Building an open benchmark - SWE-WebDevBench - for...
# share-your-work
n
Building an open benchmark - SWE-WebDevBench - for evaluating AI coding platforms like ourselves but also Replit, Lovable etc for real-world webapp development on complete software dev lifecycle. Created a "lite" version for now, and did a comparative run against 6 major AI coding products. The Arxiv paper describes the framework. https://webdevbench.com/
To quickly see some charts etc, see this X thread: https://x.com/nileshtrivedi/status/2052401472470761486
t
oh this is great!