# Built-in metric evaluator prompts for model-as-a-judge evaluation jobs
<a name="model-evaluation-type-judge-prompt"></a>

When you run a judge-based model evaluation job the *evaluator model* scores the *generator model's* responses according to a set of metrics you define. Amazon Bedrock offers a number of built-in metrics, or you can define your own [custom metrics](model-evaluation-custom-metrics-prompt-formats.md).

Refer to the following sections to see the prompts used by the available evaluator models for the Amazon Bedrock built-in metrics.

**Topics**
+ [Amazon Nova Pro](model-evaluation-type-judge-prompt-nova.md)
+ [Amazon Nova 2 Lite](model-evaluation-type-judge-prompt-nova-2-lite.md)
+ [Amazon Nova Micro](model-evaluation-type-judge-prompt-nova-micro.md)
+ [Amazon Nova Premier](model-evaluation-type-judge-prompt-nova-premier.md)
+ [Anthropic Claude 3.5 Sonnet](model-evaluation-type-judge-prompt-claude-sonnet.md)
+ [Anthropic Claude 3.5 Sonnet v2](model-evaluation-type-judge-prompt-claude-sonnet35v2.md)
+ [Anthropic Claude 3.7 Sonnet](model-evaluation-type-judge-prompt-claude-sonnet37.md)
+ [Anthropic Claude Haiku 4.5](model-evaluation-type-judge-prompt-claude-haiku-4-5.md)
+ [Anthropic Claude Opus 4.5](model-evaluation-type-judge-prompt-claude-opus-4-5.md)
+ [Anthropic Claude Sonnet 4.0](model-evaluation-type-judge-prompt-claude-sonnet-4.md)
+ [Anthropic Claude Sonnet 4.5](model-evaluation-type-judge-prompt-claude-sonnet-4-5.md)
+ [Anthropic Claude 3 Haiku](model-evaluation-type-judge-prompt-haiku.md)
+ [Anthropic Claude 3.5 Haiku](model-evaluation-type-judge-prompt-haiku35.md)
+ [Meta Llama 3.1 70B Instruct](model-evaluation-type-judge-prompt-llama.md)
+ [Mistral Large](model-evaluation-type-judge-prompt-mistral.md)