> ## Documentation Index
> Fetch the complete documentation index at: https://studio-docs.prem.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Get Started With Evaluations

> Learn how to evaluate a model in Prem.

# Start Here ↓

<Note>
  You can only evaluate a model if you have a snapshot of your dataset.
</Note>

<Steps>
  <Step title="Create an New Evaluation">
    <img src="https://static.premai.io/prem-saas-docs/evaluations/get-started/step-1-create-eval.gif" alt="Gif of creating a new evaluation" />
  </Step>

  <Step title="Browse and Choose Metrics">
    <img src="https://static.premai.io/prem-saas-docs/evaluations/get-started/step-2-browse-metrics.gif" alt="Image of filling out the fields" />
  </Step>

  <Step title="Check your results">
    Once your evaluation is done you can check your results.

    <img src="https://static.premai.io/prem-saas-docs/evaluations/get-started/step-4-result.png" alt="Image of checking your results" />

    You can click on each metric to organize the results.

    To get more details on each datapoint, click on the percentage under the model name.

    <img src="https://static.premai.io/prem-saas-docs/evaluations/get-started/step-3-checkresults.gif" alt="Image of checking your results" />

    **The results will look something like this:**

    <img src="https://static.premai.io/prem-saas-docs/evaluations/get-started/step-5-details.png" alt="Image of checking your details" />

    <Tip>
      Click **Model Results Tab** to see additional details of the evaluation based on the model and metric.

      <img src="https://static.premai.io/prem-saas-docs/evaluations/get-started/additional-details.png" alt="Image of checking your details" />
    </Tip>
  </Step>
</Steps>

### Here are Some Results to Keep in Mind:

* **Average Score**: The average score of the evaluation for the model.
* **Model Name**: The name of the model the evaluation was run on.
* **System Prompt**: The system prompt used for the evaluation.
* **User Message**: The user message from the dataset.
* **Original Assistant Message**: The original assistant message from the dataset.
* **Predicted Assistant Message**: The predicted assistant message from the model.
* **Model Score**: The score of the model chosen for the evaluation.
* **Score Reason**: The reasoning behind the score.

## Other Options

<CardGroup cols={3}>
  <Card title="Bring Your Own Evaluation" icon="chart-simple" href="/evaluations/bring-your-own-eval">
    Click here to learn how to bring your own evaluation to Prem.
  </Card>

  <Card title="Evaluation Metrics" icon="chart-simple" href="/evaluations/metrics">
    Create your own custom evaluation metrics and rules.
  </Card>

  <Card title="Fine-Tuned Model → Playground" icon="play" href="/playground/overview">
    Click here to learn how to use your fine-tuned model in the playground.
  </Card>
</CardGroup>