CUAVerifierBench
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
CUAVerifierBench Browserbase OM2W
78Accuracy
8
CUAVerifierBench Browserbase OM2W (n=106)
88Accuracy
8
CUAVerifierBench (Internal Dataset (n=140))
81Accuracy
8
CUAVerifierBench Internal Dataset
81Accuracy
8