Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Balance Scale Manipulation on Real-world robot tasks 1.0 (test)

90Success Rate

Claude-4.6

-3.620.74569.3May 26, 2026
Updated 7d ago

Evaluation Results

MethodLinks
2026.05
90
2026.05
80
2026.05
80
2026.05
80
2026.05
70
2026.05
60
2026.05
60
2026.05
40
2026.05
0
2026.05
0
2026.05
0
2026.05
0
2026.05
0
2026.05
0
2026.05
0
2026.05
0