Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
BM25 / BM25 retrieval
anchor
Findings
IC-1150
ChatGPT and Llama-2-7b-chat underperform humans by 20 and 31 points respectively on out-of-distribution NLU tasks in GLUE-X
[compared-to]