A study demonstrates that a collection of open-source models, referred to as 'Herd,' can match or surpass the performance of proprietary models like ChatGPT. By using an intelligent router, Herd can identify a suitable model to answer queries that ChatGPT cannot, achieving success in at least 40% of such cases.

We show that a herd of open source models can match or exceed the performance of proprietary models via an intelligent router. We show that in cases where GPT is not able to answer the query, Herd is able to identify a model that can, at least 40% of the time.

Open-Source 'Herd' Models Challenge ChatGPT's Performance