DeepSeek Harness

Overall

Built-in sandbox
00 passed · 38 failed
FinShield
10038 passed · 0 failed

Category scores

CategoryBuilt-in sandboxFinShield
Privacy
00 passed · 4 failed
1004 passed · 0 failed
Interaction
00 passed · 13 failed
10013 passed · 0 failed
System
00 passed · 13 failed
10013 passed · 0 failed
Data
00 passed · 8 failed
1008 passed · 0 failed