Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Household Planning on Household Domains
Loading...
96.7
Success Rate (PC Assembly)
DUPLEX Full System
68.932
76.141
83.35
90.559
Mar 25, 2026
Success Rate (PC Assembly)
Success Rate
Success Rate (Dining Setup)
Success Rate (Cleaning)
Success Rate (Office)
Average Success Rate
Updated 24d ago
Evaluation Results
Method
Method
Links
Success Rate (PC Assembly)
Success Rate
Success Rate (Dining Setup)
Success Rate (Cleaning)
Success Rate (Office)
Average Success Rate
DUPLEX Full System
Method Architecture=Fu...
2026.03
96.7
-
98
70.7
68.7
83.5
DUPLEX Fast System
Method Architecture=Fa...
2026.03
76.7
-
70
30.7
26
50.9
LLM+P
Backbone Model=GPT-4o
2026.03
76
-
4
0
0
20
LLM-as-Planner
Backbone Model=GPT-4o
2026.03
70
-
38.7
0
0
27.2
Feedback
Search any
task
Search any
task