Benchmark RadarAI BENCHMARK PROFILE
SchemaGUI
Evaluates controllable GUI generation via deterministic function-call references synthesized from parameterized schemas across six bilingual scenarios.
- Released
- 2026-08-23
- Readiness
- Runnable
- Primary field
- General AI
Why it matters
Offers scalable, annotation-free evaluation for GUI generation and reveals bottlenecks in geometric spatial control among LLMs.
Motivation
Large language models (LLMs) have demonstrated strong potential in graphical user interface (GUI) generation, but reliable evaluation remains challenging due to uncontrolled data distributions, noisy annotations, and limited layout scenario coverage.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.