Evaluation profile
SORRY-Bench
1sub-evals
0.245%total index weight
1components
Within-component eval weight: Misuse resistance 2.45%.
Model score (lower is better)Predicted score
About this eval
Refusal or harmful-compliance behavior across unsafe topics.
Included in the behavior ranking.
Sub-evals
| Measure | Component | Direction | Total index weight | Within-component weight |
|---|---|---|---|---|
| avgsorrybench/sorrybench.csv:avgMeasures whether the model refuses unsafe requests across many policy categories rather than providing harmful assistance. | ordinary_harm_misuse_resistance:1.000sorrybench | Lower is better | 0.245% | Misuse resistance 2.45% |
avg
Measures whether the model refuses unsafe requests across many policy categories rather than providing harmful assistance.