Geekbench ML Score

956
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 25 2021 04:44 PM
Views 1

System Information

System Information
Operating System iOS 15.2
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% 784
84.0 IPS
 
Image Classification (F16)
100% 763
81.7 IPS
 
Image Classification (I8)
81% 455
48.8 IPS
 
Image Segmentation (F32)
100% 1157
7.15 IPS
 
Image Segmentation (F16)
100% 1135
7.01 IPS
 
Image Segmentation (I8)
89% 1439
8.89 IPS
 
Pose Estimation (F32)
100% 441
1.78 IPS
 
Pose Estimation (F16)
100% 431
1.74 IPS
 
Pose Estimation (I8)
80% 497
2.01 IPS
 
Object Detection (F32)
100% 1112
39.0 IPS
 
Object Detection (F16)
100% 1112
39.0 IPS
 
Object Detection (I8)
52% 731
25.6 IPS
 
Face Detection (F32)
100% 1361
15.6 IPS
 
Face Detection (F16)
100% 1330
15.3 IPS
 
Face Detection (I8)
75% 848
9.74 IPS
 
Text Classification (F32)
100% 1243
491.8 IPS
 
Text Classification (F16)
100% 1317
521.0 IPS
 
Machine Translation (F32)
100% 1984
305.8 IPS
 
Machine Translation (F16)
100% 1971
303.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download