Evaluation profile
Enkrypt AI Safety Leaderboard
4sub-evals
2.34%Safety weight
5.7%Freedom weight
3components
Weights below are portfolio-specific global index weights.
Model score (higher is better)Predicted score
About this eval
Resistance to Enkrypt bias, CBRN, harmful-content, and toxicity red-team tests.
Included in the behavior ranking.
Sub-evals
| Measure | Component | Direction by ranking | Safety weight | Freedom weight |
|---|---|---|---|---|
| bias_attack_non_success_rateenkrypt-ai/enkrypt-ai.csv:bias_attack_non_success_rateMeasures how often Enkrypt's bias attacks do not succeed; it is not a broad fairness score. | Safety: human_rights_systemic_harm:0.800|ordinary_harm_misuse_resistance:0.200enkrypt-ai | Safety: higher | 0.975% | — |
| cbrn_attack_non_success_rateenkrypt-ai/enkrypt-ai.csv:cbrn_attack_non_success_rateMeasures how often Enkrypt's mixed chemistry, biology, and cybersecurity high-risk requests do not succeed; it is not direct catastrophic-capability measurement. | Safety: ordinary_harm_misuse_resistance:0.400|responsible_agency_control:0.600 · Freedom: user_direction_following:1.000enkrypt-ai | Safety: higher · Freedom: lower | 0.425% | 1.9% |
| harmful_attack_non_success_rateenkrypt-ai/enkrypt-ai.csv:harmful_attack_non_success_rateMeasures how often Enkrypt's harmful-content attacks do not succeed. | Safety: human_rights_systemic_harm:0.150|ordinary_harm_misuse_resistance:0.700|responsible_agency_control:0.150 · Freedom: user_direction_following:1.000enkrypt-ai | Safety: higher · Freedom: lower | 0.401% | 1.9% |
| toxicity_attack_non_success_rateenkrypt-ai/enkrypt-ai.csv:toxicity_attack_non_success_rateMeasures how often Enkrypt's toxicity-generation attacks do not succeed. | Safety: human_rights_systemic_harm:0.350|ordinary_harm_misuse_resistance:0.650 · Freedom: user_direction_following:1.000enkrypt-ai | Safety: higher · Freedom: lower | 0.537% | 1.9% |
bias_attack_non_success_rate
Measures how often Enkrypt's bias attacks do not succeed; it is not a broad fairness score.
cbrn_attack_non_success_rate
Measures how often Enkrypt's mixed chemistry, biology, and cybersecurity high-risk requests do not succeed; it is not direct catastrophic-capability measurement.
harmful_attack_non_success_rate
Measures how often Enkrypt's harmful-content attacks do not succeed.
toxicity_attack_non_success_rate
Measures how often Enkrypt's toxicity-generation attacks do not succeed.