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

Open-ended Generation on AlpacaEval

93.5Win Rate vs Davinci-003

GPT-4

1.4625.35549.2573.145Jun 7, 2023Nov 24, 2023May 12, 2024Oct 29, 2024Apr 17, 2025Oct 4, 2025Mar 23, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2023.06
93.5
2023.06
83.6
2024.02
81.69
2024.02
81.48
2024.02
80.93
73.6
64
2023.06
62.3
2023.06
61.8
57.3
2023.06
56.5
2023.06
48.6
43.4
2026.03
24.6
2026.03
22.51
2024.03
21.8
2026.03
21.12
2026.03
20
2026.03
19.3
2026.03
18.88
2026.03
17.83
2026.03
17.54
2026.03
17.39
2026.03
16.94
2026.03
15.82
2026.03
15.28
2024.03
14.7
2026.03
13.56
2026.03
13.47
2026.03
12.95
2026.03
11.74
2024.03
11.3
2024.03
9.6
2026.03
9.33
2026.03
8.58
2024.03
8
2024.03
7.7
2024.03
7.5
2024.03
6.9
2024.03
5