If you're talking about embeddings model metrics, the MTEB Leaderboard is a good resource: https://huggingface.co/spaces/mteb/leaderboard
see the retrieval tab
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