AI & ML interests

None defined yet.

Recent Activity

sumuksΒ  published a Space 3 days ago
yourbench/essential-web-medical
sumuksΒ  updated a Space 4 days ago
yourbench/essential-web-medical
sumuksΒ  published a Space 4 days ago
yourbench/view_essentialweb_cleaned
View all activity

YourBench is an open-source framework for generating zero-shot benchmarks from your own documents. It helps you test language models on custom domains using automated pipelines for ingestion, summarization, and question generation.

  • πŸ“š Build benchmarks from PDFs, HTML, or text files
  • 🧠 Generate both single-hop and multi-hop questions
  • πŸ” Evaluate top models and deploy leaderboards instantly
  • πŸ› οΈ Fully configurable via a single YAML file

Built with πŸ€— by the OpenEvals team β€” GitHub

models 0

None public yet