Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
SINE on Synthetic Arithmetic Tasks
Loading...
100
Success Rate
Global-Local Pipeline
-4
23
50
77
Jun 30, 2025
Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate
Global-Local Pipeline
Initialization=P_s^-,...
2025.06
100
Global-Local Pipeline
Initialization=P_s^-,...
2025.06
100
Global-Local Pipeline
Initialization=P_b^-,...
2025.06
100
Global-Local Pipeline
Initialization=P_r^-,...
2025.06
54.2
Global-Local Pipeline
Initialization=P_r^-,...
2025.06
26.3
Reverse Order
Target Length=L = 10
2025.06
21.8
Reverse Order
Target Length=L = 13
2025.06
15.2
Global-Local Pipeline
Initialization=P_r^-,...
2025.06
8.2
Reverse Order
Target Length=L = 20
2025.06
6.2
Global-Local Pipeline
Initialization=P_b^-,...
2025.06
1.7
Global-Local Pipeline
Initialization=P_s^-,...
2025.06
1.2
Reverse Order
Target Length=L = 30
2025.06
1.1
Reverse Order
Target Length=L = 40
2025.06
0.7
Global-Local Pipeline
Initialization=P_b^-,...
2025.06
0
Feedback
Search any
task
Search any
task