Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-horizon robotic manipulation on CALVIN D->D
Loading...
96.4
Success Rate (1 Task)
XR-1
70.608
77.304
84
90.696
Nov 4, 2025
Success Rate (1 Task)
Success Rate (2 Tasks)
Success Rate (3 Tasks)
Success Rate (4 Tasks)
Success Rate (5 Tasks)
Success Rate
Updated 19d ago
Evaluation Results
Method
Method
Links
Success Rate (1 Task)
Success Rate (2 Tasks)
Success Rate (3 Tasks)
Success Rate (4 Tasks)
Success Rate (5 Tasks)
Success Rate
XR-1
2025.11
96.4
90.8
84.5
79.8
74.1
4.256
Qwen-GR00T
2025.11
92.5
83.9
74.4
67.9
59.9
3.786
π0.5
2025.11
92.5
84
76.6
71
64.4
3.885
Qwen-π0
2025.11
90.9
79.5
69.6
62.2
55.4
3.576
π0
2025.11
84.8
70.4
55.9
46.6
37.7
2.954
RDT-1B
2025.11
75.7
49.5
35.9
24.3
18.4
2.038
OpenVLA
2025.11
71.6
38.5
18
8.8
4.1
1.411
Feedback
Search any
task
Search any
task