EvalEval Coalition

community

https://evalevalai.com/

evaluatingevals

Activity Feed Request to join this org

AI & ML interests

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

Recent Activity

j-chim updated a Space about 6 hours ago

evaleval/general-eval-card

evijit updated a dataset about 17 hours ago

evaleval/card_backend

evijit updated a bucket about 22 hours ago

evaleval/general-eval-card-storage

View all activity

Articles

AI evals are becoming the new compute bottleneck

evaleval 's Spaces 4

Eval Cards

Standardized evaluation cards for AI models and benchmarks

eval-card-registry

README

BenchmarkCard Webhook

Receive and process benchmark data via webhook