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

Date Understanding

Benchmarks

Task NameDataset NameSOTA ResultTrend
Symbolic ReasoningDate Understanding (DU)
Accuracy87.2
10
Multiple-Choice ReasoningDate Understanding (test)
Accuracy78.2
8
Symbolic ReasoningDate Understanding (DU) (test)
Accuracy67.52
4
Commonsense ReasoningDate Understanding
Accuracy16.3
3
Logical ReasoningDate Understanding
Accuracy (format-specific prompt)67.5
2
Showing 5 of 5 rows