira and Papailiopoulos, Dimitris and Saarikivi,  Olli and Shah, Shital and Shrivastava, Vaishnavi and Vineet, Vibhav and Wu, Yue and Yousefi, Safoora and Zheng, Guoqing},
title = {Phi-4-reasoning Technical Report},
year = {2025},
month = {April},
abstract = {We introduce Phi-4-reasoning, a 14-billion parameter reasoning model that achieves strong performance on complex reasoning tasks. Trained via supervised fine-tuning of Phi-4 on carefully curated set of “teachable” prompts–selected for the right level of complexity and diversity–and reasoning demonstrations generated using o3-mini, Phi-4-reasoning generates detailed reasoning chains that effectively leverage inference time compute. We further develop Phi-4-reasoning-plus, a variant enhanced through a short phase of outcome-based reinforcement learning that offers higher performance by generating longer reasoning traces. Across a wide range of reasoning tasks, both models outperform significantly larger open-weight models such as DeepSeekR1-Distill-Llama-70B model and approach the performance levels of full DeepSeek R1 model. Our comprehensive evaluations span benchmarks in math and scientific reasoning, coding, algorithmic problem solving, planning, and spatial understanding. Interestingly, we observe a non-trivial transfer of improvements to general-purpose benchmarks as well. In this report, we provide insights into our training data, our training methodologies, and our evaluations. We show that the benefit of careful data curation for supervised fine-tuning (SFT) extends to reasoning language models, and can be further amplified by reinforcement learning (RL). Finally, our evaluation points to opportunities for improving how we assess the performance and robustness of reasoning models.},
url = {http://approjects.co.za/?big=en-us/research/publication/phi-4-reasoning-technical-report/},
}