Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Closed-world plan-synthesis on ALFWorld unseen (val)
Loading...
100
Success Rate (SR)
Fast Downward (upper bound)
77.536
83.368
89.2
95.032
Jul 7, 2026
Success Rate (SR)
Total Tokens
Updated 16d ago
Evaluation Results
Method
Method
Links
Success Rate (SR)
Total Tokens
Fast Downward (upper bound)
2026.07
100
-
GPT-5.5 (LLM+VAL loop)
Backbone=GPT-5.5
2026.07
100
2,770,945
EvoPlan
Backbone=Qwen3-32B
2026.07
90.3
10,349,634
EvoPlan
Backbone=gpt-oss-120b
2026.07
78.4
17,071,316
Feedback
Search any
task
Search any
task