Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Embodied Manipulation on Guava Simulation (OOD Object)
Loading...
100
Success Rate (Pick Up Carrot)
CaP-Agent0
65.368
74.359
83.35
92.341
Jun 16, 2026
Success Rate (Pick Up Carrot)
Success Rate
Success Rate (Tomato Near Potato)
Success Rate (Lemon In Bin)
Success Rate (Push Pot)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate (Pick Up Carrot)
Success Rate
Success Rate (Tomato Near Potato)
Success Rate (Lemon In Bin)
Success Rate (Push Pot)
CaP-Agent0
Episodes=15
2026.06
100
-
86.7
100
20
GPT-5.4
Episodes=15
2026.06
100
-
86.7
100
26.7
Guava-Agent-4B
Episodes=15
2026.06
100
-
86.7
100
73.3
Qwen3.5-4B
Episodes=15
2026.06
66.7
-
40
20
33.3
Feedback
Search any
task
Search any
task