Geekbench ML Score

2078
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 24 2022 06:48 PM
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 GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2801
300.1 IPS
 
Image Classification (F16)
100% 4265
456.9 IPS
 
Image Classification (I8)
81% 632
67.7 IPS
 
Image Segmentation (F32)
100% 5759
35.6 IPS
 
Image Segmentation (F16)
100% 8169
50.5 IPS
 
Image Segmentation (I8)
89% 783
4.84 IPS
 
Pose Estimation (F32)
100% 1913
7.74 IPS
 
Pose Estimation (F16)
100% 4856
19.6 IPS
 
Pose Estimation (I8)
80% 151
0.61 IPS
 
Object Detection (F32)
100% 3246
113.9 IPS
 
Object Detection (F16)
100% 3642
127.8 IPS
 
Object Detection (I8)
52% 937
32.9 IPS
 
Face Detection (F32)
100% 5162
59.3 IPS
 
Face Detection (F16)
97% 8297
95.3 IPS
 
Face Detection (I8)
75% 606
6.96 IPS
 
Text Classification (F32)
100% 1491
589.6 IPS
 
Text Classification (F16)
100% 1515
599.2 IPS
 
Machine Translation (F32)
100% 2086
321.5 IPS
 
Machine Translation (F16)
100% 2062
317.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download