MolmoAct2: Action Reasoning Models for Real-world Deployment
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-vqa-on-blink
Molmo2-ER
#4
Accuracy: 72.5
robot-manipulation-on-libero
MolmoAct2-Think
#48
Success Rate: 98.10
robot-manipulation-on-libero
MolmoAct2
#78
Success Rate: 97.20
Rank counts only results with a code link.