AgentHarm measures how far a tool-using agent will go in carrying out a harmful request. It pairs 110 harmful behaviours with 110 matched benign ones, so over-refusal is measured alongside compliance.
Metric
harm score and refusal rate, with the benign pairs measuring over-refusal
Size
110 harmful and 110 benign behaviours in the source; none imported.
HarmBench is a standardized framework for comparing automated red-teaming attacks and refusal robustness on the same footing. It pits attack methods against defences and measures the success rate against harmful behaviou…
Metric
attack success rate (ASR) per attack and defence pair
Size
510 behaviours in the full benchmark, of which the linked mirror carries 400 textual ones; none imported.
JailbreakBench is an open robustness benchmark for jailbreaking attacks, defining 100 harmful behaviours alongside 100 matched benign ones. This catalogue deliberately introduces and links it rather than reproducing any …
Metric
attack success rate, with the benign pairs used to measure over-refusal
Size
100 harmful and 100 benign behaviours in the source; none imported.