Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Med

Benchmarks

Task NameDataset NameSOTA ResultTrend
Author DisambiguationMed
MRR87.1
9
Paper-Venue PredictionMed
NDCG0.446
9
Paper-Field (L2) ClassificationMed
NDCG38.4
9
Paper-Field (L1) ClassificationMed
NDCG70.9
9
Retrieval EfficiencyMed.
Retrieved Tokens23,657
8
ClusteringMED
Purity0.59
6
Machine TranslationMed. En-De out-of-domain WMT14 (test)
BLEU30.8
5
Natural Language InferenceMED (test)
Upward Acc91.4
5
Showing 8 of 8 rows