LIBERO-PRO leaderboard
Robustness variant of LIBERO that swaps objects, moves initial positions and rewrites instructions and tasks. Few papers report every cell.
Simulation · Franka Panda · MuJoCo (robosuite)Report an error
69.8%Best · QuoVLA
6Models ranked
OpenSaturation
Nov 18, 2026Numbers checked
| # | Model | Type | Score | Date | Source |
|---|---|---|---|---|---|
| 1 | VLA | 69.8%, self-reported by the authors, not a leaderboard entry | May 2026 | ||
| 2 | VLA | 62.0%, self-reported by the authors, not a leaderboard entry | Oct 2025 | ||
| 3 | SimVLAFrontier Robotics | VLA | 58.6%, self-reported by the authors, not a leaderboard entry | Feb 2026 | |
| 4 | PatchWAMPatchWAM Team | World-action | 57.9%, self-reported by the authors, not a leaderboard entry | Sep 2026 | |
| 5 | VLA | 57.5%, self-reported by the authors, not a leaderboard entry | Oct 2025 | ||
| 6 | VLA | 54.6%, self-reported by the authors, not a leaderboard entry | Oct 2025 |
Metric: Mean success over 20 cells (4 suites × 5 perturbations: original, object, position, semantic, task). One result per model: RoboFYI re-run, then official leaderboard, then paper, then third party. Runs that deviate from the official protocol are listed on the model page but not ranked.
Wrong or missing number? Report an error