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

Manipulation on OG-Bench puzzle-4x5-play-oraclerep v0

99Success Rate

MAC

-3.9622.7749.576.23Dec 8, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
99
2025.12
91
2025.12
20
2025.12
19
2025.12
1
2025.12
0
2025.12
0
2025.12
0
2025.12
0
2025.12
0