Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

LLM-as-a-Judge on ARENA

66.07Accuracy

EpiPersona-A

49.357253.696158.03562.3739Mar 30, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.03
66.07
2026.03
65.01
2026.03
64.89
2026.03
64.39
2026.03
64.36
2026.03
64.18
2026.03
64.17
2026.03
64.13
2026.03
63.97
2026.03
63.83
2026.03
63.28
2026.03
63.13
2026.03
63.06
2026.03
62.43
2026.03
62.01
2026.03
61.72
2026.03
59.71
2026.03
59.33
2026.03
50
2026.03
50