Movies
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Movies
65.74Accuracy
139
Movies
90.2F1 Score
26
Movies
0.17HR@10
15
Movies
24.59Recall
14
Movies MAGB
53.98Accuracy
13
Movies
56.53NMI
12
Movies
92.45Accuracy (%)
11
Movies
80.14AUROC
10
Movies (test)
94.15AuROC
10
Movies
0.078NDCG
8
Movies
82.9Accuracy
7
Movies
12.31Recall@10
7
Movies
31.31FP
6
Movies (test)
66.56AUPRC (pp)
6
Movies (test)
7.5CER
6
Movies
0.934Precision
6
Movies ERASER (test)
91Task Weighted Avg F1
5
Movies
0.624MRR
3
Movies Human Evaluation (Ranking)
275Rationale Quality (Rank-1)
3
Movies internal (test)
23.56DER
3
Movies (1:9)
42.17FP Rate
3
Movies (Out-of-Distribution)
94.5Accuracy
3
Movies (test)
42.4Accuracy
2
Movies
67.68End-to-end running time (min)
2