Geekbench ML Score

2218
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 06 2022 06:23 PM
Views 1

System Information

System Information
Operating System iOS 16.0
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% 2754
295.1 IPS
 
Image Classification (F16)
100% 4440
475.7 IPS
 
Image Classification (I8)
81% 684
73.2 IPS
 
Image Segmentation (F32)
100% 5559
34.3 IPS
 
Image Segmentation (F16)
100% 8087
50.0 IPS
 
Image Segmentation (I8)
89% 1168
7.21 IPS
 
Pose Estimation (F32)
100% 1804
7.30 IPS
 
Pose Estimation (F16)
100% 4646
18.8 IPS
 
Pose Estimation (I8)
80% 225
0.91 IPS
 
Object Detection (F32)
100% 3190
111.9 IPS
 
Object Detection (F16)
100% 3436
120.6 IPS
 
Object Detection (I8)
52% 926
32.5 IPS
 
Face Detection (F32)
100% 4468
51.3 IPS
 
Face Detection (F16)
97% 8425
96.8 IPS
 
Face Detection (I8)
75% 880
10.1 IPS
 
Text Classification (F32)
100% 1651
652.9 IPS
 
Text Classification (F16)
100% 1995
788.9 IPS
 
Machine Translation (F32)
100% 2022
311.6 IPS
 
Machine Translation (F16)
100% 2022
311.7 IPS
 

Compare

Set Baseline Geekbench 6 now available