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

NLP tasks

Benchmarks

Task NameDataset NameSOTA ResultTrend
Natural Language Processing7 NLP Tasks (test)
Average Accuracy88.9
20
Natural Language Processing8 NLP Tasks (avg)
Accuracy82.21
10
Natural Language Processingeleven NLP tasks
Average Accuracy73.1
10
NLP tasks11 NLP tasks Symbol-Tuning (held-out)
Accuracy86.4
9
Multiple-Choice Classification14 standard NLP tasks suite (held-out)
StoryCloze86.9
8
Natural Language Understanding10 NLP tasks (BoolQ, CB, COPA, H-SWAG, MultiRC, RTE, Story Cloze, WiC, Winogrande, WSC) (test)
BoolQ92.1
3
Showing 6 of 6 rows