Web Clone Bench leaderboard

Web Clone Bench (Web Clone Bench v1) is an external benchmark published by Introducing Web Clone Bench v1. Coding agents recreate nine reference web apps from an empty directory. Plato checks visual and functional behavior through end-to-end workflows. Its evaluation set is described by the source as 9 reference web apps. The source rates its difficulty as long-running web application recreation.

Each model's result is published by Introducing Web Clone Bench v1 as published full score (%). ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 0 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.