Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Semantic Reasoning Manipulation on DROID Tabletop Semantic tasks
Loading...
26
Success Rate
TiPToP
-1.04
5.98
13
20.02
Mar 10, 2026
Success Rate
Task Progress
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
Task Progress
TiPToP
Scene=Semantic Aggrega...
2026.03
26
71.3
π0.5-DROID
Scene=Semantic Aggrega...
2026.03
10
46.8
TiPToP
Scene=Red A → color pi...
2026.03
5
100
TiPToP
Scene=Sort blocks by c...
2026.03
5
100
TiPToP
Scene=Toy → matching p...
2026.03
4
90
π0.5-DROID
Scene=Banana → matchin...
2026.03
4
90
TiPToP
Scene=Creeper → plate,...
2026.03
3
70
TiPToP
Scene=Largest toy → pl...
2026.03
3
70
π0.5-DROID
Scene=Red A → color pi...
2026.03
3
80
TiPToP
Scene=N block → indica...
2026.03
3
80
TiPToP
Scene=Banana → box, En...
2026.03
2
40
π0.5-DROID
Scene=N block → indica...
2026.03
2
60
π0.5-DROID
Scene=Toy → matching p...
2026.03
1
62
TiPToP
Scene=Banana → matchin...
2026.03
1
20
π0.5-DROID
Scene=Creeper → plate,...
2026.03
0
0
π0.5-DROID
Scene=Largest toy → pl...
2026.03
0
20
π0.5-DROID
Scene=Banana → box, En...
2026.03
0
30
π0.5-DROID
Scene=Sort blocks by c...
2026.03
0
32
Feedback
Search any
task
Search any
task