Geekbench ML Score

955
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 26 2022 11:05 AM
Views 1

System Information

System Information
Operating System iOS 16.0
Model iPhone15,2
Model IDiPhone15,2
Motherboard D73AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.44 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.51 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 793
85.0 IPS
 
Image Classification (F16)
100% 772
82.7 IPS
 
Image Classification (I8)
81% 434
46.5 IPS
 
Image Segmentation (F32)
100% 1186
7.33 IPS
 
Image Segmentation (F16)
100% 1158
7.15 IPS
 
Image Segmentation (I8)
89% 1473
9.10 IPS
 
Pose Estimation (F32)
100% 439
1.78 IPS
 
Pose Estimation (F16)
100% 426
1.72 IPS
 
Pose Estimation (I8)
80% 503
2.04 IPS
 
Object Detection (F32)
100% 1132
39.7 IPS
 
Object Detection (F16)
100% 1130
39.7 IPS
 
Object Detection (I8)
52% 763
26.8 IPS
 
Face Detection (F32)
100% 1437
16.5 IPS
 
Face Detection (F16)
100% 1401
16.1 IPS
 
Face Detection (I8)
75% 841
9.66 IPS
 
Text Classification (F32)
100% 967
382.3 IPS
 
Text Classification (F16)
100% 1008
398.7 IPS
 
Machine Translation (F32)
100% 2265
349.1 IPS
 
Machine Translation (F16)
100% 2277
350.9 IPS
 

Compare

Set Baseline Geekbench 6 now available