Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Common Sense Reasoning on HellaSwag (dev)
Loading...
95.4
Accuracy
DeBERTa-ASA
37.472
52.511
67.55
82.589
Dec 13, 2021
Jan 14, 2022
Feb 15, 2022
Mar 20, 2022
Apr 21, 2022
May 23, 2022
Jun 25, 2022
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
DeBERTa-ASA
Backbone=DeBERTa-large...
2022.06
95.4
DeBERTa (large)
Backbone=DeBERTa-large...
2022.06
94.3
Megatron-NLG
Model Size=530B, Evalu...
2021.12
82.4
GPT-3
Model Size=175B, Evalu...
2021.12
79.3
Gopher
Model Size=280B, Evalu...
2021.12
79.2
GPT-3
Model Size=175B, Evalu...
2021.12
78.9
GPT-3
Model Size=175B, Evalu...
2021.12
78.1
GLaM
Model Size=64B/64E, Ev...
2021.12
77.2
GLaM
Model Size=64B/64E, Ev...
2021.12
76.8
GLaM
Model Size=64B/64E, Ev...
2021.12
76.6
BERT-ASA
Backbone=BERT-base, ta...
2022.06
40.8
BERT
Backbone=BERT-base, ta...
2022.06
39.7
Feedback
Search any
task
Search any
task