🪡AI Model Evaluation Tools

A guide on how to use our evaluation playground to test the results of your chatbot.

The Evaluation Playground lets users test different AI models and see which one produces the best results for their use case. It helps answer the question, “Which AI model should I pick?” by allowing side-by-side comparisons of model outputs.

Users can either run a single prompt across multiple AI models, or test multiple prompts across different AI models to evaluate performance and consistency.

In this section:

How to Use the Single-Prompt Evaluation FeatureHow to Use the Multi‑Prompt Evaluation Feature