Choosing Your LLM: Cutting Through the Hype to Find the Right Model for You

Everyone’s building AI agents these days — but under the hood, it all comes down to one big decision: which LLM to use. With new models dropping every week, how do you make a smart, data-driven choice instead of just following the hype?
In this session, we’ll break down how to evaluate and pick the right model for real-world use. We’ll share results from a hands-on study testing 15 of today’s top LLMs on code summarization tasks, comparing their cost, speed, accuracy, verbosity, and information gain.
You’ll walk away with a clear picture of how different models actually perform — not just in benchmarks, but in practical scenarios. Perfect for anyone building coding assistants, developer copilots, or next-gen multimodal agents who wants to make confident, informed model choices.