Geekbench ML Score

940
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

User MaxxxDredd
Upload Date September 30 2022 02:36 AM
Views 2

System Information

System Information
Operating System iOS 16.0.2
Model iPhone 13 Pro Max
Model IDiPhone14,3
Motherboard D64AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 781
83.7 IPS
 
Image Classification (F16)
100% 772
82.7 IPS
 
Image Classification (I8)
81% 453
48.5 IPS
 
Image Segmentation (F32)
100% 1148
7.09 IPS
 
Image Segmentation (F16)
100% 1130
6.98 IPS
 
Image Segmentation (I8)
89% 1457
9.00 IPS
 
Pose Estimation (F32)
100% 442
1.79 IPS
 
Pose Estimation (F16)
100% 434
1.76 IPS
 
Pose Estimation (I8)
80% 500
2.02 IPS
 
Object Detection (F32)
100% 1102
38.7 IPS
 
Object Detection (F16)
100% 1110
39.0 IPS
 
Object Detection (I8)
52% 761
26.7 IPS
 
Face Detection (F32)
100% 1349
15.5 IPS
 
Face Detection (F16)
100% 1321
15.2 IPS
 
Face Detection (I8)
75% 859
9.87 IPS
 
Text Classification (F32)
100% 969
383.3 IPS
 
Text Classification (F16)
100% 1084
428.7 IPS
 
Machine Translation (F32)
100% 2054
316.6 IPS
 
Machine Translation (F16)
100% 2037
314.0 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download