New from the Lab·The Compass — an open moral reasoning standard for AI, tested across frontier modelsExplore →
<- Production AI Graph
model record

GPT-4.1

PAI Lab scorecard coverage for general production behavior. Model scorecards inform deployment decisions but do not replace system-level PSF evidence.

Confidence
75%
Sources
2
Events
0
Observed
30 June 2026

Public record summary

PAI Lab scorecard coverage for general production behavior. Model scorecards inform deployment decisions but do not replace system-level PSF evidence.

D1D2D3D8

Related events

No event records are attached to this entity in the current seed.

Assessments

AssessmentTypeConfidence
GPT-4.1 — PSF coveragepsf coverage75%