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

Phi-3-medium-128k-instruct · azureml v1

azureFoundry/azureml/Phi-3-medium-128k-instruct@1

## Model Summary The Phi-3-Medium-128K-Instruct is a 14B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense prop

Input modalities
text
Output modalities
text

Phi-3-medium-128k-instruct · azureml v2

azureFoundry/azureml/Phi-3-medium-128k-instruct@2

## Model Summary The Phi-3-Medium-128K-Instruct is a 14B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense prop

Input modalities
text
Output modalities
text

Phi-3-medium-4k-instruct

vertexAI/publishers/microsoft/models/phi3@phi-3-medium-4k-instruct

Input modalities
text
Output modalities
text

Benchmarks

  • Open Ko-LLM Leaderboard: 41.333
  • Open LLM Leaderboard v1: 73.449%
  • Open LLM Leaderboard v2: 33.098%

Phi-3-medium-4k-instruct · azureml v1

azureFoundry/azureml/Phi-3-medium-4k-instruct@1

## Model Summary The Phi-3-Medium-4K-Instruct is a 14B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense proper

Input modalities
text
Output modalities
text

Phi-3-medium-4k-instruct · azureml v2

azureFoundry/azureml/Phi-3-medium-4k-instruct@2

## Model Summary The Phi-3-Medium-4K-Instruct is a 14B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense proper

Input modalities
text
Output modalities
text

Phi-3-medium instruct (128k) · azureml v3

azureFoundry/azureml/Phi-3-medium-128k-instruct@3

Same Phi-3-medium model, but with a larger context size for RAG or few shot prompting.

Context window
131,072
Maximum output
4,096
Input modalities
text
Output modalities
text

Phi-3-medium instruct (128k) · azureml v4

azureFoundry/azureml/Phi-3-medium-128k-instruct@4

Same Phi-3-medium model, but with a larger context size for RAG or few shot prompting.

Context window
131,072
Maximum output
4,096
Input modalities
text
Output modalities
text

Phi-3-medium instruct (128k) · azureml v5

azureFoundry/azureml/Phi-3-medium-128k-instruct@5

Same Phi-3-medium model, but with a larger context size for RAG or few shot prompting.

Context window
131,072
Maximum output
4,096
Input modalities
text
Output modalities
text

Phi-3-medium instruct (128k) · azureml v6

azureFoundry/azureml/Phi-3-medium-128k-instruct@6

Same Phi-3-medium model, but with a larger context size for RAG or few shot prompting.

Context window
131,072
Maximum output
4,096
Input modalities
text
Output modalities
text

Phi-3-medium instruct (4k) · azureml v3

azureFoundry/azureml/Phi-3-medium-4k-instruct@3

A 14B parameters model, proves better quality than Phi-3-mini, with a focus on high-quality, reasoning-dense data.

Context window
4,096
Maximum output
4,096
Input modalities
text
Output modalities
text

Phi-3-medium instruct (4k) · azureml v4

azureFoundry/azureml/Phi-3-medium-4k-instruct@4

A 14B parameters model, proves better quality than Phi-3-mini, with a focus on high-quality, reasoning-dense data.

Context window
4,096
Maximum output
4,096
Input modalities
text
Output modalities
text

Phi-3-medium instruct (4k) · azureml v5

azureFoundry/azureml/Phi-3-medium-4k-instruct@5

A 14B parameters model, proves better quality than Phi-3-mini, with a focus on high-quality, reasoning-dense data.

Context window
4,096
Maximum output
4,096
Input modalities
text
Output modalities
text

Phi-3-medium instruct (4k) · azureml v6

azureFoundry/azureml/Phi-3-medium-4k-instruct@6

A 14B parameters model, proves better quality than Phi-3-mini, with a focus on high-quality, reasoning-dense data.

Context window
4,096
Maximum output
4,096
Input modalities
text
Output modalities
text

Phi-3-mini-128k-instruct · azureml v4

azureFoundry/azureml/Phi-3-mini-128k-instruct@4

## Model Details Phi-3 Mini-128K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model built upon datasets used for Phi-2 - synthetic data and filtered websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model fami

Input modalities
text
Output modalities
text

Phi-3-mini-128k-instruct · azureml v5

azureFoundry/azureml/Phi-3-mini-128k-instruct@5

## Model Details Phi-3 Mini-128K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model built upon datasets used for Phi-2 - synthetic data and filtered websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model fami

Input modalities
text
Output modalities
text

Phi-3-mini-128k-instruct · azureml v6

azureFoundry/azureml/Phi-3-mini-128k-instruct@6

## Model Details Phi-3 Mini-128K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model built upon datasets used for Phi-2 - synthetic data and filtered websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model fami

Input modalities
text
Output modalities
text

Phi-3-mini-128k-instruct · azureml v7

azureFoundry/azureml/Phi-3-mini-128k-instruct@7

## Model Details Phi-3 Mini-128K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model built upon datasets used for Phi-2 - synthetic data and filtered websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model fami

Input modalities
text
Output modalities
text

Phi-3-mini-128k-instruct · azureml v8

azureFoundry/azureml/Phi-3-mini-128k-instruct@8

## Model Details Phi-3 Mini-128K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model built upon datasets used for Phi-2 - synthetic data and filtered websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model fami

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