Tencent Hunyuan Researchers Introduce WebCraftBench to Test AI-Built Web Apps in the Browser
Sign in✓ Signed in
Researchers from Tencent Hunyuan, Tsinghua University and Peking University have introduced WebCraftBench, a benchmark that evaluates AI-generated web applications by running them and testing their behavior, not just inspecting code or screenshots. The WebCraftBench paper, submitted September 14 and revised September 20, reports 85.3% agreement with validated human preferences on 197 application pairs.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...