# Model Rating

> The platform helps you train models by calculating a holistic model rating. This rating assesses the overall health and performance of your model by considering a number of key contributing factors.

The platform helps you train models by calculating a holistic model rating. This rating assesses the overall health and performance of your model by considering a number of key contributing factors.

This rating is a proprietary score created to ensure that you create models that perform well in all of the most important areas.

The main factors that the rating takes into account are:

* **Balance** - this factor assesses whether the training data is a balanced representative of the dataset as a whole.
* **Underperforming Labels** - assesses the performance of the 10% of labels that have the most significant warnings.
* **Coverage** - assesses how well predictions for informative labels cover the dataset as a whole.
* **All Labels** - assesses the average performance of labels by looking at every label in the taxonomy.