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

# verial benchmarks

> Create and manage benchmarks from the command line.

The `verial benchmarks` commands manage [Benchmarks](/api-reference/resources/benchmarks) — ordered groups of tasks that reference an environment and are evaluated against criteria. Use them to script benchmark definitions alongside your agent code.

Authentication is required. See [verial auth](/cli/auth).

## Subcommands

| Command                    | Description                              |
| -------------------------- | ---------------------------------------- |
| `verial benchmarks list`   | List benchmarks in your organization.    |
| `verial benchmarks create` | Create a new benchmark.                  |
| `verial benchmarks get`    | Get a single benchmark by ID.            |
| `verial benchmarks update` | Update benchmark metadata or run limits. |
| `verial benchmarks delete` | Delete a benchmark.                      |

## verial benchmarks list

List benchmarks visible to your organization.

Synopsis:

```bash theme={null}
verial benchmarks list
```

Example:

```bash theme={null}
verial benchmarks list
```

```
ID                  NAME                        CREATED
bench_cly987        Prior Auth Workflow         4/1/2026, 1:15:42 PM
bench_cly988        Appointment Scheduling      4/3/2026, 10:08:19 AM
```

REST equivalent: [GET /benchmarks](/api-reference/benchmarks/list).

## verial benchmarks create

Create a benchmark. Tasks and criteria are attached through the REST API or dashboard after creation.

Synopsis:

```bash theme={null}
verial benchmarks create --name <name> \
  [--description <desc>] \
  [--timeout <seconds>] \
  [--concurrency <n>]
```

Options:

| Flag                   | Description                                | Default  |
| ---------------------- | ------------------------------------------ | -------- |
| `--name <name>`        | Benchmark name.                            | Required |
| `--description <desc>` | Free-text description.                     | —        |
| `--timeout <seconds>`  | Per-task timeout in seconds.               | `300`    |
| `--concurrency <n>`    | Max tasks to run in parallel during a run. | `1`      |

Example:

```bash theme={null}
verial benchmarks create \
  --name "Prior Auth Workflow" \
  --description "End-to-end PA submission across fax + payer portal" \
  --timeout 600 \
  --concurrency 4
```

REST equivalent: [POST /benchmarks](/api-reference/benchmarks/create).

## verial benchmarks get

Fetch a single benchmark, including tasks and criteria.

Synopsis:

```bash theme={null}
verial benchmarks get --id <id>
```

Example:

```bash theme={null}
verial benchmarks get --id bench_cly987
```

REST equivalent: [GET /benchmarks/:id](/api-reference/benchmarks/get).

## verial benchmarks update

Update benchmark metadata or run limits. Omitted fields are left unchanged.

Synopsis:

```bash theme={null}
verial benchmarks update --id <id> \
  [--name <name>] \
  [--description <desc>] \
  [--timeout <seconds>] \
  [--concurrency <n>]
```

Example:

```bash theme={null}
verial benchmarks update --id bench_cly987 --concurrency 8
```

REST equivalent: [PATCH /benchmarks/:id](/api-reference/benchmarks/update).

## verial benchmarks delete

Delete a benchmark. Previously completed runs are retained.

Synopsis:

```bash theme={null}
verial benchmarks delete --id <id>
```

```
Deleted bench_cly987
```

REST equivalent: [DELETE /benchmarks/:id](/api-reference/benchmarks/delete).

## Next Steps

<CardGroup cols={2}>
  <Card title="Benchmarks" icon="clipboard-list" href="/api-reference/resources/benchmarks">
    Benchmark model, tasks, and criteria.
  </Card>

  <Card title="Benchmarks API" icon="code" href="/api-reference/benchmarks/list">
    Full REST parameters and response schema.
  </Card>
</CardGroup>