EvalEval Coalition

AI & ML interests

We’re building a research coalition on evaluating evaluations (EvalEval)! Hosted by Hugging Face, University of Edinburgh, and EleutherAI.

Recent Activity

deepmage121  new activity 1 day ago

evaleval/alphaxiv_datastore:Add alphaXiv SOTA raw scrape (5,069 files, 237MB)

EvalEvalBot  new activity 1 day ago

evaleval/EEE_datastore:Add alphaXiv SOTA evaluations (27,976 records, 1,646 benchmarks)

EvalEvalBot  new activity 1 day ago

evaleval/EEE_datastore:Add alphaXiv SOTA evaluations (27,976 records, 1,646 benchmarks)

View all activity

Team members 33