Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety and Utility Evaluation on FINVAULT
Loading...
50.5
Approve Rate
B5 LF-A
6.716
18.083
29.45
40.817
May 26, 2026
Approve Rate
ASR
Net Score
Updated 7d ago
Evaluation Results
Method
Method
Links
Approve Rate
ASR
Net Score
B5 LF-A
mapping=advisory, base...
2026.05
50.5
40.2
10.3
FH-post
mode=observation-aware...
2026.05
46.7
19.6
27.1
B0
2026.05
41.1
38.3
2.8
FH-routed
mode=cost-aware pre-ex...
2026.05
39.3
15
24.3
B1
2026.05
38.3
28
10.3
FH-AA
mode=always-advanced a...
2026.05
37.4
8.4
29
B3
2026.05
36.4
17.8
18.6
B4
2026.05
36.4
20.6
15.8
B2
2026.05
35.5
26.2
9.3
B5 LF-S†
mapping=strict / fail-...
2026.05
26.2
5.6
20.6
B6 GA
2026.05
8.4
2.8
5.6
B7 IA
2026.05
8.4
0.9
7.5
Feedback
Search any
task
Search any
task