Scenario A
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Scenario A 5% contamination
99ARI
21
Scenario A Multi-Step Financial Transfer
100Accuracy
15
Scenario A (linear, heteroskedastic)
3.4FCR
8
Scenario A Fixed Stance, 8 N Step Disturbance
1.281RMS Error (mm)
7
Scenario A
97.6Finish Rate Avg
7
Scenario A 25 Vehicles
0.435Decision Time (s)
5
Scenario A With External Disturbance 100 independent trials (Simulation)
92Success Rate
4
Scenario A No External Disturbance Simulation 100 independent trials
100Success Rate
4
Scenario A Low Impact 1.0 (test)
0.99Compliance Score
3
Scenario A Online A/B Test
8.356Revenue Lift
1