List your company

Human Correlation on WebArena

0.79Pearson Correlation Coefficient (r)ADARUBRIC-DA
0.29080.42040.550.6796Mar 22, 2026

Evaluation results

MethodLinks
ADARUBRIC-DAMethod=AdaRubric, Variant=DA (ours), Evaluator=GPT-4o, Details=DimensionAwareFilter variant2026.030.790.7670.147
ADARUBRIC-GMMethod=AdaRubric, Variant=GM (ours), Evaluator=GPT-4o2026.030.760.7370.117
ADARUBRIC-WMMethod=AdaRubric, Variant=WM (ours), Evaluator=GPT-4o2026.030.740.720.1
GPT-4 DirectMethod=GPT-4 Direct, configuration=single-turn, no rubric, Evaluator=GPT-4o2026.030.640.62—
PrometheusMethod=Prometheus2026.030.610.590.05
G-EvalMethod=G-Eval2026.030.540.5170.123
BERTScoreMethod=BERTScore2026.030.430.410.23
ROUGE-LMethod=ROUGE-L2026.030.310.2870.353