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

Task Planning on BoxNet3D-OBS (test)

62Success Rate

NC-REPLAN-S3

-1.4415.0331.547.97Apr 22, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
62-0.11
2026.04
57-0.14
2026.04
53-0.08
2026.04
53-0.25
2026.04
51-0.12
2026.04
47-0.28
2026.04
350.21
2026.04
330.09
2026.04
320.34
2026.04
290.12
2026.04
290.17
2026.04
28-0.05
2026.04
27-0.12
2026.04
26-0.18
2026.04
24-0.08
2026.04
230.1
2026.04
210.15
2026.04
190.12
2026.04
180.18
2026.04
15-0.11
2026.04
140.31
2026.04
130.25
2026.04
11-0.04
2026.04
110.14
2026.04
10-0.01
2026.04
90.18
2026.04
90.16
2026.04
80.26
2026.04
80.22
2026.04
80.39
2026.04
80.25
2026.04
70.35
2026.04
60.43
2026.04
60.45
2026.04
50.75
2026.04
50.24
2026.04
50.31
2026.04
50.52
2026.04
40.64
2026.04
40.79
2026.04
40.28
2026.04
40.48
2026.04
30.52
2026.04
31.34
2026.04
20.85
2026.04
21.53
2026.04
21.14
2026.04
10.76