About Microsoft
Explore research at Microsoft, a site featuring the impact of research along with publications, products, downloads, and research careers.
Microsoft Research conducts fundamental science and technology research across a spectrum of research areas. With labs around the globe we pursue breakthroughs across the computing and AI stack to accelerate discovery across sciences and advance the frontiers of computing and AI to create new foundations for others to build upon.
Artificial intelligence | Search & information retrieval | Human language technologies | Human-computer interaction | Computer vision | Graphics & multimedia | Audio & acoustics
Medical, health & genomics | Economics | Social sciences | Technology for emerging markets | Ecology & environment
Website ↗Documentation ↗
Source ↗ · 2026-11-12T02:17:04.301031227Zmicrosoft/phi-4
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
- Context window
- 16,384
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs
Benchmarks
- Artificial Analysis: 5.9
- LMArena: 1,216.694
- Open LLM Leaderboard v2: 30.358%
Inference prices
- Published price : $0.07 / input_tokens_per_million · deepInfra ↗
- Published price : $0.14 / output_tokens_per_million · deepInfra ↗
vertexAI/publishers/microsoft/models/phi3@phi-3-small-8k-instruct
- Input modalities
- text
- Output modalities
- text
Benchmarks
- LiveBench: 24.452%
- LMArena: 1,109.829
- Open LLM Leaderboard v2: 32.342%
vertexAI/publishers/microsoft/models/phi3@phi-3-mini-4k-instruct
- Input modalities
- text
- Output modalities
- text
Benchmarks
- LLM-Perf: 11,804,449.309
- LMArena: 1,073.312
- Open LLM Leaderboard v1: 69.905%
- Open LLM Leaderboard v2: 27.562%
vertexAI/publishers/microsoft/models/phi3@phi-3-mini-128k-instruct
- Input modalities
- text
- Output modalities
- text
Benchmarks
- LiveBench: 17.356%
- LMArena: 1,050.394
- Open LLM Leaderboard v1: 68.071%
- Open LLM Leaderboard v2: 26.344%
azureFoundry/azureml-msr/Aurora-1.5@2
Aurora 1.5 is a fine-tuned version of the Aurora foundation earth system prediction model.
- Input modalities
- data
- Output modalities
- data
azureFoundry/azureml/Aurora@1
Aurora: A Foundation Model for the Earth System Aurora is a machine learning model that can predict atmospheric variables, such as temperature. It is a _foundation model_, which means that it was first generally trained on a lot of data, and then can be adapted to specialised at
azureFoundry/azureml/Aurora@2
Aurora is a machine learning model that can predict general environmental variables, such as temperature and wind speed. It is a _foundation model_, which means that it was first generally trained on a lot of data, and then can be adapted to specialised environmental forecasting
azureFoundry/azureml/Aurora@3
Aurora is a machine learning model that can predict general environmental variables.
- Input modalities
- data
- Output modalities
- data
azureFoundry/azureml/Aurora@4
Aurora is a machine learning model that can predict general environmental variables.
- Input modalities
- data
- Output modalities
- data
azureFoundry/azureml-cogsvc/Azure-AI-Content-Safety@1
## Azure AI Content Safety ## Introduction Azure AI Content Safety is a safety system for monitoring content generated by both foundation models and humans. Detect and block potential risks, threats, and quality problems. You can build an advanced safety system for foundation mo
azureFoundry/azureml-cogsvc/Azure-AI-Content-Understanding@1
# Azure AI Content Understanding ## Introduction Azure AI Content Understanding empowers you to transform unstructured multimodal data—such as text, images, audio, and video—into structured, actionable insights. By streamlining content processing with advanced AI techniques li
azureFoundry/azureml-cogsvc/Azure-AI-Document-Intelligence@1
## Azure AI Document Intelligence Document Intelligence is a cloud-based service that enables you to build intelligent document processing solutions. Massive amounts of data, spanning a wide variety of data types, are stored in forms and documents. Document Intelligence enables y
azureFoundry/azureml-cogsvc/Azure-AI-Vision@1
## Azure AI Vision ## Introduction The Azure AI Vision service gives you access to advanced algorithms that process images and videos and return insights based on the visual features and content you are interested in. Azure AI Vision can power a diverse set of scenarios, includi
azureFoundry/azureml-cogsvc/Azure-Content-Understanding-Layout@1
# Azure Content Understanding - Layout Content Understanding Layout offers rich, structure‑aware extraction that captures text, formatting, tables, figures, and geometric layout details. It’s designed for complex document understanding workflows that require positional accuracy
azureFoundry/azureml-cogsvc/Azure-Content-Understanding-Read@1
# Azure Content Understanding - Read Content Understanding Read provides fast, reliable extraction of text and basic content elements from documents, enabling simple ingestion workflows without layout interpretation. It’s ideal for scenarios where clean text output is needed for
azureFoundry/azureml-cogsvc/Azure-Language-Conversational-PII-redaction@1
PII Redaction for Conversation automatically detects and masks sensitive information such as names, addresses, phone numbers, credit card details, and other personally identifiable information (PII) in meeting transcripts.
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml-cogsvc/Azure-Language-Document-PII-redaction@1
PII Redaction for Documents automatically detects and masks sensitive information such as names, addresses, phone numbers, credit card details, and other personally identifiable information (PII) in native documents including PDF, Word, and text files.
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml-cogsvc/Azure-Language-Language-detection@1
Language detection quickly and accurately identifies the language of any text, supporting over 100 languages and dialects, including the ISO 15924 standard for a select number of languages.
- Input modalities
- text
- Output modalities
- text