HELM (incl. HELM Safety)
EvalsFramework / harness (not an eval — tooling/reference entry)
Holistic Evaluation of Language Models; safety, bias, robustness scenarios.
- Category
- Eval frameworks & harnesses
- Insurance exposure
- Regulatory/bias
- Publisher
- Stanford CRFM
- Publisher type
- Academic
- License
- Apache-2.0
- Status
- Maintained (<12mo) / deprecated
- Last commit
- 2026-09-01
- Stars
- 2946
- Notes
- Maintenance mode since June 1, 2026.
Wanich Risk Lab, 2026.