Documentation Index

Fetch the complete documentation index at: https://docs.benchgen.com/llms.txt

Use this file to discover all available pages before exploring further.

​

Run a Benchmark

​

Prerequisites

• A model connected or uploaded in Eval (see Upload 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).

​

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.