Dwarkesh Pretraining Replication Finds Data Gains Deliver 3.24x More Compute Multipliers Than Model Gains

josh_wills · x · 2026-09-09

Dwarkesh Patel and collaborator @whoisjerbear pretrained combinations of year-representative open model recipes and data corpora from 2019–2025 at various small scales. Key findings:

Full results and implications for future AI progress are published in the linked writeup.

Related event: Dwarkesh Experiments: Data Drives Most Pretraining Progress(3 posts)→

Original post →

More from Research

Research channel →