§ feed · storyline
Small open-source LLM outperforms Claude Sonnet by 60% on healthcare
Parsed fine-tunes a 27B open-source model that outperforms Claude Sonnet 4 by 60% on a healthcare task at 10–100x lower cost.
Parsed fine-tuned a 27B open-source model to beat Claude Sonnet 4 by 60% on a real-world healthcare task—while running 10–100x cheaper.
§ sources1 publication · timeline below