AILuminate (demo prompts)

Evals

Benchmark / dataset

Public demo set of the AILuminate hazard benchmark.

Category
Jailbreak & misuse
Insurance exposure
Regulatory/bias
Publisher
MLCommons
Publisher type
Nonprofit / research org
License
Apache-2.0
Status
Stale (>12mo)
Last commit
2025-06-11
Stars
84
Notes
Full set is held out.

View source on GitHub →


Wanich Risk Lab, 2026.