Synthetic Data Trains 27B Qwen to Beat Frontier Models at 10x Lower Cost

soumitrashukla9 · x · 2026-08-18

Engram Lab published research utilizing a synthetic law firm to train AI. They trained a 27B Qwen model on synthetic client matters, applying this learned knowledge to perform online searches more efficiently. The trained model outperforms frontier models in search tasks at 10x lower cost per query, suggesting promising applications for scaling enterprise search and personalization.

Original post →

More from Research

Research channel →