Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Abductive Reasoning on ART10
Loading...
4.45
Average Rating
References
2.682
3.141
3.6
4.059
May 3, 2023
Average Rating
% Gap Closed
Updated 3mo ago
Evaluation Results
Method
Method
Links
Average Rating
% Gap Closed
References
Type=Golden references
2023.05
4.45
-
T5-L
Model size=Large, Type...
2023.05
4
-
T5-KD
Type=Final distilled m...
2023.05
3.65
72
T5-S
Model size=Small, Type...
2023.05
2.75
-
Feedback
Search any
task
Search any
task