Live webinar

How well do coding agents write Vaadin?

Register now
Wednesday, 02 December 2026 | |
About this webinar

If you let Claude Code or Codex write your Vaadin views, you'll want to know which of their models gets them right.

VaadinBench is Vaadin's benchmark for coding agents. It hands the agent a task, such as building views to a spec, bootstrapping a new project or migrating a Vaadin 14 app from Polymer to Lit. Then it runs deterministic validation tests that the agent never sees. The code passes or fails, and the model's cost in dollars is recorded. The October run made 1,440 attempts: nine tasks, five tries each, across several models and setups.

Join Vesa Nieminen, Principal Software Engineer at Vaadin, as he walks through the results.

What you'll learn

  • Why an LLM grading the code wasn't good enough
  • How a VaadinBench task is built
  • Which models pass the most tasks, and at what cost
  • How Vaadin and Angular compared on the same Petclinic app
  • Running it yourself: a git clone and two commands
Join us! Register below to secure your spot.

Speakers
Vesa Nieminen
Vesa Nieminen Principal Software Engineer
Miikka Andersson
Miikka Andersson Technical Product Marketing Manager