Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-Horizon TAMP on Calvin Unconstrained
Loading...
100
SR (3/5)
ReStruct
-0.776
25.387
51.55
77.713
Jun 25, 2026
SR (3/5)
SR (4/5)
SR (5/5)
Updated 1mo ago
Evaluation Results
Method
Method
Links
SR (3/5)
SR (4/5)
SR (5/5)
ReStruct
Param (M)=571
2026.06
100
93.8
93.8
Flower*
Param (M)=947, Fine-tu...
2026.06
93.8
93.8
76.6
ReStruct
Param (M)=571
2026.06
90.6
84.4
81.3
Flower*
Param (M)=947, Fine-tu...
2026.06
78.1
78.1
54.7
Flower
Param (M)=947
2026.06
73.4
70.3
60.9
Flower
Param (M)=947
2026.06
64.1
51.6
45.3
LCD
Param (M)=68
2026.06
15.6
15.6
9.4
MDT
Param (M)=440
2026.06
15.6
15.6
15.6
LCD
Param (M)=68
2026.06
14.1
10.9
3.1
MDT
Param (M)=440
2026.06
14.1
10.9
10.9
HULC
Param (M)=47
2026.06
6.3
0
0
HULC
Param (M)=47
2026.06
3.1
3.1
3.1
Feedback
Search any
task
Search any
task