Geekbench ML Score

2265
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 11:59 PM
Views 2

System Information

System Information
Operating System iOS 16.1.2
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 GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2853
305.6 IPS
 
Image Classification (F16)
100% 4376
468.9 IPS
 
Image Classification (I8)
81% 690
73.9 IPS
 
Image Segmentation (F32)
100% 5814
35.9 IPS
 
Image Segmentation (F16)
100% 8455
52.2 IPS
 
Image Segmentation (I8)
89% 1239
7.65 IPS
 
Pose Estimation (F32)
100% 1921
7.77 IPS
 
Pose Estimation (F16)
100% 4899
19.8 IPS
 
Pose Estimation (I8)
80% 240
0.97 IPS
 
Object Detection (F32)
100% 3292
115.5 IPS
 
Object Detection (F16)
100% 3355
117.7 IPS
 
Object Detection (I8)
52% 984
34.5 IPS
 
Face Detection (F32)
100% 5202
59.8 IPS
 
Face Detection (F16)
97% 9342
107.3 IPS
 
Face Detection (I8)
75% 912
10.5 IPS
 
Text Classification (F32)
100% 1514
598.7 IPS
 
Text Classification (F16)
100% 1553
614.2 IPS
 
Machine Translation (F32)
100% 2039
314.2 IPS
 
Machine Translation (F16)
100% 2046
315.3 IPS
 

Compare

Set Baseline