Headline: Phi-4-Vision-Reasoning—training a multimodal reasoning model

We are pleased to announce Phi-4-reasoning-vision-15B, a 15 billion parameter open‑weight multimodal reasoning model, available through Microsoft Foundry (opens in new tab), HuggingFace (opens in new tab) and GitHub (opens in new tab). Phi-4-reasoning-vision-15B is a broadly capable model that can be used for a wide array of vision-language tasks such as image captioning, asking questions about images, reading documents and receipts, helping with homework, inferring about changes in sequences of images, and much more. Beyond these general capabilities, it excels at math and science reasoning and at understanding and grounding elements on computer and mobile screens. In particular, our model presents an appealing value relative to popular open-weight models, pushing the pareto-frontier of the tradeoff between accuracy and compute costs. We have competitive performance to much slower models that require ten times or more compute-time and tokens and better accuracy than similarly fast models, particularly when it comes to math and science reasoning.

In this post, we share the motivations, design choices, experiments, and learnings that informed its development, as well as an evaluation of the model’s performance and guidance on how to use it. Our goal is to contribute practical insight to the community on building smaller, efficient multimodal reasoning models and to share an open-weight model that is competitive with models of similar size at general vision-language tasks, excels at computer use, and excels on scientific and mathematical multimodal reasoning.

A focus on smaller and faster vision–language models

Many popular vision-language models (VLMs) have trended towards growing in parameter count and, in particular, the number of tokens they consume and generate. This leads to increase in training and inference-time cost and latency, and impedes their usability for downstream deployment, especially in resource‑constrained or interactive settings.

A growing countertrend towards smaller (opens in new tab) models aims to boost efficiency, enabled by careful model design and data curation – a goal pioneered by the Phi family of models (opens in new tab) and furthered by Phi-4-reasoning-vision-15B. We specifically build on learnings from the Phi-4 and Phi-4-Reasoning language models and show how a multimodal model can be trained to cover a wide range of vision and language tasks without relying on extremely large training datasets, architectures, or excessive inference‑time token generation. Our model is intended to be lightweight enough to run on modest hardware while remaining capable of structured reasoning when it is beneficial. Our model was trained with far less compute than many recent open-weight VLMs of similar size. We used just 200 billion tokens of multimodal data leveraging Phi-4-reasoning (trained with 16 billion tokens) based on a core model Phi-4 (400 billion unique tokens), compared to more than 1 trillion tokens used for training multimodal models like Qwen 2.5 VL (opens in new tab) and 3 VL (opens in new tab), Kimi-VL (opens in new tab), and Gemma3 (opens in new tab). We can therefore present a compelling option compared to existing models pushing the pareto-frontier of the tradeoff between accuracy and compute costs.

Lessons from training a multimodal model

Training a multimodal reasoning model raises numerous questions and requires many nuanced design choices around model architecture, dataset quality and composition, and the interaction between reasoning‑heavy and non-reasoning perception‑focused tasks.

Model architecture: Early- vs mid-fusion

Model architectures for VLMs differ primarily in how visual and textual information is fused. Mid-fusion models use a pretrained vision encoder to convert images into visual tokens that are projected into a pretrained LLM’s embedding space, enabling cross-modal reasoning while leveraging components already trained on trillions of tokens. Early-fusion models process image patches and text tokens in a single model transformer, yielding richer joint representations but at significantly higher compute, memory, and data cost. We adopted a mid-fusion architecture as it offers a practical trade-off for building a performant model with modest resources.

Model architecture: Vision encoder and image processing

We build on the SigLIP-2 (opens in new tab) vision encoder and the Phi-4-Reasoning backbone. In previous research, we found that multimodal language models sometimes struggled to solve tasks, not because of a lack of reasoning proficiency, but rather an inability to extract and select relevant perceptual information from the image. An example would be a high-resolution screenshot that is information-dense with relatively small interactive elements.

Several open-source multimodal language models have adapted their methodologies accordingly, e.g., Gemma3 (opens in new tab) uses pan-and-scan and NVILA (opens in new tab) uses Dynamic S2. However, their trade-offs are difficult to understand across different datasets and hyperparameters. To this end, we conducted an ablation study of several techniques. We trained a smaller 5 billion parameter Phi-4 based proxy model on a dataset of 10 million image-text pairs, primarily composed of computer-use and GUI grounding data. We compared with Dynamic S2, which resizes images to a rectangular resolution that minimizes distortion while admitting a tiling by 384×384 squares; Multi-crop, which splits the image into potentially overlapping 384×384 squares and concatenates their encoded features on the token dimension; Multi-crop with S2, which broadens the receptive field by cropping into 1536×1536 squares before applying S2; and Dynamic resolution using the Naflex variant of SigLIP-2, a natively dynamic-resolution encoder with adjustable patch counts.

Our primary finding is that dynamic resolution vision encoders perform the best and especially well on high-resolution data. It is particularly interesting to compare dynamic resolution with 2048 vs 3600 maximum tokens: the latter roughly corresponds to native HD 720p resolution and enjoys a substantial boost on high-resolution benchmarks, particularly ScreenSpot-Pro. Reinforcing the high-resolution trend, we find that multi-crop with S2 outperforms standard multi-crop despite using fewer visual tokens (i.e., fewer crops overall). The dynamic resolution technique produces the most tokens on average; due to their tiling subroutine, S2-based methods are constrained by the original image resolution and often only use about half the maximum tokens. From these experiments we choose the SigLIP-2 Naflex variant as our vision encoder.

Method	Max Tokens	MathVista	ScreenSpot	ScreenSpot-Pro	V*Bench
Dynamic-S2	3096	42.9	78.4	9.4	52.9
Multi-crop	3096	43.4	67.8	5.4	51.8
Multi-crop with S2	2048	43.4	79.1	10.6	57.1
Dynamic resolution	2048	45.2	81.5	9.2	51.3
Dynamic resolution	3600	44.9	79.7	17.5	56.0

Data: Quality and composition

As with its language backbone Phi-4-Reasoning, Phi-4-reasoning-vision-15B was trained with a deliberate focus on data quality. Our final dataset consists primarily of data from three sources: open-source datasets which were meticulously filtered and improved; high-quality domain-specific internal data; and high-quality data from targeted acquisitions. The overwhelming majority of our data lies in the first category: data which originated as open-source data, which were significantly filtered and improved, whether by removing low-quality datasets or records, programmatically fixing errors in data formatting, or using open-source images as seeds to synthetically generate higher-quality accompanying text.

The process of improving open-source data began by manually reviewing samples from each dataset. Typically, 5 to 10 minutes were sufficient to classify data as excellent-quality, good questions with wrong answers, low-quality questions or images, or high-quality with formatting errors. Excellent data was kept largely unchanged. For data with incorrect answers or poor-quality captions, we re-generated responses using GPT-4o and o4-mini, excluding datasets where error rates remained too high. Low-quality questions proved difficult to salvage, but when the images themselves were high quality, we repurposed them as seeds for new caption or visual question answering (VQA) data. Datasets with fundamentally flawed images were excluded entirely. We also fixed a surprisingly large number of formatting and logical errors across widely used open-source datasets.

We extracted additional value from existing datasets through reformatting, diversification, and using images as seeds for new data generation. We generated detailed image descriptions alongside original QA pairs for math and science data, had data perform “double-duty” by embedding instruction-following requirements directly into domain-specific QA, created “scrambled,” “caption-matching,” and “what’s changed?” records to improve multi-image reasoning and sequential navigation for CUA scenarios, and diversifying prompt styles to encourage robustness beyond perfectly structured questions.

To supplement the improved open-source data, we utilize high-quality internal datasets, several math-specific datasets which were acquired during training of the Phi-4 language model, and also some domain-specific curated data; for example, latex-OCR data generated by processing and rendering equations from arXiv documents.