Geekbench ML Score

933
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 09 2022 03:56 AM
Views 1

System Information

System Information
Operating System iOS 16.2
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 5.52 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% 744
79.7 IPS
 
Image Classification (I8)
81% 466
50.0 IPS
 
Image Segmentation (F32)
100% 1130
6.98 IPS
 
Image Segmentation (F16)
100% 1102
6.81 IPS
 
Image Segmentation (I8)
89% 1463
9.04 IPS
 
Pose Estimation (F32)
100% 433
1.75 IPS
 
Pose Estimation (F16)
100% 423
1.71 IPS
 
Pose Estimation (I8)
80% 491
1.99 IPS
 
Object Detection (F32)
100% 1083
38.0 IPS
 
Object Detection (F16)
100% 1095
38.4 IPS
 
Object Detection (I8)
52% 755
26.5 IPS
 
Face Detection (F32)
100% 1330
15.3 IPS
 
Face Detection (F16)
100% 1310
15.1 IPS
 
Face Detection (I8)
75% 847
9.74 IPS
 
Text Classification (F32)
100% 1068
422.3 IPS
 
Text Classification (F16)
100% 1032
408.1 IPS
 
Machine Translation (F32)
100% 2051
316.1 IPS
 
Machine Translation (F16)
100% 2051
316.1 IPS
 

Compare

Set Baseline