# Evals: how to tell if your model is improving > Source: > Published: 2026-11-05 22:39:38+00:00 An eval is a repeatable test for an AI system. You collect example inputs, decide what a good answer looks like, and score the outputs the same way every time. That lets you compare two prompts or two models with numbers instead of impressions. Scoring is usually a mix of programmatic checks (valid JSON, required fields), human review, and an LLM acting as judge. LLM judges are fast but tend to favor longer or more confident answers, so it helps to check them against human ratings. Hugging Face’s `evaluate` and `lighteval` libraries cover many standard model-level metrics, and a custom dataset built from your own use case usually matters more than any public benchmark.