Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Commonsense Reasoning on CoS-E v1.0
Loading...
0.695
Score (Finetune+Baseline vs Predict+Baseline)
T5-base
0.50468
0.55409
0.6035
0.65291
May 4, 2023
Score (Finetune+Baseline vs Predict+Baseline)
Score (Finetune+Baseline vs Predict+Infusion)
Simulatability Score
Score (Finetune+Infusion vs Predict+Infusion)
TREU Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Score (Finetune+Baseline vs Predict+Baseline)
Score (Finetune+Baseline vs Predict+Infusion)
Simulatability Score
Score (Finetune+Infusion vs Predict+Infusion)
TREU Score
T5-base
Backbone=T5-base
2023.05
0.695
0.645
-0.05
0.878
0.133
BART-base
Backbone=BART-base
2023.05
0.512
0.486
-0.026
0.79
0.252
Feedback
Search any
task
Search any
task