# 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**.