Geekbench ML Score

929
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 14 2022 11:22 PM
Views 1

System Information

System Information
Operating System iOS 15.2.1
Model iPhone 13 Pro
Model IDiPhone14,2
Motherboard D63AP
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 5.56 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 770
82.5 IPS
 
Image Classification (F16)
100% 746
80.0 IPS
 
Image Classification (I8)
81% 450
48.2 IPS
 
Image Segmentation (F32)
100% 1102
6.80 IPS
 
Image Segmentation (F16)
100% 1074
6.63 IPS
 
Image Segmentation (I8)
89% 1459
9.01 IPS
 
Pose Estimation (F32)
100% 415
1.68 IPS
 
Pose Estimation (F16)
100% 411
1.66 IPS
 
Pose Estimation (I8)
80% 488
1.97 IPS
 
Object Detection (F32)
100% 1073
37.6 IPS
 
Object Detection (F16)
100% 1077
37.8 IPS
 
Object Detection (I8)
52% 747
26.2 IPS
 
Face Detection (F32)
100% 1321
15.2 IPS
 
Face Detection (F16)
100% 1280
14.7 IPS
 
Face Detection (I8)
75% 853
9.80 IPS
 
Text Classification (F32)
100% 1152
455.5 IPS
 
Text Classification (F16)
100% 1229
486.1 IPS
 
Machine Translation (F32)
100% 1954
301.1 IPS
 
Machine Translation (F16)
100% 1968
303.3 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download