Coffee
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Coffee (test)
1.2MSE
10
Coffee (test)
1Accuracy
10
Coffee simulated environment
96Success Rate
6
Coffee
80.89Accuracy
6
Coffee
100Effectiveness
6
Coffee D2 MimicGen (10° perturbation)
38Success Rate
5
Coffee
1Effectiveness
5
Coffee
100Accuracy
5
Coffee
99.3Success Rate
3
Coffee
1Validation Score
3
Coffee
99.826Precision
3
Coffee drawer Hard (test)
70Success Rate
2
Coffee box Medium (test)
10Successes
2