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

Trajectory completion judgment on OGRBench Windows

85.5Accuracy

OS-Themis

72.70876.02979.3582.671Jun 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
85.583.2
2026.06
8583.7
2026.06
8481.1
2026.06
8483
2026.06
82.278.9
2026.06
82.281
2026.06
81.776.4
2026.06
80.875.7
2026.06
79.877.5
2026.06
78.977.2
2026.06
78.477.2
2026.06
78.477
2026.06
77.568.8
2026.06
7770.7
2026.06
7771
2026.06
76.167.5
2026.06
75.168.3
2026.06
74.262.1
2026.06
73.771.7
2026.06
73.274.9