Evaluator prompts based used in judge-based model evaluation job - Amazon Bedrock

Evaluator prompts based used in judge-based model evaluation job

When you run a judge-based model evaluation job the Evaluator model scores the Generator model's responses.

Use the following sections to see the prompt uses to score the model's response, and to provide an explanation of why it was scored the way it was scored. Each section is organized by supported by evaluator model, and then metric.