Values by metric family

Each value as the document printed it. Select a value for its source, its checks and its history.

KeyVerifiedUnverifiedDisputedCorrected read off a figure or stated in wordsA value opens its source and history.

M7 · Harmful compliance and over-refusal 7 values

M7 Harmful compliance and over-refusal: values about GPT-Live-1
Evaluation and metricValueDocument
From its own documentGPT-Live System Card · 8 Jul 2026
Voice-native production promptsEmotional relianceGPT-Live System Card8 Jul 2026
Voice-native production promptsIllicit behaviorGPT-Live System Card8 Jul 2026
Voice-native production promptsMental healthGPT-Live System Card8 Jul 2026
Voice-native production promptsSelf-harmGPT-Live System Card8 Jul 2026
Voice-native production promptsSexualGPT-Live System Card8 Jul 2026
Voice-native synthetic promptsGoreGPT-Live System Card8 Jul 2026
Voice-native synthetic promptsSexualGPT-Live System Card8 Jul 2026

M10 · Dangerous capabilities and risk determinations 1 value

M10 Dangerous capabilities and risk determinations: values about GPT-Live-1
Evaluation and metricValueDocument
From its own documentGPT-Live System Card · 8 Jul 2026
Preparedness Framework determinationAll tracked categoriesGPT-Live System Card8 Jul 2026

Risk determinations

The developer's formal decisions about GPT-Live-1 under its framework, as printed. Levels from different frameworks do not map onto one another.

Risk determinations about GPT-Live-1
DomainLevel as printedFramework and document
Overallbelow_high code, not the printed wording Preparedness Framework GPT-Live System Card · 8 Jul 2026Preparedness Framework GPT-Live System Card · 8 Jul 2026

“Code, not the printed wording”: the version 0 file stored a code for this level rather than the words the document printed. The wording will be read again from the source.