---
schema_version: "1"
id: ff5759acdd430c158c131c1080b9b25268731fff33b7318db2af2232d74002fa
title: How Article Results Are Ranked
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/ai/264-0-0/search_esk_models.md
canonical_url: https://help.salesforce.com/s/articleView?id=ai.search_esk_models.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: eacfdee4e8cfc4d305bd4db7749f5e43da2e72cb9718316ee2436465bae6071f
description: Agents get relevant results with the latest AI models in Einstein Search for Knowledge. Your models can learn complex relationships between your articles and provide you with the most relevant articles in your top results.
products:
  - Cross Cloud
release: "264"
---
# How Article Results Are Ranked

Agents get relevant results with the latest AI models in Einstein Search for Knowledge. Your models can learn complex relationships between your articles and provide you with the most relevant articles in your top results.

The AI models analyze these factors to provide you the best-ranking search results.

- The article fields that match your term, which include metadata and matching query terms. The AI algorithm learns which fields are the most relevant to have matches on.
- The article field metadata, which includes the number of views, votes, references, and how recently the article was created.
- The most relevant relationships between the different article fields and metadata and how they match the query terms. The AI algorithm learns the combination of matches in article fields and metadata that matters most in ranking.

![How Einstein Search for Knowledge works on the Admins org.](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-ai-search-264-0-0-production-enus/6a28c936-3b68-4186-bc09-7ab905f33ef3/search/images/esk_image.png)