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

Instruction Following on AlpacaEval Chinese

70.4Win Rate

CLO

49.65560.465.8May 20, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.05
70.411.3
2025.05
65.25.9
2025.05
6412
2025.05
61.12
2025.05
59.95.7
2025.05
59.3-
2025.05
59.1-
2025.05
59.1-
2025.05
57.40.6
2025.05
57.15.7
2025.05
56.8-
2025.05
56.76
2025.05
55.74.6
2025.05
54.2-
2025.05
52-
2025.05
51.4-
2025.05
51.1-
2025.05
50.7-
2025.05
50.6-
2025.05
50.4-0.2