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

# How to return multiple scores in one evaluator

Sometimes it is useful for a custom evaluator or summary evaluator to return multiple metrics. For example, if you have multiple metrics being generated by an LLM judge, you can save time and money by making a single LLM call that generates multiple metrics instead of making multiple LLM calls.

To return multiple scores using the Python SDK, simply return a list of dictionaries/objects of the following form:

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
[
    # 'key' is the metric name
    # 'score' is the value of a numerical metric
    {"key": string, "score": number},
    # 'value' is the value of a categorical metric
    {"key": string, "value": string},
    ... # You may log as many as you wish
]
```

To do so with the JS/TS SDK, return an object with a 'results' key and then a list of the above form

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{results: [{ key: string, score: number }, ...]};
```

Each of these dictionaries can contain any or all of the [feedback fields](/langsmith/feedback-data-format); check out the linked document for more information.

Example:

* Python: Requires `langsmith>=0.2.0`
* TypeScript: Support for multiple scores is available in `langsmith@0.1.32` and higher

<CodeGroup>
  ```python Python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  def multiple_scores(outputs: dict, reference_outputs: dict) -> list[dict]:
      # Replace with real evaluation logic.
      precision = 0.8
      recall = 0.9
      f1 = 0.85
      return [
          {"key": "precision", "score": precision},
          {"key": "recall", "score": recall},
          {"key": "f1", "score": f1},
      ]
  ```

  ```typescript TypeScript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  import type { Run, Example } from "langsmith/schemas";

  function multipleScores(rootRun: Run, example: Example) {
    // Your evaluation logic here
    return {
        results: [
            { key: "precision", score: 0.8 },
            { key: "recall", score: 0.9 },
            { key: "f1", score: 0.85 },
        ],
    };
  }
  ```
</CodeGroup>

Rows from the resulting experiment will display each of the scores.

<img src="https://mintcdn.com/langchain-5e9cc07a/4kN8yiLrZX_amfFn/langsmith/images/multiple-scores.png?fit=max&auto=format&n=4kN8yiLrZX_amfFn&q=85&s=7f0a67189b7202a46d5e093cce9ea283" alt="multiple_scores.png" width="1622" height="1020" data-path="langsmith/images/multiple-scores.png" />

## Related

* [Return categorical vs numerical metrics](/langsmith/metric-type)

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/langsmith/multiple-scores.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>