MSSBench
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
MSSBench
93.1Safety Score
25
MSSBench
2.55Safety Score
22
MSSbench (test)
99.66Effectiveness Score
20
MSSBench
96.05RIR
12
MSSBench
70.5Safety Rate
12
MSSBench Embodied
61.97AUPRC (Prompt)
9
MSSBench Chat
52.07AUPRC (Prompt)
9
MSSBench
79.18Safety Score
4