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

# Run a Benchmark

> Step-by-step guide to running a model against a benchmark in Eval.

A benchmark run evaluates a model against a set of test cases and produces a structured results report.

***

## Prerequisites

* A model added in Eval (see [Add a model](/eval/add-a-model))
* At least one benchmark dataset available in your workspace

***

## Steps

1. **Open Eval** from the left sidebar.
2. **Select a benchmark** from the benchmark library or upload your own.
3. **Choose a model** to evaluate — pick from connected APIs or uploaded models.
4. **Configure run settings**
   * Temperature and sampling parameters
   * Max tokens per response
   * Timeout per question
5. **Click Run** to start the evaluation.
6. **Monitor progress** in the run dashboard — results stream in as each test case completes.
7. **View the report** when the run finishes (see [Read results](/eval/read-results)).

***

## Tips

* Run the same benchmark against multiple models to compare them side by side.
* Start with a small benchmark (10–50 cases) to validate your setup before scaling up.
* Save run configs to re-run the same evaluation after each training iteration.