Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-agent planning on MAP-THOR 2-agent
Loading...
66
SR
LLaMAR
8.8
23.65
38.5
53.35
Jul 14, 2024
SR
Trajectory Rate (TR)
Completion (C)
Bottleneck (B)
Updated 1mo ago
Evaluation Results
Method
Method
Links
SR
Trajectory Rate (TR)
Completion (C)
Bottleneck (B)
LLaMAR
LM=GPT-4V, explanation...
2024.07
66
91
97
82
LLaMAR
LM=GPT-4V, explanation...
2024.07
62
87
95
82
LLaMAR
LM=CogVLM
2024.07
61
89
95
80
LLaMAR
LM=IDEFICS-2
2024.07
57
86
94
78
LLaMAR
LM=LLaVA
2024.07
54
84
91
75
LLaMAR
LM=GPT-4
2024.07
51
85
95
83
ReAct
LM=GPT-4V
2024.07
34
72
92
67
Act
LM=GPT-4V
2024.07
33
67
91
59
CoELA
LM=GPT-4V
2024.07
25
46
76
73
CoT
LM=GPT-4V
2024.07
14
59
87
62
SmartLLM
LM=GPT-4V
2024.07
11
23
91
45
Feedback
Search any
task
Search any
task
