Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Long-horizon robotic manipulation on Long-horizon tasks (test)
Loading...
0.445
PFC Score
MIND-V
0.40028
0.41189
0.4235
0.43511
Dec 7, 2025
PFC Score
Task Success Rate
User Study Preference
Updated 4d ago
Evaluation Results
Method
Method
Links
PFC Score
Task Success Rate
User Study Preference
MIND-V
Mode=Full Model
2025.12
0.445
61.3
46.7
WoW-1-DiT-7B
Architecture=DiT, Size=7B
2025.12
0.423
32.2
16.7
WoW-1-Wan-14B
Architecture=Wan, Size...
2025.12
0.42
34.7
23.3
Robodreamer
2025.12
0.418
27.5
6.7
HunyuanVideo
2025.12
0.411
9.8
3.3
Wan2.2-14B
Architecture=Wan, Vers...
2025.12
0.402
11.1
0
Feedback
Search any
task
Search any
task