Co-Design Bench, a reference-free benchmark of 273 tasks curated from 37,463 deduplicated queries across 26,314 real user coding sessions, was introduced to test whether coding agents can translate users' multimodal requests into working application revisions. The benchmark targets human-AI co-design evaluation for agentic models.
Evaluating human-AI co-design requires testing whether coding agents can translate real users' multimodal requests into working application revisions. We introduce Co-Design Bench, a reference-free benchmark of 273 tasks curated from 37,463 deduplicated queries across 26,314 real user coding session
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.