Pinned Loading

1. circle-guard-bench circle-guard-bench Public

   First-of-its-kind AI benchmark for evaluating the protection capabilities of large language model (LLM) guard systems (guardrails and safeguards)

   Python 61 4

2. killbench killbench Public

   Benchmark showing all major LLMs exhibit measurable decision biases, worsened by structured outputs that reduce safety refusals.

   Python 18 1