Safety IndexEvaluationsBenign science refusals (lab-reported)
Benign science refusals (lab-reported)
Refusal calibration · Over-refusalDeveloper-reported
The developer's own refusal rate on benign CBRN-science queries.
- Metric
- % refused. Lower is better.
- Dataset
- –
- Grader
- the developer's own grader (see the model's system card)
- Status
- –. Measured on 1 model, 0 readings by SAI.
- Notes
- From Google's Gemini 4 Argon Safety & Security Report; 700+ internal bioinformatics/genomics/chemistry queries. Developer-reported; never counted.
Results
| Model | Value | Score | Source | Setting |
|---|---|---|---|---|
| 6.1% | developer-reported | Google, Gemini 4 Argon Safety & Security Report Developer-reported · 2026-10 | Reported by the model's developer in its own system card or report.Full configurationBenign refusals on Google's internal CBRN Science set |