Phi-4-reasoning-plus

Phi-4-reasoning-plus is an advanced open-weight reasoning model, finetuned from Phi-4 with additional reinforcement learning for higher accuracy. Like Phi-4-reasoning, it is trained on a blend of synthetic and high-quality public data, focusing on math, science, and coding, but generates on average 50% more tokens for more detailed responses. The model has 14B parameters and supports a 128K token context length.

Outputs include a reasoning chain-of-thought block and a summarization block. Released under the MIT license, this static model was trained on data up to March 2025. For best results, use prompts in chat format and review the license for details.