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

Chat on AlpacaEval

3,213Win Rate

Fine-tuned

-128.1872739.23641,606.662,474.0836Oct 25, 2023Feb 19, 2024Jun 16, 2024Oct 12, 2024Feb 6, 2025Jun 4, 2025Sep 30, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.04
3,213
2025.04
1,877
2025.04
1,839
2025.04
1,776
2025.04
1,718
2025.04
1,563
2025.04
988
2025.04
845
2025.04
713
2025.04
572
2025.04
227
2023.10
95.57
2023.10
95.28
2025.09
94.6
2023.10
92.66
2023.10
91.36
2023.10
90.6
2025.09
90.05
2025.09
89.92
2025.09
89.91
2025.09
89.84
2023.10
89.37
2023.10
88.99
2025.09
88.69
2023.10
87.83
2023.10
71.8
2025.09
71.18
2025.04
71
2025.09
70.42
2025.09
70.42
2025.09
69.8
2025.09
69.64
2025.09
67.67
2023.10
45.71
2025.04
36
2025.09
31.24
2025.04
10
2025.04
8
2025.09
0.32