← Evals

Evaluation profile

OpenAI GPT-5 System Card

1sub-evals
0.0678%total index weight
1components

Within-component eval weight: Misuse resistance 0.678%.

Model score (higher is better)Predicted score

About this eval

Developer-reported release-time safety behavior.

Included in the behavior ranking.

Sub-evals

MeasureComponentDirectionTotal index weightWithin-component weight
harmful_request_safetysystem-cards-2026-08-01/openai-gpt5.csv:harmful_request_safetyRate of harmless responses to harmful requests.ordinary_harm_misuse_resistance:1.000openai-gpt5Higher is better0.0678%Misuse resistance 0.678%

harmful_request_safety

Rate of harmless responses to harmful requests.

RankModelValueRelative performanceProvenance
1gpt-50.912official
2gpt-4o0.633official