> For the complete documentation index, see [llms.txt](https://ai-docs.fptcloud.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai-docs.fptcloud.com/fpt-ai-studio/services/model-testing-test-jobs/overview.md).

# Overview

## What is Model Testing - Test Jobs?

**Model Testing - Test Jobs** is a core feature of the FPT AI Factory Portal that provides a structured and automated way to evaluate fine-tuned AI models. Unlike **Interactive Sessions** - which focus on real-time, manual interactions, **Test Jobs** are designed for large-scale, repeatable testing using predefined datasets.

<figure><img src="https://fptcloud.com/wp-content/uploads/2025/09/Test-Jobs.png" alt=""><figcaption></figcaption></figure>

**Key capabilities of Test Jobs:**

* **Automated Evaluation:** Run large-scale tests using structured input data to evaluate model responses without manual intervention.
* **Custom Test Sets:** Upload domain-specific datasets tailored to your business cases (e.g., custom queries, legal documents, medical records)
* **Standardized Test Sets:** Leverage publicly available benchmarks developed be researchers to evaluate models against industry standards (e.g., Nejumi Leaderboard 3, LM Evaluation Harness, VLM Evaluation Kit)
* **Performance Metrics:** Analyze model outputs using quantitative and qualitative metrics.

**Model Testing - Test Jobs** ensures that your AI model is not only responsive in live interactions but also robust, consistent, and scalable across a wide range of inputs. It’s an essential step before deployment, especially for high-stakes applications in industries like finance, healthcare and legal services.

## When to Use Model Testing - Test Jobs?

**Model Testing - Test Jobs** is most valuable when you need to evaluate the overall performance, reliability, and scalability of a fine-tuned model before deployment.

You should use **Test Jobs** when:

* You want to validate model performance **at scale**.
* You want to track improvements **across model versions**.
* You require **quantitative performance metrics**.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://ai-docs.fptcloud.com/fpt-ai-studio/services/model-testing-test-jobs/overview.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
