Glossary · Evals & quality

LLM-as-judge

Using a strong LLM to automatically score or compare the quality of other models' outputs instead of relying solely on human raters.

Related terms

• Chatbot Arena
• Elo rating (LLM)
• LLM benchmark
• LLM observability
• MMLU
• PII detection

Vynaris is an inference gateway that routes each request to the cheapest right-sized model and shows the receipt. Get an API key or read the docs.