{"slug":"evals","name":"Evals","kind":"tool","kindLabel":"Tool","grade":null,"score":null,"tagline":"Framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.","description":"Framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.","tags":["evaluation"],"url":"https://way.space/tool/evals","stars":"—","category":"coding","categories":["coding"],"repo":"https://github.com/openai/evals","maintainers":[{"login":"openai","url":"https://github.com/openai","isMember":false,"verified":false}]}