The Every Eval Ever (EEE) project and Hugging Face Community Evals have achieved interoperability, letting researchers submit evaluation results to both platforms at once. EEE maintains a single JSON schema for evaluation results, and a new converter tool automatically transforms EEE records into Hugging Face Community Evals YAML files. This lets evaluation scores appear directly on model pages while preserving traceable links to source records, addressing the fragmentation of eval results across papers, leaderboards, and blogs.
