Human Evaluation of Robot Rollout Generation on WorldArena rollouts
1.81Task SuccessPelican-Unified 1.0
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Pelican-Unified 1.0Model Access=Local2026.05 | 1.81 | 2 | 2 | 1.23 | 1.76 | |
| Happyhorse-1.0Model Access=API2026.05 | 1.65 | 1.81 | 2 | 0.13 | 1.4 | |
| Seedance2.0Model Access=API2026.05 | 1.21 | 1.87 | 1.98 | 1.15 | 1.55 | |
| Wan2.7Model Access=API2026.05 | 1.19 | 1.68 | 2 | 0.29 | 1.29 | |
| Cosmos-Predict2Model Access=Local2026.05 | 0.63 | 1.85 | 1.79 | 0.35 | 1.16 | |
| GigaWorld-0Model Access=Local2026.05 | 0.33 | 1.94 | 1.98 | 0.13 | 1.09 | |
| UnifoLM-WMA-0Model Access=Local2026.05 | 0.05 | 1.48 | 2 | 0.11 | 0.91 | |
| EnerVerse-ACModel Access=Local2026.05 | 0 | 1.84 | 2 | 1.64 | 1.37 |