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/NextCoder-14B

vertexAI/publishers/hf-microsoft/models/nextcoder-14b@001

Input modalities
text
Output modalities
text

microsoft/NextCoder-32B

vertexAI/publishers/hf-microsoft/models/nextcoder-32b@001

Input modalities
text
Output modalities
text

microsoft/NextCoder-7B

vertexAI/publishers/hf-microsoft/models/nextcoder-7b@001

Input modalities
text
Output modalities
text

microsoft/OmniParser-v2.0

azureFoundry/HuggingFace/microsoft-omniparser-v2-0@3

📢 [[GitHub Repo](https://github.com/microsoft/OmniParser/tree/master)] [[OmniParser V2 Blog Post](https://www.microsoft.com/en-us/research/articles/omniparser-v2-turning-any-llm-into-a-computer-use-agent/)] [Huggingface demo](https://huggingface.co/spaces/microsoft/OmniParser-v2)

microsoft/OptiMind-SFT

vertexAI/publishers/hf-microsoft/models/optimind-sft@001

Input modalities
text
Output modalities
text

microsoft/Orca-2-13b

vertexAI/publishers/hf-microsoft/models/orca-2-13b@001

Benchmarks

  • Open LLM Leaderboard v1: 61.981%
  • Open LLM Leaderboard v2: 18.502%

microsoft/Orca-2-7b

vertexAI/publishers/hf-microsoft/models/orca-2-7b@001

Input modalities
text
Output modalities
text

Benchmarks

  • Open Ko-LLM Leaderboard: 51.009%
  • Open LLM Leaderboard v1: 54.549%
  • Open LLM Leaderboard v2: 14.405%

microsoft/phi-1

vertexAI/publishers/hf-microsoft/models/phi-1@001

Input modalities
text
Output modalities
text

Benchmarks

  • BigCode Models Leaderboard: 4,941
  • Open LLM Leaderboard v2: 5.574%

microsoft/phi-1_5

vertexAI/publishers/hf-microsoft/models/phi-1_5@001

Input modalities
text
Output modalities
text

Benchmarks

  • LLM-Perf: 122,412,549.98
  • Open LLM Leaderboard v1: 47.687%
  • Open LLM Leaderboard v2: 7.171%

microsoft-phi-1-5 · azureml-msr v10

azureFoundry/azureml-msr/microsoft-phi-1-5@10

## **Microsoft Phi-1.5** Phi-1.5 is a Transformer-based language model with 1.3 billion parameters. It was trained on a combination of data sources, including an additional source of NLP synthetic texts. Phi-1.5 performs exceptionally well on benchmarks testing common sense, lan

Input modalities
text
Output modalities
text

microsoft-phi-1-5 · azureml-msr v11

azureFoundry/azureml-msr/microsoft-phi-1-5@11

## **Microsoft Phi-1.5** Phi-1.5 is a Transformer-based language model with 1.3 billion parameters. It was trained on a combination of data sources, including an additional source of NLP synthetic texts. Phi-1.5 performs exceptionally well on benchmarks testing common sense, lan

Input modalities
text
Output modalities
text

microsoft-phi-1-5 · azureml-msr v8

azureFoundry/azureml-msr/microsoft-phi-1-5@8

## **Microsoft Phi-1.5** Phi-1.5 is a Transformer-based language model with 1.3 billion parameters. It was trained on a combination of data sources, including an additional source of NLP synthetic texts. Phi-1.5 performs exceptionally well on benchmarks testing common sense, lan

Input modalities
text
Output modalities
text

microsoft-phi-1-5 · azureml-msr v9

azureFoundry/azureml-msr/microsoft-phi-1-5@9

## **Microsoft Phi-1.5** Phi-1.5 is a Transformer-based language model with 1.3 billion parameters. It was trained on a combination of data sources, including an additional source of NLP synthetic texts. Phi-1.5 performs exceptionally well on benchmarks testing common sense, lan

Input modalities
text
Output modalities
text

microsoft/phi-2

vertexAI/publishers/hf-microsoft/models/phi-2@001

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 61.325%
  • Open LLM Leaderboard v2: 15.534%

microsoft-phi-2 · azureml-msr v17

azureFoundry/azureml-msr/microsoft-phi-2@17

## **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-2 · azureml-msr v19

azureFoundry/azureml-msr/microsoft-phi-2@19

## **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-2 · azureml-msr v20

azureFoundry/azureml-msr/microsoft-phi-2@20

## **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-2 · azureml-msr v21

azureFoundry/azureml-msr/microsoft-phi-2@21

## **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

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