Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Task Completion on L-IVA 1.0 (test)
Loading...
73.8
Task Success Rate - Kit
ORCA
56.016
60.633
65.25
69.867
Dec 23, 2025
Task Success Rate - Kit
Task Success Rate - Live
Task Success Rate - Work
Task Success Rate - Gard
Task Success Rate - Off
Task Success Rate - Avg
Physical Plausibility - Kit
Physical Plausibility - Live
Physical Plausibility - Work
Physical Plausibility - Gard
Physical Plausibility - Off
Physical Plausibility - Avg
Action Fidelity - Kit
Action Fidelity - Live
Action Fidelity - Work
Action Fidelity - Gard
Action Fidelity - Off
Action Fidelity - Avg
Updated 4d ago
Evaluation Results
Method
Method
Links
Task Success Rate - Kit
Task Success Rate - Live
Task Success Rate - Work
Task Success Rate - Gard
Task Success Rate - Off
Task Success Rate - Avg
Physical Plausibility - Kit
Physical Plausibility - Live
Physical Plausibility - Work
Physical Plausibility - Gard
Physical Plausibility - Off
Physical Plausibility - Avg
Action Fidelity - Kit
Action Fidelity - Live
Action Fidelity - Work
Action Fidelity - Gard
Action Fidelity - Off
Action Fidelity - Avg
ORCA
2025.12
73.8
58.4
80.4
81.5
61
71
3.53
3.68
3.93
3.77
3.67
3.72
64
70
54
63
70
64
Open-Loop
2025.12
72.3
72.3
72.7
46.2
47.9
62.3
3.57
3.5
3.27
2.92
2.6
3.17
57
72
53
64
65
62
VAGEN
2025.12
70.8
63.6
61.1
60
50.4
61.2
3.56
3.59
3.67
2.54
2.73
3.22
64
63
59
58
68
62
Reactive
2025.12
56.7
58.7
45.8
55
38.1
50.9
3.47
3.05
3.13
3.08
2.8
3.11
53
56
41
61
63
55
Feedback
Search any
task
Search any
task
