Safety IndexEvaluationsXSTest safe-prompt refusals
XSTest safe-prompt refusals
Refusal calibration · Over-refusalRetired from the mean (saturated)Run by SAI
How often the model refuses 250 safe prompts that superficially resemble unsafe ones.
- Metric
- % refused of 250 safe prompts. Lower is better.
- Dataset
- github.com/paul-rottger/xstest · 250 safe (+200 unsafe) · CC-BY-4.0
- Grader
- 3-class LLM judge (the paper used GPT-4 / string match)
- Status
- Run by SAI. Measured on 2 models, 2 readings by SAI.
- Replicability
- public
- Notes
- Results so far are SAI engine runs on open-weight models; the HELM Safety XSTest score is listed separately.
Results
| Model | Value | Score | Source | Setting |
|---|---|---|---|---|
| 1.3%n = 228 | not scored | SAI Measured by SAI · 2026-10-20 | Run by SAI on the open-weight model served locally; graded by azure gpt-4.1-mini.Full configurationvLLM, thinking on unless noted, no system prompt; research run; any-refusal rate; judge azure gpt-4.1-mini | |
| 7.7%n = 233 | not scored | SAI Measured by SAI · 2026-10-20 | Run by SAI on the open-weight model served locally; graded by azure gpt-4.1-mini.Full configurationvLLM, thinking on unless noted, no system prompt; research run; any-refusal rate (full refusal 2.1%); judge azure gpt-4.1-mini |