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

# Running evaluations

> Score a workflow version against your dataset and compare accuracy over time

An **evaluation** scores one workflow version against your [dataset](/guides/health/datasets). It runs an extraction on every in-scope document, compares each result to that document's ground truth, and records the run with an accuracy you can trust to compare against other runs.

Evaluations live under **Health → Evaluations**.

***

## Running an evaluation

Choose **Run eval** and set two things:

* **Scope** — the **full dataset**, or a single **sub-dataset** (including **Untagged**). This is the set of documents that will be scored.
* **Workflow version** — the version being measured.

The evaluation runs an extraction for each in-scope file and scores it against ground truth.

<Warning>
  Running an evaluation **runs extractions**, which consume credits — one per in-scope document. Narrow the scope to a sub-dataset when you only need to measure a slice.
</Warning>

<Info>
  If the version has fields the dataset has no ground truth for, the run still proceeds — those fields simply **aren't scored**, and you'll see a warning naming them. Missing ground truth never blocks a run.
</Info>

***

## Reading the run list

Each evaluation appears as a numbered run — `#1`, `#2`, … — in a table with:

| Column       | What it shows                                              |
| ------------ | ---------------------------------------------------------- |
| **Run**      | The run number, e.g. `#3`                                  |
| **Dataset**  | The scope that was evaluated (full dataset or sub-dataset) |
| **Version**  | The workflow version that was scored                       |
| **Date**     | When the run happened                                      |
| **Status**   | Whether the run is in progress, complete, or failed        |
| **Accuracy** | Share of graded fields that matched ground truth           |
| **Files**    | How many documents were in scope                           |

Because each run is pinned to a version and a scope, the list doubles as an **accuracy-over-time** history — the signal for whether a workflow is improving or regressing.

***

## Inside a single evaluation

Open a run to debug where accuracy comes from:

* **Accuracy**, **Documents** (how many passed), and **Fields** as headline numbers, plus a **vs previous run** delta so you can see the change at a glance.
* **By file** — per-document accuracy, to find the documents dragging the number down.
* **By field** — per-field accuracy, to find the fields that consistently fail.

From there you can inspect a document's **expected vs predicted** values side by side to see exactly what the workflow got wrong.

***

## Comparing versions

The evaluation workflow is built for iteration:

1. Run an evaluation on the current version — your baseline.
2. Refine the workflow (fields, instructions, the pipeline) and save a **new version**.
3. Run another evaluation on the same scope.
4. Compare the two runs' accuracy.

<Info>
  Editing ground truth or refining the workflow **never** changes a past evaluation — each run is immutable. That's what makes the difference between two runs real signal rather than noise. Always run a fresh evaluation to measure a change.
</Info>

***

## What's next?

<CardGroup cols={2}>
  <Card title="Building a dataset" icon="database" href="/guides/health/datasets">
    Add documents, edit ground truth, and tag sub-datasets.
  </Card>

  <Card title="Confidence & Accuracy" icon="chart-line" href="/guides/workflows/analytics-quality">
    How accuracy and confidence work across anyformat.
  </Card>
</CardGroup>