Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Human Correlation on WebArena
Loading...
0.79
Pearson Correlation Coefficient (r)
ADARUBRIC-DA
0.2908
0.4204
0.55
0.6796
Mar 22, 2026
Pearson Correlation Coefficient (r)
Average Correlation Score
Average Absolute Delta
Updated 25d ago
Evaluation Results
Method
Method
Links
Pearson Correlation Coefficient (r)
Average Correlation Score
Average Absolute Delta
ADARUBRIC-DA
Method=AdaRubric, Vari...
2026.03
0.79
0.767
0.147
ADARUBRIC-GM
Method=AdaRubric, Vari...
2026.03
0.76
0.737
0.117
ADARUBRIC-WM
Method=AdaRubric, Vari...
2026.03
0.74
0.72
0.1
GPT-4 Direct
Method=GPT-4 Direct, c...
2026.03
0.64
0.62
-
Prometheus
Method=Prometheus
2026.03
0.61
0.59
0.05
G-Eval
Method=G-Eval
2026.03
0.54
0.517
0.123
BERTScore
Method=BERTScore
2026.03
0.43
0.41
0.23
ROUGE-L
Method=ROUGE-L
2026.03
0.31
0.287
0.353
Feedback
Search any
task
Search any
task