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

Hierarchical reasoning on symbolic sequences on Long ListOps (test)

62.75Accuracy

Liquid-S4

13.942826.613939.28551.9561May 2, 2023
Updated 1mo ago

Evaluation Results

MethodLinks
2023.05
62.75
2023.05
62.75
2023.05
62.15
2023.05
61.45
2023.05
60.52
2023.05
59.6
2023.05
57.6
2023.05
49.53
2023.05
44.05
2023.05
37.27
2023.05
37.25
2023.05
37.15
2023.05
36.37
2023.05
36.05
2023.05
35.63
2023.05
35.33
2023.05
33.67
2023.05
18.01
2023.05
17.07
2023.05
16.13
2023.05
16.13
2023.05
15.82