Geekbench ML Score

839
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 25 2023 10:24 AM
Views 1

System Information

System Information
Operating System iOS 16.3
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 CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 765
82.0 IPS
 
Image Classification (F16)
100% 745
79.8 IPS
 
Image Classification (I8)
81% 444
47.6 IPS
 
Image Segmentation (F32)
100% 1097
6.77 IPS
 
Image Segmentation (F16)
100% 1070
6.61 IPS
 
Image Segmentation (I8)
89% 1460
9.02 IPS
 
Pose Estimation (F32)
100% 407
1.65 IPS
 
Pose Estimation (F16)
100% 401
1.62 IPS
 
Pose Estimation (I8)
80% 396
1.60 IPS
 
Object Detection (F32)
100% 863
30.3 IPS
 
Object Detection (F16)
100% 884
31.0 IPS
 
Object Detection (I8)
52% 438
15.4 IPS
 
Face Detection (F32)
100% 1063
12.2 IPS
 
Face Detection (F16)
100% 987
11.3 IPS
 
Face Detection (I8)
75% 852
9.78 IPS
 
Text Classification (F32)
100% 1019
403.0 IPS
 
Text Classification (F16)
100% 1013
400.5 IPS
 
Machine Translation (F32)
100% 2046
315.3 IPS
 
Machine Translation (F16)
100% 2042
314.7 IPS
 

Compare

Set Baseline