Featuring Every Eval Ever Results on Hugging Face Model Pages
Every Eval Ever (EEE) and Hugging Face Community Evals are now interoperable, allowing cross-posting of evaluation results and standardized metadata, which helps users, researchers, and policymakers compare and trust AI evaluations. EEE provides a unified JSON schema for evaluation results, ensuring consistency across different sources and formats, while Hugging Face Community Evals decentralizes benchmark score reporting. The system addresses the fragmentation of evaluation data, enabling accurate tracking of results from various sources, including harness logs and leaderboard scrapes, and allows both first and third-party evaluators to submit results to both platforms.
More from Huggingface
LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge
Thinking of ACE? We Can Do It with Fewer Tokens
Meta is back with Muse Glimmer: local, agentic, multimodal, and open source
