Geekbench ML Score

1457
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

User M91
Upload Date June 10 2023 08:32 AM
Views 3

System Information

System Information
Operating System iOS 16.6
Model iPad Pro 11-inch (2nd generation)
Model IDiPad8,10
Motherboard J418AP
CPU Information
Name Apple A12Z Bionic
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 5.56 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3739
400.7 IPS
 
Image Classification (F16)
100% 3701
396.5 IPS
 
Image Classification (I8)
81% 401
43.0 IPS
 
Image Segmentation (F32)
100% 1480
9.14 IPS
 
Image Segmentation (F16)
100% 1486
9.18 IPS
 
Image Segmentation (I8)
89% 747
4.62 IPS
 
Pose Estimation (F32)
100% 7816
31.6 IPS
 
Pose Estimation (F16)
100% 7816
31.6 IPS
 
Pose Estimation (I8)
80% 142
0.57 IPS
 
Object Detection (F32)
94% 4049
142.1 IPS
 
Object Detection (F16)
94% 4075
143.0 IPS
 
Object Detection (I8)
52% 566
19.9 IPS
 
Face Detection (F32)
67% 5127
58.9 IPS
 
Face Detection (F16)
67% 5207
59.8 IPS
 
Face Detection (I8)
75% 553
6.35 IPS
 
Text Classification (F32)
100% 354
140.2 IPS
 
Text Classification (F16)
100% 351
138.9 IPS
 
Machine Translation (F32)
100% 980
151.1 IPS
 
Machine Translation (F16)
100% 962
148.3 IPS
 

Compare

Set Baseline Geekbench 6 now available