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

EvalEvalBot  new activity about 3 hours ago

evaleval/EEE_datastore:Upload gsm8k/ollama/llama3.1-8b/fb9e009d-b14a-431e-99d4-77ce95a71d41.json

EvalEvalBot  new activity about 3 hours ago

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

deepmage121  updated a dataset about 4 hours ago

evaleval/EEE_datastore

View all activity

Team members 33