Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Closed-world plan-synthesis on Blocksworld Randomized variant
Loading...
100
Success Rate
Fast Downward
-4
23
50
77
Jul 7, 2026
Success Rate
# Tokens
Updated 17d ago
Evaluation Results
Method
Method
Links
Success Rate
# Tokens
Fast Downward
upper bound=true
2026.07
100
-
EvoPlan
backbone=gpt-oss-120b
2026.07
100
301,100
EvoPlan
backbone=Qwen3-32B
2026.07
78.7
456,100
NL-PDDL
2026.07
70
-
GPT-4o
2026.07
0
835,974
Gemini-2.0 Flash
2026.07
0
835,824
LLaMA-3.1
2026.07
0
842,622
Feedback
Search any
task
Search any
task