Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Embodied Manipulation on Guava Simulation OOD Long Horizon
Loading...
93.3
Success Rate: Separate Food and Utensils
Guava-Agent-4B
-3.732
21.459
46.65
71.841
Jun 16, 2026
Success Rate: Separate Food and Utensils
Overall Success Rate
Success Rate: Set Table
Success Rate: Shell Game
Success Rate: Place Red Objects in Basket
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate: Separate Food and Utensils
Overall Success Rate
Success Rate: Set Table
Success Rate: Shell Game
Success Rate: Place Red Objects in Basket
Guava-Agent-4B
Episodes=15
2026.06
93.3
-
93.3
6.7
0
CaP-Agent0
Episodes=15
2026.06
86.7
-
93.3
0
53.3
GPT-5.4
Episodes=15
2026.06
86.7
-
93.3
46.7
80
Qwen3.5-4B
Episodes=15
2026.06
0
-
20
53.3
0
Feedback
Search any
task
Search any
task