UI-Bench is the first large-scale benchmark that ranks AI text-to-app tools by blinded expert pairwise preference, using TrueSkill to produce a leaderboard with confidence intervals.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
UI-Bench: A Benchmark for Evaluating Design Capabilities of AI Text-to-App Tools
UI-Bench is the first large-scale benchmark that ranks AI text-to-app tools by blinded expert pairwise preference, using TrueSkill to produce a leaderboard with confidence intervals.