Phi-4 Reasoning Vision

Active

15B multimodal reasoning model with image understanding.

Overview

Phi-4 Reasoning Vision adds image understanding to the Phi-4 Reasoning model via a SigLIP-2 vision encoder, enabling visual reasoning over charts, diagrams, and screenshots. Released March 2026.

Integrations & tooling support

Tool calling: Not supported
Structured outputs: Not supported

Price vs quality

Not enough data

This model has no benchmark scores recorded yet.

Community ratings

No ratings yet. Be the first to rate Phi-4 Reasoning Vision.