Wiki
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Wiki
2Perplexity (PPL)
298
wiki (test)
84.57Accuracy
56
Wiki
3.53Perplexity
54
Wiki
35.8ARI
41
Wiki
0.041MAE
32
Wiki 500K
81.26P@1
30
WIKI
0.46MRR
28
WIKI (test)
84.5Micro F1
27
Wiki
68F1 Score
25
wiki
0.214CRPS
25
Wiki
1,657Topic Judge Elo Score
24
WIKI (test)
89.2Micro F1
24
Wiki
59.67Accuracy
23
Wiki
0.591Micro F1
23
Wiki ZSL (test)
71.54Precision (%)
22
WIKI v1.0 (test)
95.9AUC
21
Wiki
0.036SMAPE
20
WIKI (meta-test)
33.5MRR
19
wiki (test)
0.214CRPS
19
Wiki
62.07BLEU
18
Wiki real-world (test)
-1.373Negative Log-Likelihood
18
WIKI (test)
99.28Positive Performance
17
WIKI (test)
55.52BLEU-4
17
WIKI (test)
30.9MRR
17
Wiki
0.12Clustering Time (s)
16