In-distribution
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Full in-distribution (test)
0.964AUROC
63
In-distribution (test)
0.892AUC
40
In-Distribution Avg
45.6Average Score
29
In-Distribution (test)
99.7Accuracy
18
In-Distribution (ID)
10.2Mean Effectiveness Score (ID)
16
In-Distribution n=2,919 (test)
57Average Performance (%)
15
In-distribution (held-out)
0.58Reward
13
In-distribution (InDist) (test)
0.004ADE
10
In-Distribution (ID)
100Accuracy (ID)
9
In-Distribution 5K corpus (test)
47.5Savings Rate
9
In-distribution
98.4r Score
8
In-distribution
1.95NoC@90 Clicks
6
In-distribution
57.4Avg Displacement Error
6
in-distribution clean (test)
53.4F1 Score
5
In-distribution (ID) (test)
95.41Macro F1 Score
5
In-distribution ID (test)
3.87MOS
5
In-Distribution (test)
74SG
2