Geekbench ML Score

1977
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date May 31 2023 02:31 PM
Views 2

System Information

System Information
Operating System iOS 16.5
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% 1734
185.8 IPS
 
Image Classification (F16)
100% 2618
280.5 IPS
 
Image Classification (I8)
81% 645
69.1 IPS
 
Image Segmentation (F32)
100% 5334
32.9 IPS
 
Image Segmentation (F16)
100% 7194
44.4 IPS
 
Image Segmentation (I8)
89% 1113
6.87 IPS
 
Pose Estimation (F32)
100% 1763
7.13 IPS
 
Pose Estimation (F16)
100% 4190
17.0 IPS
 
Pose Estimation (I8)
80% 214
0.87 IPS
 
Object Detection (F32)
100% 2132
74.8 IPS
 
Object Detection (F16)
100% 3075
107.9 IPS
 
Object Detection (I8)
52% 895
31.4 IPS
 
Face Detection (F32)
100% 4790
55.0 IPS
 
Face Detection (F16)
97% 5795
66.6 IPS
 
Face Detection (I8)
75% 858
9.85 IPS
 
Text Classification (F32)
100% 1801
712.2 IPS
 
Text Classification (F16)
100% 2052
811.7 IPS
 
Machine Translation (F32)
100% 2035
313.7 IPS
 
Machine Translation (F16)
100% 2045
315.2 IPS
 

Compare

Set Baseline Geekbench 6 now available