Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Commonsense Reasoning on HellaSwag (leaderboard)
Loading...
95.6
Accuracy
Human
81.144
84.897
88.65
92.403
Mar 24, 2021
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Human
2021.03
95.6
UNICORN
2021.03
93.9
RoBERTa-Large Ensemble
ensemble=true
2021.03
85.5
HYKAS+CSKG
2021.03
85
RoBERTa-Large
2021.03
81.7
Feedback
Search any
task
Search any
task