# Evaluating performances

To get an evaluation of a model version's performances, you need to create a validation set **before** training a model version.

{% content-ref url="/pages/-LQ-KwTGnBm3VygG8H\_U" %}
[Validation split](/platform-documentation/deepomatic-drive/configuring-visual-automation-applications/evaluating-performances/validation-split.md)
{% endcontent-ref %}

 Once you have trained a model, you will likely want to know how good it performs at the task you are trying to automate.

You can start with a qualitative evaluation here:

{% content-ref url="/pages/-LQ-HanE9-n4IM96VcQb" %}
[Qualitative evaluation](/platform-documentation/deepomatic-drive/configuring-visual-automation-applications/evaluating-performances/qualitative-evaluation.md)
{% endcontent-ref %}

You can then access the performance report to get more details on your models:

{% content-ref url="/pages/-LzrQdQ7cvazSN8jHUT0" %}
[Performance report](/platform-documentation/deepomatic-drive/configuring-visual-automation-applications/evaluating-performances/performance-report.md)
{% endcontent-ref %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.deepomatic.com/platform-documentation/deepomatic-drive/configuring-visual-automation-applications/evaluating-performances.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.