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

Safety Evaluation on Redteaming Resistance Benchmark (RRB) 919-example subset

5.9HarmR

Base LLM

4.0816.36528.6540.935Oct 19, 2025
Updated 26d ago

Evaluation Results

MethodLinks
2025.10
5.93.25
2025.10
9.93.29
2025.10
10.52.14
2025.10
11.82.15
2025.10
12.73.1
2025.10
16.22.49
2025.10
21.72.2
2025.10
29.12.52
2025.10
29.82.51
2025.10
32.42.55
2025.10
39.82.6
2025.10
44.32.6
2025.10
50.92.42
2025.10
51.42.58