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

Trajectory Completion Judgment on OGRBench Mobile

91Accuracy

StainFlow

63.33670.51877.784.882Jun 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
9191.3
2026.06
89.990.4
2026.06
89.490
2026.06
86.787.3
2026.06
85.686.2
2026.06
85.687.2
2026.06
85.184.4
2026.06
85.184.6
2026.06
8482.8
2026.06
8385.6
2026.06
81.483.1
2026.06
80.382.8
2026.06
77.179.2
2026.06
75.578.9
2026.06
73.479.3
2026.06
72.971.8
2026.06
71.370
2026.06
67.666.3
2026.06
64.962.9
2026.06
64.455.6