Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Planning on Full Sokoban
Loading...
46
Validity Rate
L-ICL
-1.84
10.58
23
35.42
Jan 30, 2026
Validity Rate
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Validity Rate
Success Rate
L-ICL
Number of training exa...
2026.01
46
20
L-ICL
Number of training exa...
2026.01
42
14
RAG-ICL
Context size (characte...
2026.01
36
15
RAG-ICL
Context size (characte...
2026.01
31
11
L-ICL
Number of training exa...
2026.01
19
13
L-ICL
Number of training exa...
2026.01
12
9
ReAct
Inference feedback=Ora...
2026.01
3
0
Self-Consistency
Reasoning samples (k)=...
2026.01
2
1
Zero-Shot
Input representation (...
2026.01
1
0
ReAct
Prompting strategy=ReA...
2026.01
1
0
Self-Refine
Reasoning samples (k)=...
2026.01
0
0
ToT
Prompting strategy=ToT...
2026.01
0
0
Feedback
Search any
task
Search any
task
