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

Trajectory completion judgment on OGRBench (Overall)

88.2Accuracy

StainFlow

61.1668.1875.282.22Jun 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
88.287.58988.2
2026.06
87.486.488.687.5
2026.06
86.688.484.186.2
2026.06
86.4898385.6
2026.06
84.783.885.784.8
2026.06
84.582.287.984.9
2026.06
83.580.68884.2
2026.06
81.980.683.782.1
2026.06
81.580.183.681.8
2026.06
81.175.591.982.9
2026.06
80.786.372.778.9
2026.06
80.176.985.781.1
2026.06
80.189.967.477.1
2026.06
79.184.970.477
2026.06
7769.894.780.4
2026.06
69.480.750.462
2026.06
67.278.147.358.9
2026.06
67.180.544.757.5
2026.06
667646.157.4
2026.06
62.281.131.345.2