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

# Model evaluation overview

> Evaluate model performance across multiple dimensions on QwenCloud, with LLM-based scoring and manual annotation.

Model evaluation quantifies model output quality across multiple dimensions. You can create evaluation dimensions and tasks on the [Model Evaluation](https://home.qwencloud.com/model-production/evaluations/tasks) console page.

<Note>
  Model evaluation is available only in Singapore and China North 2 (Beijing). It is not available in China (Hong Kong), Germany (Frankfurt), Japan (Tokyo), or US (Virginia), and its menu is hidden in the console in those regions. To use it, switch to Singapore or China North 2 (Beijing) with the region selector in the upper-right corner of the [console](https://home.qwencloud.com/). See [Feature availability by region](/developer-guides/getting-started/regions#feature-availability-by-region).
</Note>

Evaluation jobs and their results belong to the region where you run them and cannot be used in another region.

## Core concepts

Model evaluation consists of two sub-modules:

- **Evaluation dimensions** — Define the scoring criteria. Supports LLM-based scoring (numeric / classification) and manual annotation.
- **Evaluation tasks** — Select dimensions + dataset + model to evaluate, then view results.

## Evaluation workflow

<Steps>
  <Step title="Define evaluation dimensions">
    Create one or more evaluation dimensions, choosing the dimension type, judge model, and scoring template. See [Evaluation dimensions](/developer-guides/evaluation/evaluation-dimensions).
  </Step>

  <Step title="Prepare evaluation data">
    Create and publish an **evaluation dataset** in [Datasets](/developer-guides/datasets/create-dataset).
  </Step>

  <Step title="Create an evaluation task">
    Select the data source, evaluation model, and evaluation dimensions, then submit the task. See [Evaluation tasks](/developer-guides/evaluation/evaluation-tasks).
  </Step>

  <Step title="View results">
    Check scores, token usage, and per-sample scoring details in the task list.
  </Step>
</Steps>

## Billing

Model evaluation costs consist of two parts:

| Cost type                 | Billed?             | Description                                                                                                                                                                                     |
| ------------------------- | ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Evaluated model inference | Yes                 | When using an "Evaluation dataset" as the data source, the system calls the evaluated model to run inference, billed at standard token rates. No inference cost when using "Inference results". |
| Judge model scoring       | Free (limited time) | The judge model scoring process for LLM-based dimensions (numeric and classification) is currently free for a limited time.                                                                     |

## Next steps

- [Evaluation dimensions](/developer-guides/evaluation/evaluation-dimensions) -- Learn about the three dimension types and create custom scoring criteria.
- [Evaluation tasks](/developer-guides/evaluation/evaluation-tasks) -- Create evaluation tasks and view results.
- [Create a dataset](/developer-guides/datasets/create-dataset) -- Prepare an evaluation dataset.