Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Transitive Reasoning on Mammal
Loading...
71.8
F1 Score
RegD
23.544
36.072
48.6
61.128
Jan 29, 2025
F1 Score
Updated 3mo ago
Evaluation Results
Method
Method
Links
F1 Score
RegD
Variant=ball, d=5
2025.01
71.8
RegD
Variant=box, d=5
2025.01
71.6
ShadowCone*
Variant=Umbral-half, d=5
2025.01
69.4
ShadowCone*
Variant=Penumbral-half...
2025.01
67.8
RegD
Variant=box, d=2
2025.01
64.9
RegD
Variant=ball, d=2
2025.01
62.7
ShadowCone*
Variant=Umbral-half, d=2
2025.01
57.7
EntailmentCone*
d=5
2025.01
56.3
EntailmentCone*
d=2
2025.01
54.4
ShadowCone*
Variant=Penumbral-half...
2025.01
52.8
ELBE
Variant=box baseline, d=5
2025.01
36.8
τBox
d=5
2025.01
33.5
OE
d=5
2025.01
31
ELBE
Variant=box baseline, d=2
2025.01
30.3
τBox
d=2
2025.01
29
ELEM
Variant=ball baseline,...
2025.01
28.8
ELEM
Variant=ball baseline,...
2025.01
27.7
OE
d=2
2025.01
25.4
Feedback
Search any
task
Search any
task