# Phi-4-Reasoning-Vision-15B — Microsoft's Compact Multimodal Reasoner: 88.2% ScreenSpot v2, Open-Weight

> Microsoft's 15B open-weight model combines visual reasoning with math and GUI understanding — and knows when NOT to think.

- Org: Microsoft Research
- Date: 2026-04-10
- Category: model
- Source: https://www.microsoft.com/en-us/research/blog/phi-4-reasoning-vision-and-the-lessons-of-training-a-multimodal-reasoning-model/
- Canonical page: https://ai-tldr.dev/releases/phi-4-reasoning-vision-15b-microsoft/

## In short

Phi-4-Reasoning-Vision-15B combines SigLIP-2 vision with the Phi-4-Reasoning language backbone via mid-fusion. At 15B parameters it achieves 88.2% ScreenSpot v2, 75.2% MathVista, and 83.3% ChartQA — outperforming larger models while staying open-weight under a permissive license.

## What it is

Phi-4-Reasoning-Vision-15B is Microsoft's compact multimodal reasoning model, released open-weight on March 4, 2026 via Microsoft Foundry and Hugging Face. It extends the Phi-4-Reasoning language backbone with a SigLIP-2 vision encoder using a mid-fusion architecture. A blog post with detailed training insights was published in April 2026.

## How it works

The model uses a mid-fusion approach combining SigLIP-2's vision encoder with the Phi-4-Reasoning backbone, processing high-resolution images via dynamic resolution up to 3,600 visual tokens. Training data was split roughly 20% reasoning-focused (with explicit chain-of-thought traces) and 80% perception-focused (direct response), enabling the model to invoke structured reasoning for math and science while defaulting to fast response for perception tasks.

## Why it matters

GUI grounding benchmarks like ScreenSpot v2 reflect real agentic workflows: reading screens, clicking buttons, understanding interfaces. At 88.2% on ScreenSpot v2 and comparable to larger models at far lower compute, Phi-4-Reasoning-Vision opens the door for capable multimodal agents on edge hardware and laptops.

## Who it's for

Developers building computer-use agents, document understanding pipelines, or multimodal scientific tools who need an open-weight model with strong reasoning at low deployment cost.

## Links

- [Microsoft Research Blog](https://www.microsoft.com/en-us/research/blog/phi-4-reasoning-vision-and-the-lessons-of-training-a-multimodal-reasoning-model/)
- [Hugging Face Model](https://huggingface.co/microsoft/Phi-4-reasoning-vision-15B)
- [VentureBeat](https://venturebeat.com/technology/microsoft-built-phi-4-reasoning-vision-15b-to-know-when-to-think-and-when)