# Judge Model

> A model used to score, compare, or critique other model outputs.

- Category: Evaluation & Safety
- Stage: Rising
- Also called: LLM-as-judge, Evaluator model
- Canonical: https://www.joelcsaji.com/ai-dictionary/judge-model

## Plain English

One AI grades another AI's work.

## Example

A judge model checks if an answer is grounded in the supplied document chunks.

## Why it matters

Judge models scale evaluation, but they can be biased or fooled, so they need calibration.

## Related

- [Evals](https://www.joelcsaji.com/ai-dictionary/evals)
- [Evaluator-Optimizer](https://www.joelcsaji.com/ai-dictionary/evaluator-optimizer)
- [Grounding](https://www.joelcsaji.com/ai-dictionary/grounding)

## Sources

- [Anthropic: Building Effective Agents](https://www.anthropic.com/engineering/building-effective-agents)
- [Stanford HAI: 2026 AI Index](https://hai.stanford.edu/ai-index/2026-ai-index-report)