Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Robotic Failure Analysis on RoboFAC 1.0 (mixed simulated and real-world)

82.74Task Success Rate (Short Horizon)

RoboFAC-7B

11.520830.010448.566.9896May 18, 2025
Updated 2mo ago

Evaluation Results

MethodLinks
2025.05
82.7484.9281.7883.2868.9479.1
2025.05
81.6684.6779.3283.0263.2976.8
2025.05
63.3253.2345.6748.9141.7251.11
2025.05
61.553.8142.4645.8265.8957.42
2025.05
40.9927.8225.1828.9417.3627.82
2025.05
14.2611.7338.841850.9627.47