CLUTRR
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
CLUTRR
0.69Empirical Generalization Error G(W)
60
CLUTRR
95.9Accuracy
54
CLUTRR (test)
80.1Accuracy
39
CLUTRR (test)
76.4Accuracy
24
Clutrr
95.5Pass@1
18
CLUTRR
78Accuracy
18
CLUTRR rob_train_disc_23_all (test)
41.6Accuracy
3
CLUTRR rob train irr 23 all (test)
34.5Accuracy
3
CLUTRR rob_train_sup_23_all (test)
45.2Accuracy
3
CLUTRR rob train clean 23 all (test)
35.6Accuracy
3
CLUTRR gen_train234_test2to10
25Accuracy
3
CLUTRR gen_train23_test2to10
24Accuracy
3