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

Preference Alignment on Argilla

5.9Reward (R)

AAD

-1.13040.69482.524.3452Sep 30, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.09
5.9-
2025.09
5.64-
2025.09
5.25-
2025.09
5.0156
2025.09
4.6572
2025.09
4.5470
2025.09
4.0676
2025.09
3.84-
2025.09
3.6479
2025.09
3.39-
2025.09
3.2861
2025.09
3.1686
2025.09
3.0284
2025.09
2.8258
2025.09
2.5587
2025.09
2.4886
2025.09
2.33-
2025.09
2.1772
2025.09
1.9952
2025.09
1.9478
2025.09
1.7289
2025.09
1.6575
2025.09
1.5991
2025.09
1.5988
2025.09
1.3782
2025.09
0.787
2025.09
0.6877
2025.09
0.1280
2025.09
0.0285
2025.09
-0.8689