Hacker News Reader

The BEIR project might be what you're looking for: https://github.com/beir-cellar/beir/wiki/Leaderboard

https://huggingface.co/spaces/mteb/leaderboard

see the retrieval tab

It's interesting how the massive model of e5-mistral has only marginal performance gains over the bge-base and similar ones. It could still be useful for the longer sentence length though.

e5-mistral is essentially a distillation from gpt-4 to a smaller model. You can see here https://github.com/microsoft/unilm/blob/16da2f193b9c1dab0a69...

they actually have custom prompts for each dataset being tested.

Question would be, if you haven't seen the task before, what is a good prompt to prepend for your task?

IMO e5-mistral is overfit to MTEB