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

Relational Reasoning on CLUTRR

0.69Empirical Generalization Error G(W)

CoLA

0.4981.7943.094.386Jun 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
0.69
2026.06
0.94
2026.06
0.95
2026.06
0.96
2026.06
0.97
2026.06
1
2026.06
1
2026.06
1
2026.06
1.01
2026.06
1.01
2026.06
1.04
2026.06
1.09
2026.06
1.12
2026.06
1.15
2026.06
1.55
2026.06
1.55
2026.06
1.63
2026.06
1.88
2026.06
1.89
2026.06
1.91
2026.06
2.06
2026.06
2.16
2026.06
2.16
2026.06
2.19
2026.06
2.19
2026.06
2.25
2026.06
2.25
2026.06
2.27
2026.06
2.27
2026.06
2.34
2026.06
2.34
2026.06
2.44
2026.06
2.51
2026.06
2.51
2026.06
2.53
2026.06
2.53
2026.06
2.59
2026.06
2.59
2026.06
2.65
2026.06
2.65
2026.06
2.66
2026.06
2.66
2026.06
2.69
2026.06
2.69
2026.06
2.9
2026.06
2.9
2026.06
2.97
2026.06
2.97
2026.06
4.23
2026.06
4.23
2026.06
4.29
2026.06
4.29
2026.06
4.33
2026.06
4.33
2026.06
5.02
2026.06
5.02
2026.06
5.48
2026.06
5.48
2026.06
5.49
2026.06
5.49