Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Skill evolution on App permission
Loading...
93.67
Best@20
MaskClaw
88.9865
91.32825
93.67
96.01175
May 27, 2026
Best@20
Base Accuracy
Evo Accuracy
Base Unsafe Rate
Evo Unsafe Rate
Compliance
Updated 6d ago
Evaluation Results
Method
Method
Links
Best@20
Base Accuracy
Evo Accuracy
Base Unsafe Rate
Evo Unsafe Rate
Compliance
MaskClaw
Tests=8
2026.05
93.67
25
100
75
0
100
Feedback
Search any
task
Search any
task