Geekbench ML Score

1831
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 26 2022 02:37 AM
Views 1

System Information

System Information
Operating System iOS 16.0.2
Model iPhone 13
Model IDiPhone14,5
Motherboard D17AP
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 3.56 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1375
147.3 IPS
 
Image Classification (F16)
100% 2583
276.8 IPS
 
Image Classification (I8)
81% 692
74.1 IPS
 
Image Segmentation (F32)
100% 5253
32.4 IPS
 
Image Segmentation (F16)
100% 7383
45.6 IPS
 
Image Segmentation (I8)
89% 1163
7.18 IPS
 
Pose Estimation (F32)
100% 1765
7.14 IPS
 
Pose Estimation (F16)
100% 4205
17.0 IPS
 
Pose Estimation (I8)
80% 226
0.91 IPS
 
Object Detection (F32)
100% 1533
53.8 IPS
 
Object Detection (F16)
100% 3061
107.4 IPS
 
Object Detection (I8)
52% 951
33.4 IPS
 
Face Detection (F32)
100% 4847
55.7 IPS
 
Face Detection (F16)
97% 5862
67.3 IPS
 
Face Detection (I8)
75% 904
10.4 IPS
 
Text Classification (F32)
100% 1001
395.8 IPS
 
Text Classification (F16)
100% 1131
447.5 IPS
 
Machine Translation (F32)
100% 2026
312.2 IPS
 
Machine Translation (F16)
100% 2020
311.4 IPS
 

Compare

Set Baseline Geekbench 6 now available