Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Goal Prediction on Sokoban OOD
Loading...
80
Classification Accuracy
SVoTp
33.2
45.35
57.5
69.65
Jun 10, 2026
Classification Accuracy
Free-response Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Classification Accuracy
Free-response Accuracy
SVoTp
Size=4, Backbone=Anole
2026.06
80
68.3
SVoTp
Size=5, Backbone=Anole
2026.06
73.3
53.3
SVoTo
Size=4, Backbone=Anole
2026.06
70
50
SVoTp
Size=6, Backbone=Anole
2026.06
65
48.3
SVoTo
Size=5, Backbone=Anole
2026.06
63.3
45
MVoT
Size=4, Backbone=Anole
2026.06
61.7
3.3
T-CoT
Size=4, Backbone=GPT-4o
2026.06
56.7
36.7
SVoTo
Size=6, Backbone=Anole
2026.06
56.7
33.3
MVoT
Size=5, Backbone=Anole
2026.06
55
3.3
T-CoT
Size=4, Backbone=Anole
2026.06
53.3
0
MVoT
Size=6, Backbone=Anole
2026.06
51.7
6.7
T-CoT
Size=5, Backbone=Anole
2026.06
50
0
T-CoT
Size=5, Backbone=GPT-4o
2026.06
43.3
20
T-CoT
Size=6, Backbone=Anole
2026.06
41.7
3.3
T-CoT
Size=6, Backbone=GPT-4o
2026.06
35
16.7
Feedback
Search any
task
Search any
task