New top story on Hacker News: Ask HN: Benchmarks for models other than LLMs

Ask HN: Benchmarks for models other than LLMs
3 by caydenm | 0 comments on Hacker News.
I have seen some amazing benchmarks used to rank LLMs abilities, it got me thinking are there similar benchmarks for propensity modelling, churn prediction or other types of models? Are there best practices for comparing model performance beyond benchmark data when they may have different underlying datasets?

No comments:

Post a Comment