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

Planning Accuracy on Blocksworld (test)

98.2Accuracy

DeepSeek-R1

-3.30423.04849.475.752May 22, 2026May 29, 2026Jun 6, 2026Jun 13, 2026Jun 21, 2026Jun 28, 2026Jul 6, 2026
Updated 18d ago

Evaluation Results

MethodLinks
98.2
2026.07
97.8
2026.05
97
2026.05
96
2026.05
93
2026.07
88.8
2026.05
87
2026.05
83
2026.05
82
2026.05
81.4
2026.05
79
2026.05
77.4
2026.07
77.2
2026.05
76
2026.07
73.8
2026.05
71
2026.05
62
2026.05
60
2026.05
58
2026.05
57
2026.05
55
2026.05
53
2026.07
52.6
44.8
2026.07
42.4
2026.07
42
2026.05
41
2026.05
37
2026.07
31.2
21.6
13.8
2026.05
9
2026.05
2
1.4
0.6