Geekbench ML Score

1016
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 06:01 PM
Views 1

System Information

System Information
Operating System iOS 16.1.2
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

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 825
88.3 IPS
 
Image Classification (F16)
100% 827
88.6 IPS
 
Image Classification (I8)
81% 484
51.8 IPS
 
Image Segmentation (F32)
100% 1300
8.03 IPS
 
Image Segmentation (F16)
100% 1283
7.92 IPS
 
Image Segmentation (I8)
89% 1499
9.26 IPS
 
Pose Estimation (F32)
100% 502
2.03 IPS
 
Pose Estimation (F16)
100% 495
2.00 IPS
 
Pose Estimation (I8)
80% 551
2.23 IPS
 
Object Detection (F32)
100% 1233
43.3 IPS
 
Object Detection (F16)
100% 1239
43.5 IPS
 
Object Detection (I8)
52% 766
26.9 IPS
 
Face Detection (F32)
100% 1552
17.8 IPS
 
Face Detection (F16)
100% 1549
17.8 IPS
 
Face Detection (I8)
75% 856
9.83 IPS
 
Text Classification (F32)
100% 954
377.4 IPS
 
Text Classification (F16)
100% 1044
413.1 IPS
 
Machine Translation (F32)
100% 2247
346.4 IPS
 
Machine Translation (F16)
100% 2258
348.0 IPS
 

Compare

Set Baseline