Geekbench ML Score

1011
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 05:13 PM
Views 1

System Information

System Information
Operating System iOS 16.1.2
Model iPhone15,3
Model IDiPhone15,3
Motherboard D74AP
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 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 852
91.3 IPS
 
Image Classification (F16)
100% 824
88.2 IPS
 
Image Classification (I8)
81% 483
51.8 IPS
 
Image Segmentation (F32)
100% 1255
7.75 IPS
 
Image Segmentation (F16)
100% 1244
7.68 IPS
 
Image Segmentation (I8)
89% 1508
9.31 IPS
 
Pose Estimation (F32)
100% 485
1.96 IPS
 
Pose Estimation (F16)
100% 475
1.92 IPS
 
Pose Estimation (I8)
80% 544
2.20 IPS
 
Object Detection (F32)
100% 1228
43.1 IPS
 
Object Detection (F16)
100% 1237
43.4 IPS
 
Object Detection (I8)
52% 766
26.9 IPS
 
Face Detection (F32)
100% 1531
17.6 IPS
 
Face Detection (F16)
100% 1513
17.4 IPS
 
Face Detection (I8)
75% 860
9.88 IPS
 
Text Classification (F32)
100% 976
385.9 IPS
 
Text Classification (F16)
100% 1089
430.7 IPS
 
Machine Translation (F32)
100% 2257
347.8 IPS
 
Machine Translation (F16)
100% 2242
345.5 IPS
 

Compare

Set Baseline