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

Safety Evaluation on StrongReject (SR)

16.7Reasoning Harmful Ratio

IPO

14.81227.55640.353.044Sep 29, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.09
16.710.9
2025.09
1919.7
2025.09
19.313.7
2025.09
20.78.4
2025.09
21.914.6
2025.09
23.222.6
2025.09
24.917.8
2025.09
25.121.9
2025.09
31.824.4
2025.09
34.323.3
2025.09
34.76.1
2025.09
36.52.1
2025.09
49.633.8
2025.09
55.338.7
2025.09
57.642
2025.09
63.249.3
2025.09
63.951.9