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

LLM-as-a-judge on AlpacaEval

78.3Coverage

Heuristic Selection

31.39643.57355.7567.927May 14, 2026
Updated 16d ago

Evaluation Results

MethodLinks
2026.05
78.30
2026.05
74.50
2026.05
54.564.7
2026.05
54.582.1
2026.05
52.672.8
2026.05
5275.7
2026.05
48.774.6
2026.05
38.494.8
2026.05
37.686.9
2026.05
34.693.4
2026.05
34.190.8
2026.05
33.292