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

Instruction Following on AlpacaEval Korean

77.8Win Rate

CLO

48.88856.39463.971.406May 20, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.05
77.815.3
2025.05
64.412.3
2025.05
62.5-
2025.05
54.82.5
2025.05
54.82.9
2025.05
541
2025.05
53.92.3
2025.05
53.81.3
2025.05
53-
2025.05
52.5-
2025.05
52.30.9
2025.05
52.3-
2025.05
52.1-
2025.05
51.9-
2025.05
51.6-
2025.05
51.4-
2025.05
51.11.1
2025.05
510.4
2025.05
50.6-
2025.05
50-