Geekbench ML Score

3133
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 05 2022 03:31 AM
Views 2

System Information

System Information
Operating System iOS 16.0
Model iPad14,5
Model IDiPad14,5
Motherboard J620AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.46 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.33 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 7591
813.4 IPS
 
Image Classification (F16)
100% 7562
810.2 IPS
 
Image Classification (I8)
81% 734
78.7 IPS
 
Image Segmentation (F32)
100% 2312
14.3 IPS
 
Image Segmentation (F16)
100% 2298
14.2 IPS
 
Image Segmentation (I8)
89% 1343
8.29 IPS
 
Pose Estimation (F32)
100% 27550
111.5 IPS
 
Pose Estimation (F16)
100% 27705
112.1 IPS
 
Pose Estimation (I8)
80% 255
1.03 IPS
 
Object Detection (F32)
100% 8506
298.5 IPS
 
Object Detection (F16)
100% 8460
296.9 IPS
 
Object Detection (I8)
52% 1048
36.8 IPS
 
Face Detection (F32)
100% 9663
111.0 IPS
 
Face Detection (F16)
100% 9645
110.8 IPS
 
Face Detection (I8)
75% 1026
11.8 IPS
 
Text Classification (F32)
100% 1306
516.4 IPS
 
Text Classification (F16)
100% 1319
521.5 IPS
 
Machine Translation (F32)
100% 1913
294.8 IPS
 
Machine Translation (F16)
100% 1917
295.4 IPS
 

Compare

Set Baseline Geekbench 6 now available