Benchmark
Firebase
24 tasks across 3 tiers
Tier 1: Structural Claims Verification
8 tasks
Tier 2: Styling Claims Verification
8 tasks
Tier 3: Functional/Interactive Claims Verification
8 tasks
Design is never finished.
Loading Design TheaterDesign is never finished.
Loading Design TheaterBenchmark
24 tasks across 3 tiers
8 tasks
8 tasks
8 tasks