ROPES
Benchmarks
TaskDatasetSOTA resultTrendResults
Ropes In-domain (Brown, Yellow, Red, Orange)
0Average Distance Error (45cm, 5g)
14
ROPES
58.64F1 Score
14
ROPES
77.63F1 Score
10
ROPES
94.66Refusal F1
8
ROPES CS
45.5Score
6
ROPES
67Score
6
ROPES
0.752Accuracy
5