Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Generalized Planning on PDDL trapnewspapers domain
Loading...
100
Solution Percentage
cot4
-4
23
50
77
Mar 10, 2026
Solution Percentage
Runtime
Score
Cost
Generation Time
Updated 1mo ago
Evaluation Results
Method
Method
Links
Solution Percentage
Runtime
Score
Cost
Generation Time
cot4
LLM=GPT-4
2026.03
100
0.1
0.75
-
-
cot4o
LLM=GPT-4o
2026.03
100
0.12
0.75
-
-
evo_nev
Variant=No Evolution
2026.03
100
0.1
0.75
1.22
462
evo_mini
LLM=GPT-4o-mini
2026.03
100
0.11
0.75
0.08
1,088.75
evo_ds
Variant=DS
2026.03
100
0.09
1
1.44
1,761.47
evo
Name=GenePlan (Full)
2026.03
100
0.1
0.94
1.11
396.38
fd_1800
Search Limit=1800s
2026.03
86.67
216.66
0.7
-
-
fd_300
Search Limit=300s
2026.03
83.33
71.69
0.64
-
-
fd_opt
Search Strategy=Optimal
2026.03
0
-
0
-
-
evo_abl
Variant=Ablation
2026.03
0
-
0
-
-
Feedback
Search any
task
Search any
task
