The Objective Revision Evaluation Service (ORES) is a web service that provides machine learning as a service for Wikimedia Projects. The system is designed to help automate critical wiki-work -- for example, vandalism detection and removal. This service is developed as a project of the Wikimedia Scoring Platform team.

This the experimental version of ORES running in Wikimedia Labs. For the stable, production version of ORES, see

Scores API

ORES is intended to be used as a source of information by tool developers. To access ORES, scores, a simple RESTful API is provided. There are two versions of the scoring API that differ slightly in their behavior. Version 2 provides access to model info in a scoring request. Version 1 is preserved for backwards compatibility.

Version 3 (docs)
The current recommended version of the API.
Accessible via /v3/scores/.
Version 2 (docs)
Preserved for backwards compatibility.
Accessible via /v2/scores/.
Version 1 (docs)
Preserved for backwards compatibility -- this version of the API implements ORES original behavior.
Accessible via /scores/ and /v1/scores/.

Reference scoring user interface

ORES provides a simple user interface for obtaining scores. See /ui/.

Version information

See /versions/.

On-wiki documentation

To read more about the service and the models available, see:


See On-wiki FAQ page.

Privacy policy

See the Wikimedia policy here:

Hosted by Wikimedia Labs & written in Python 3