Fine-tuning a smaller open-weight model isn't a compromise.
For specialised tasks it can be the better way to build.
Sep 25, 2026 · 6:30 PM UTC
1
1
5
230
Across legal, biomedical and aviation benchmarks, our fine-tuned models were 7x more accurate at quoting clauses word for word and 20x cheaper on the legal task.
How we did it: overmindlab.ai/research/when…
1
6
465