in truth i dont think these leader boards have value !
As they only contain the model providers models and evals which are heavily Pre prepped !
The Main leaderboard was the definitive Leaderboard For all models !
The only think was it just needs to change evaluation datasets every few months :
The main leadwer board only accepts your first submission ! So intruth it is valid !
so when newer models are eval,uated it is expected that they are up to date with current lllm phylospohys and testing metrics !
AS you will see the providers are not top of the leader board but the sub devlopers in the open source community !
Again there was a peoblem with the main leader board !!!
Only models of a dspecific sizew should have been opn there ! IE BIG MODELS SHOULD BE SEPERATED ! and perhaps moved to a paid leaderboard as evalauating these models do take resources and costs !
I am not pleased they disbanded this most impotant resource despite its failures !!
Very dissapointed that hugging face have even allowed it to fail !!!
this i think is very bad for thew site !
The leader board should have been its own section of the site and not directly as space connected to spaces !
Now we actually do not have leaderboard to measure or compete with other models !
Only the fake clones which are just for the faking of results and thew inhuibility to compare your own llm training with the so caled officaL FIGURES !
wow !
Completly Unbeliveablke that also you have sugfghested these non open source sites to replace the original !
( even the lists of best model produced by the leaderboards were sponsered !!!!! ) ( my model was actually the top mistral 7b model ... it did not feature on the best models list !! ( in faxt it was probably a friends list only thing !)