Geekbench ML Score

899
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 28 2023 07:40 AM
Views 3

System Information

System Information
Operating System iOS 17.0.2
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 3.55 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 751
80.5 IPS
 
Image Classification (F16)
100% 725
77.7 IPS
 
Image Classification (I8)
81% 449
48.1 IPS
 
Image Segmentation (F32)
100% 1070
6.61 IPS
 
Image Segmentation (F16)
100% 1034
6.38 IPS
 
Image Segmentation (I8)
89% 1442
8.90 IPS
 
Pose Estimation (F32)
100% 396
1.60 IPS
 
Pose Estimation (F16)
100% 391
1.58 IPS
 
Pose Estimation (I8)
80% 456
1.85 IPS
 
Object Detection (F32)
100% 1004
35.2 IPS
 
Object Detection (F16)
100% 1004
35.3 IPS
 
Object Detection (I8)
52% 749
26.3 IPS
 
Face Detection (F32)
100% 1257
14.4 IPS
 
Face Detection (F16)
100% 1218
14.0 IPS
 
Face Detection (I8)
75% 840
9.65 IPS
 
Text Classification (F32)
100% 1142
451.7 IPS
 
Text Classification (F16)
100% 1031
407.9 IPS
 
Machine Translation (F32)
100% 2067
318.6 IPS
 
Machine Translation (F16)
100% 2047
315.5 IPS
 

Compare

Set Baseline Geekbench 6 now available