ML
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
ML-1M
80.99AUC
49
ML 1M
0.909AUC
46
ML-100K
13.29NDCG@20
34
ML-20M
0.78NDCG@10
26
ML 20% 20M (test)
0.799RMSE
24
ML 20% 10M (test)
0.807RMSE
24
Ml 1M (test)
21.2Recall
24
ML
36.7Claude-4 Sonnet Score
24
ML 1M
0.208Recall@10
22
ML OOD 10M
61Hit Rate @10
18
ML-100K
46.15HR@5
18
ML-20M large (test)
0.403Recall@20
17
ML 1M (test)
32.94HR@10
16
ML-10M
75.91HR@5
15
ML-20M strong generalization
0.396AOA Recall@20
14
ML 10M
9.16HR@10
13
ML-1M
81.24HR@5
13
ML-1M
59HR@5
12
ML 10M
19.34Recall@10
12
ML-1M (test)
62.6N@10
12
ML-100K
19.21NDCG@1
11
ML-1M
0.819AUC
11
ML 32M
18.02HR@5
10
ML-1M Head
4.46NDCG@10
10
ML-10M (test)
0.777RMSE
10