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

CoS-E

Benchmarks

Task NameDataset NameSOTA ResultTrend
Commonsense ReasoningCoS-E v1.0
Score (Finetune+Baseline vs Predict+Baseline)0.695
2
Commonsense ReasoningCoS-E v1.11
Score (Finetune+Baseline vs Predict+Baseline)0.608
2
Showing 2 of 2 rows