Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Embodied Reasoning on EB-Habitat
Loading...
73.33
Base Success Rate
MuSix
52.53
57.93
63.33
68.73
Jul 1, 2026
Base Success Rate
Common Success Rate
Complex Success Rate
Visual Success Rate
Spatial Success Rate
Long Success Rate
Average Success Rate
Updated 24d ago
Evaluation Results
Method
Method
Links
Base Success Rate
Common Success Rate
Complex Success Rate
Visual Success Rate
Spatial Success Rate
Long Success Rate
Average Success Rate
MuSix
backbone=Qwen3-VL-4B-I...
2026.07
73.33
26.67
37.33
42.67
36
26.67
40.44
SayCanPay
2026.07
72
11.67
30.67
37.33
37.33
17.33
34.39
FLARE
paradigm=retrieval-aug...
2026.07
72
4
18.67
29.33
28
10.67
27.11
Conventional MoE
routing=standard top-k...
2026.07
60
10.67
8
32
30.67
12
25.56
LLM-Planner
paradigm=few-shot prom...
2026.07
53.33
2.67
18.67
22.67
30.67
10.67
23.11
Feedback
Search any
task
Search any
task