Geekbench ML Score

2303
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 06 2022 08:48 PM
Views 1

System Information

System Information
Operating System iOS 16.1
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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2847
305.1 IPS
 
Image Classification (F16)
100% 4423
474.0 IPS
 
Image Classification (I8)
81% 696
74.6 IPS
 
Image Segmentation (F32)
100% 5894
36.4 IPS
 
Image Segmentation (F16)
100% 8430
52.1 IPS
 
Image Segmentation (I8)
89% 1251
7.73 IPS
 
Pose Estimation (F32)
100% 1906
7.71 IPS
 
Pose Estimation (F16)
100% 4889
19.8 IPS
 
Pose Estimation (I8)
80% 240
0.97 IPS
 
Object Detection (F32)
100% 3232
113.4 IPS
 
Object Detection (F16)
100% 3364
118.1 IPS
 
Object Detection (I8)
52% 994
34.9 IPS
 
Face Detection (F32)
100% 5181
59.5 IPS
 
Face Detection (F16)
97% 9329
107.2 IPS
 
Face Detection (I8)
75% 965
11.1 IPS
 
Text Classification (F32)
100% 1905
753.4 IPS
 
Text Classification (F16)
100% 1566
619.5 IPS
 
Machine Translation (F32)
100% 2055
316.7 IPS
 
Machine Translation (F16)
100% 2048
315.6 IPS
 

Compare

Set Baseline Geekbench 6 now available