Geekbench ML Score

971
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 19 2022 10:09 AM
Views 1

System Information

System Information
Operating System iOS 15.2.1
Model iPhone 13
Model IDiPhone14,5
Motherboard D17AP
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 3.60 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 792
84.9 IPS
 
Image Classification (F16)
100% 754
80.8 IPS
 
Image Classification (I8)
81% 462
49.5 IPS
 
Image Segmentation (F32)
100% 1112
6.87 IPS
 
Image Segmentation (F16)
100% 1073
6.63 IPS
 
Image Segmentation (I8)
89% 1447
8.94 IPS
 
Pose Estimation (F32)
100% 417
1.69 IPS
 
Pose Estimation (F16)
100% 408
1.65 IPS
 
Pose Estimation (I8)
80% 478
1.93 IPS
 
Object Detection (F32)
100% 1054
37.0 IPS
 
Object Detection (F16)
100% 1070
37.5 IPS
 
Object Detection (I8)
52% 759
26.7 IPS
 
Face Detection (F32)
100% 1322
15.2 IPS
 
Face Detection (F16)
100% 1283
14.7 IPS
 
Face Detection (I8)
75% 846
9.72 IPS
 
Text Classification (F32)
100% 1713
677.5 IPS
 
Text Classification (F16)
100% 1844
729.3 IPS
 
Machine Translation (F32)
100% 1963
302.6 IPS
 
Machine Translation (F16)
100% 1965
302.9 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download