List your company

Evaluation Reliability on Web Automation (WA)

0.85Krippendorff's AlphaADARUBRIC-DA
0.63160.68830.7450.8017Mar 22, 2026

Evaluation results

MethodLinks
ADARUBRIC-DA2026.030.85
ADARUBRIC-GM2026.030.83
ADARUBRIC-WM2026.030.81
Prometheus2026.030.71
GPT-4 Direct2026.030.69
G-EvalBackbone=GPT-4o2026.030.64