[jyu]

for text, is there a standard to compare model results?

[brucethemoose2]

There are tons of metrics people have come up with, for example look at the huggingface leaderboard. There are more niche leaderboards/tests for chat models, chain of thought, summarization and such.

But the best test is personal experimentation. Prompt engineering and subjective preference have a massive effect on finetune performance.