ListOps
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
ListOps
98.85Accuracy (%)
35
ListOps
78Accuracy
32
ListOps Long Range Arena (test)
63.04Accuracy
26
Long ListOps (test)
62.75Accuracy
22
ListOps
61.3Accuracy
12
ListOps-O Argument Generalization (Arguments 15)
79Accuracy
11
ListOps-O Argument Generalization (Arguments 10)
0.842Accuracy
11
ListOps-O Length Generalization (Lengths 900-1000)
99.5Accuracy
11
ListOps-O Length Generalization (Lengths 500-600)
99.4Accuracy
11
ListOps-O Length Generalization (Lengths 200-300)
99.9Accuracy
11
ListOps-O near-IID (Lengths < 1000, Arguments < 5)
99.9Accuracy
11
ListOps (5, 14) (test)
53.1Mean Accuracy
7
ListOps (5, 9) (test)
49.6Mean Accuracy
7
ListOps (3, 14) (test)
79.1Mean Accuracy
7
ListOps (3, 9) (test)
89.9Mean Accuracy
7
ListOps Long Range Arena (test)
41.4Accuracy
7
ListOps mid L1024
85.4Accuracy
6
ListOps Long Range Arena (LRA) 2K (test)
37.9Accuracy
6
ListOpsMix (test)
70.43Accuracy
5
ListOps (test)
68.07Accuracy
5
ListOps (val)
67.65Accuracy
5
ListOps simplified (test)
93.78Accuracy (Max)
4