Microsoft

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 ↗ · 2026-11-12T02:17:04.301031227Z

669 indexed models

669 matching models

microsoft-phi-2 · azureml-msr v22

azureFoundry/azureml-msr/microsoft-phi-2@22

## **Microsoft Phi-2** The phi-2 is a language model with 2.7 billion parameters. The phi-2 model was trained using the same data sources as phi-1, augmented with a new data source that consists of various NLP synthetic texts and filtered websites (for safety and educational val

Input modalities
text
Output modalities
text

microsoft/Phi-3-vision-128k-instruct

vertexAI/publishers/hf-microsoft/models/phi-3-vision-128k-instruct@001

Input modalities
text
Output modalities
text

Benchmarks

  • LMArena: 881.036
  • MMBench: 97.8%

microsoft/Phi-4-mini-instruct

vertexAI/publishers/hf-microsoft/models/phi-4-mini-instruct@001

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v2: 29.412%

microsoft/Promptist

azureFoundry/HuggingFace/microsoft-promptist@6

# Promptist: reinforcement learning for automatic prompt optimization ## News - [Demo Release] Dec, 2022: [Demo at HuggingFace Space](https://aka.ms/promptist-demo) - [Model Release] Dec, 2022: [link](#load-pretrained-model-for-stable-diffusion-v14) - [Paper Release] Dec, 2022:

Input modalities
text
Output modalities
text

microsoft/prophetnet-large-uncased

azureFoundry/HuggingFace/microsoft-prophetnet-large-uncased@5

## prophetnet-large-uncased Pretrained weights for [ProphetNet](https://arxiv.org/abs/2001.04063). ProphetNet is a new pre-trained language model for sequence-to-sequence learning with a novel self-supervised objective called future n-gram prediction. ProphetNet is able to p

Input modalities
text
Output modalities
text

microsoft/prophetnet-large-uncased-squad-qg

azureFoundry/HuggingFace/microsoft-prophetnet-large-uncased-squad-qg@3

## prophetnet-large-uncased-squad-qg Fine-tuned weights(converted from [original fairseq version repo](https://github.com/microsoft/ProphetNet)) for [ProphetNet](https://arxiv.org/abs/2001.04063) on question generation SQuAD 1.1. ProphetNet is a new pre-trained language mode

Input modalities
text
Output modalities
text

microsoft-rad-dino · azureml v1

azureFoundry/azureml/microsoft-rad-dino@1

## Model Description # Model card for RAD-DINO ## Model description RAD-DINO is a vision transformer model trained to encode chest X-rays using the self-supervised learning method [DINOv2](https://openreview.net/forum?id=a68SUt6zFt). RAD-DINO is described in detail in [RAD-DI

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

microsoft-rad-dino · azureml v2

azureFoundry/azureml/microsoft-rad-dino@2

## Model Description # Model card for RAD-DINO ## Model description RAD-DINO is a vision transformer model trained to encode chest X-rays using the self-supervised learning method [DINOv2](https://openreview.net/forum?id=a68SUt6zFt). RAD-DINO is described in detail in [RAD-DI

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

microsoft-rad-dino · azureml v3

azureFoundry/azureml/microsoft-rad-dino@3

## Model Description # Model card for RAD-DINO ## Model description RAD-DINO is a vision transformer model trained to encode chest X-rays using the self-supervised learning method [DINOv2](https://openreview.net/forum?id=a68SUt6zFt). RAD-DINO is described in detail in [RAD-DI

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

microsoft-rad-dino · azureml v4

azureFoundry/azureml/microsoft-rad-dino@4

## Model Description # Model card for RAD-DINO ## Model description RAD-DINO is a vision transformer model trained to encode chest X-rays using the self-supervised learning method [DINOv2](https://openreview.net/forum?id=a68SUt6zFt). RAD-DINO is described in detail in [RAD-DI

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

microsoft/resnet-101

azureFoundry/HuggingFace/microsoft-resnet-101@1

# ResNet-101 v1.5 ResNet model pre-trained on ImageNet-1k at resolution 224x224. It was introduced in the paper [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385) by He et al. Disclaimer: The team releasing ResNet did not write a model card for t

microsoft: resnet-50

cloudflareWorkersAI/@cf/microsoft/resnet-50

50 layers deep image classification CNN trained on more than 1M images from ImageNet

Input modalities
image
Capabilities
visionInput

microsoft/rho-math-1b-v0.1

vertexAI/publishers/hf-microsoft/models/rho-math-1b-v0.1@001

Benchmarks

  • LLM-Perf: 186,889,804.983
  • Open LLM Leaderboard v1: 34.985%

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace