SOmeHow the best at testing !!!
ohters may contain more paradigms and even data ... but somehow this one is top at leaderboard testing !
@misc{open-llm-leaderboard-v2,
author = {Clémentine Fourrier and Nathan Habib and Alina Lozovskaya and Konrad Szafer and Thomas Wolf},
title = {Open LLM Leaderboard v2},
year = {2024},
publisher = {Hugging Face},
howpublished = "\url{
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard}",
}
@software{eval-harness,
author = {Gao, Leo and
Tow, Jonathan and
Biderman, Stella and
Black, Sid and
DiPofi, Anthony and
Foster, Charles and
Golding, Laurence and
Hsu, Jeffrey and
McDonell, Kyle and
Muennighoff, Niklas and
Phang, Jason and
Reynolds, Laria and
Tang, Eric and
Thite, Anish and
Wang, Ben and
Wang, Kevin and
Zou, Andy},
title = {A framework for few-shot language model evaluation},
month = sep,
year = 2021,
publisher = {Zenodo},
version = {v0.0.1},
doi = {10.5281/zenodo.5371628},
url = {
https://doi.org/10.5281/zenodo.5371628},
}
Detailed results can be found
here
