Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Trajectory Rollout Prediction on DiffReact f2 dense (OOD)
Loading...
0.086
OOD Mean Error
CCM-Coord
0.08192
0.10946
0.137
0.16454
May 14, 2026
OOD Mean Error
OOD Worst Error
OOD Gain vs Base
Updated 2mo ago
Evaluation Results
Method
Method
Links
OOD Mean Error
OOD Worst Error
OOD Gain vs Base
CCM-Coord
2026.05
0.086
0.1
54.2
Oracle per-task
2026.05
0.086
0.1
54.2
Endpoint average
2026.05
0.183
0.224
2.4
Best fixed
2026.05
0.183
0.224
2.4
Base
2026.05
0.188
0.228
-
Feedback
Search any
task
Search any
task