← all datasets

5 different benchmarks

Emerging
1papers using it
2025first seen

The '5 different benchmarks' dataset/benchmark is used to evaluate the effectiveness and robustness of reasoning-based safety guardrails for Large Reasoning Models (LRMs) against various jailbreak methods.

🔎 Find this dataset

Papers using 5 different benchmarks (1)

5 different benchmarks — datasets — cybersecurity