Phi 4 Reasoning
Phi-4-reasoning is a state-of-the-art open-weight reasoning model finetuned from Phi-4 using supervised fine-tuning on a dataset of chain-of-thought traces and reinforcement learning. It focuses on math, science, and coding skills.
Benchmarks
Arena Performance
Phi 4 Reasoning Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Fri Feb 27 2026Notice missing or incorrect data?Start an Issue discussion→
FAQ
Common questions about Phi 4 Reasoning
Phi 4 Reasoning was released on April 30, 2025 by Microsoft.
Phi 4 Reasoning was created by Microsoft.
Phi 4 Reasoning has 14.0 billion parameters.
Phi 4 Reasoning is released under the MIT license. This is an open-source/open-weight license.
Phi 4 Reasoning has a knowledge cutoff of March 2025. This means the model was trained on data up to this date.