Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
Multi-language Overall Score
#21
by
loretoparisi
- opened
It would be worth to add an overall score, across available benchmarks across multiple-languages. Currently, only the Classification tab has a Other tab scoring (Acc) models on as few as 47 languages.
Good point, I think the problem is that we don't have enough tasks for other languages in MTEB as of now. Only the Classification & STS have lots of languages. We first need to add lots of new tasks to the GitHub repo for that I think 🧐