Databricks recently released DBRX Instruct, an open, general-purpose LLM. Across a range of standard benchmarks, DBRX sets a new state-of-the-art for established open LLMs. Moreover, it provides the open community and enterprises building their own LLMs with capabilities that were previously limited to closed model APIs.

According to our measurements, it surpasses GPT-3.5, and it is competitive with Gemini 1.0 Pro. It is an especially capable code model, rivalling specialized models like CodeLLaMA-70B on programming in addition to its strength as a general-purpose LLM.

In this Product Tour, you’ll discover how to try and explore DBRX Instruct leveraging Databricks Playground, a simple UI to benchmark multiple models and improve your prompt (including RAG), a key step to successfully deploy your GenAI Apps.
You will learn how to query Databricks DBRX Instruct and compare the results to the other Foundation Models provided by Databricks or an external provider.