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

# Create Evaluation

> Enqueue a benchmark evaluation run for a model using a selected validation dataset.

Start an evaluation run for one of your models by providing a valid dataset. The endpoint returns immediately with a queued status and an evaluation ID you can use to poll for results.

## Endpoint

**POST** `/v1/models/{id}/evaluate`

Authentication: `Authorization: Bearer $ARIA_PIN_KEY`

## Path parameters

<ParamField path="id" type="string" required>
  The model ID to evaluate.
</ParamField>

## Request body

<ParamField body="dataset_id" type="string" required>
  ID of a validated dataset owned by the same user.
</ParamField>

## Response

<ResponseField name="eval_id" type="string">
  Unique identifier for the evaluation run.
</ResponseField>

<ResponseField name="status" type="string">
  Queued status (for example, `queued`).
</ResponseField>

## Example

```bash theme={null}
curl -X POST http://<pin-host>:8001/v1/models/mod_123/evaluate \
  -H "Authorization: Bearer $ARIA_PIN_KEY" \
  -H "Content-Type: application/json" \
  -d '{"dataset_id":"ds_456"}'
```

```json theme={null}
{
  "eval_id": "ev_1712345678901234567",
  "status": "queued"
}
```


## Related topics

- [Get Evaluation](/api-reference/pin/evaluations/get.md)
- [List Evaluations](/api-reference/pin/evaluations/list.md)
- [Aria Compute PIN API: Post-Training & Evaluation](/api-reference/pin/introduction.md)
- [Create Agent Event](/api-reference/agent/events/create.md)
- [Create a GPU Node](/api-reference/pin/gpu-nodes/create.md)