Welcome to Tromero Model Evaluations & Playground

In the Model Evaluations & Playground section on Tromero, users can assess and refine their AI models across a wide range of tasks and domains. What you will find here includes:

  • Evaluation Explanations: In-depth explanation of the 18 model evaluation tests.
  • Evaluation Start: A guide on how to start any of the 18 model evaluation tests through the Tromero's Python, TypeScript library or the CLI.
  • Playground: A visual on how to use the playground.

By using the Model Evaluation feature on Tromero, users can gain a deeper understanding of your model's strengths and weaknesses, identifying areas for improvement, and refining the performance of the model to achieve their goal.

Guides

Understand the Evaluation Metircs

Discover what each of the model evaluations do on Tromero.

Read more

Start A Model Evaluation Job

Learn how to start model evaluations.

Read more

Was this page helpful?