# How do I evaluate my BigQuery ML model, before making predictions?

To evaluate your model after training completes, run:
```
SELECT
  *
FROM
  ML.EVALUATE(MODEL bqmlretail.MY_MODEL_NAME)
```
Hint: Look at the **AUC** metric to compare performance between your models.

## How does ML.EVALUATE work if I never split the data?
When you use CREATE MODEL, BigQuery ML automatically splits your training data into its own training/test data so that you can evaluate the performance of the model immediately when the model has finished training. 

_For more information on how BigQuery ML automatically splits your training data, read the [docs here on the `DATA_SPLIT_METHOD` parameter](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-create#data_split_method) when using CREATE MODEL._