Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Visual Entailment on e-SNLI-VE e-ViL (test)
Loading...
85.7
Human Eval
OFA-X
57.412
64.756
72.1
79.444
Dec 8, 2022
Human Eval
Meteor
BERTScore
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Human Eval
Meteor
BERTScore
Accuracy
OFA-X
model_variant=large (4...
2022.12
85.7
18.6
80.9
80.9
Ground-truth
2022.12
85
-
-
-
OFA-XMT
model_variant=large (4...
2022.12
80.4
17.9
80.3
78.9
e-UG
2022.12
68.9
19.6
81.7
79.5
NLX-GPT
2022.12
67.4
18.8
80.8
73.91
PJ-X
2022.12
59.6
14.7
79.1
69.2
FME
2022.12
58.5
15.6
79.7
73.7
Feedback
Search any
task
Search any
task