Geekbench ML Score

2301
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 07 2022 01:29 AM
Views 1

System Information

System Information
Operating System iOS 16.0.2
Model iPhone 13 Pro Max
Model IDiPhone14,3
Motherboard D64AP
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 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2889
309.5 IPS
 
Image Classification (F16)
100% 4448
476.6 IPS
 
Image Classification (I8)
81% 692
74.1 IPS
 
Image Segmentation (F32)
100% 5877
36.3 IPS
 
Image Segmentation (F16)
100% 8264
51.0 IPS
 
Image Segmentation (I8)
89% 1246
7.70 IPS
 
Pose Estimation (F32)
100% 1905
7.71 IPS
 
Pose Estimation (F16)
100% 4888
19.8 IPS
 
Pose Estimation (I8)
80% 233
0.94 IPS
 
Object Detection (F32)
100% 3266
114.6 IPS
 
Object Detection (F16)
100% 3345
117.4 IPS
 
Object Detection (I8)
52% 988
34.7 IPS
 
Face Detection (F32)
100% 5104
58.6 IPS
 
Face Detection (F16)
97% 9270
106.5 IPS
 
Face Detection (I8)
75% 947
10.9 IPS
 
Text Classification (F32)
100% 1914
757.1 IPS
 
Text Classification (F16)
100% 1703
673.5 IPS
 
Machine Translation (F32)
100% 2024
311.9 IPS
 
Machine Translation (F16)
100% 2023
311.8 IPS
 

Compare

Set Baseline Geekbench 6 now available