Overview

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.

Phi 4 Reasoning was released on April 30, 2025.

Performance

Timeline

Release DateUnknown

Knowledge CutoffUnknown

Other Details

Parameters

14.0B

License

MIT

Training Data

Unknown

Related Models

Compare Phi 4 Reasoning to other models by quality (GPQA score) vs cost. Higher scores and lower costs represent better value.

Performance visualization loading...

Gathering benchmark data from similar models

Benchmarks

Phi 4 Reasoning Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

llm-stats.com - Sun Dec 14 2025

Notice missing or incorrect data?Start an Issue discussion→

Pricing

Pricing, performance, and capabilities for Phi 4 Reasoning across different providers:

No pricing information available for this model.

Example Outputs

Recent Reviews

API Access

API Access Coming Soon

API access for Phi 4 Reasoning will be available soon through our gateway.

FAQ

Common questions about Phi 4 Reasoning

Phi 4 Reasoning was released on April 30, 2025.

Phi 4 Reasoning has 14.0 billion parameters.

Phi 4 Reasoning