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

Classification on LRA ListOps N=2000 (test)

61.48Accuracy

Full model

14.31626.560538.80551.0495Apr 22, 2022Nov 18, 2022Jun 16, 2023Jan 13, 2024Aug 10, 2024Mar 8, 2025Oct 5, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2024.11
61.48
2024.11
61.48
2024.11
61.48
2024.11
61.48
2024.11
56.42
2024.11
56.27
2024.11
55.82
2024.11
49.95
2025.10
42.2
2025.10
41.9
2025.10
41.6
41.4
2025.10
41.3
2025.10
41
2025.10
40.2
2025.10
39.6
2022.04
39.57
2025.10
38.9
2022.04
38.36
2022.04
37.78
2022.04
37.7
2022.04
37.38
2022.04
37.34
2022.04
37.27
2022.04
37.25
2022.04
37.15
2022.04
37.13
2022.04
37.1
2022.04
36.8
2022.04
36.44
2022.04
36.37
2022.04
36.06
2022.04
35.63
2022.04
32.78
2022.04
19.05
2022.04
18.8
2022.04
18.01
2022.04
17.07
2022.04
16.13