
Measuring on-device machine learning performance, this benchmark runs ten real-world AI workloads across CPU, GPU, and Neural Engine hardware, with Core ML as one selectable framework. Results come as single precision, half precision, and quantized scores, so users and IT teams can compare devices and judge readiness for AI-heavy applications.
anchor apple generic and identifier "com.primatelabs.macos.geekbenchml" and (certificate leaf[field.1.2.840.113635.100.6.1.9] /* exists */ or certificate 1[field.1.2.840.113635.100.6.2.6] /* exists */ and certificate leaf[field.1.2.840.113635.100.6.1.13] /* exists */ and certificate leaf[subject.OU] = SRW94G4YYQ)