RynnVLA-002: A Unified Vision-Language-Action and World Model

Benchmark Model Rank Results
robot-manipulation-on-libero-objectRynnVLA-002#12Success Rate: 99.8
robot-manipulation-on-libero-spatialRynnVLA-002#18Success Rate: 99.0
robot-manipulation-on-libero-longRynnVLA-002#56Success Rate: 94.4
robot-manipulation-on-libero-goalRynnVLA-002#67Success Rate: 96.4
robot-manipulation-on-liberoRynnVLA-002#68Success Rate: 97.4