Human Preference Evaluation on EgoDex and DreamDojo-HV novel out-of-distribution (eval)
73.5Physics CorrectnessDreamDojo-14B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DreamDojo-14BComparison Baseline=Cosmos-Predict2.52026.02 | 73.5 | 72.55 | |
| DreamDojo-14BComparison Baseline=DreamDojo-2B2026.02 | 72.5 | 65.53 | |
| DreamDojo-2BComparison Baseline=Cosmos-Predict2.52026.02 | 62.5 | 63.45 |