Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Financial Safety Evaluation on FinRED R3: Misinformation

97.76ASR

GPTFuzzer (Black-box)

-3.910422.484848.8875.2752Jun 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
97.76
2026.06
97.01
2026.06
87.01
2026.06
86.57
2026.06
76.87
2026.06
73.13
2026.06
71.04
2026.06
70.15
2026.06
66.42
2026.06
66.41
2026.06
64.17
2026.06
59.7
2026.06
58.81
2026.06
54.18
2026.06
52.99
2026.06
42.39
2026.06
41.79
2026.06
39.55
2026.06
38.06
2026.06
37.55
2026.06
35.07
2026.06
34.33
2026.06
33.58
2026.06
32.09
2026.06
32.09
2026.06
31.34
2026.06
31.34
2026.06
31.34
2026.06
31.34
2026.06
29.1
2026.06
27.61
2026.06
27.61
2026.06
27.61
2026.06
26.87
2026.06
26.87
2026.06
23.88
2026.06
23.88
2026.06
20.15
2026.06
20.15
2026.06
19.4
2026.06
16.42
2026.06
15.67
2026.06
14.93
2026.06
14.18
2026.06
9.2
2026.06
8.96
2026.06
8.15
2026.06
7.46
2026.06
7.14
2026.06
6.72
2026.06
6.72
2026.06
6.72
2026.06
5.22
2026.06
5.22
2026.06
3.73
2026.06
3.73
2026.06
2.99
2026.06
2.24
2026.06
1.49
2026.06
0.75
2026.06
0
2026.06
0