Geekbench ML Score

286
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date June 10 2023 08:47 PM
Views 1

System Information

System Information
Operating System iOS 16.5
Model iPad Pro (10.5-inch)
Model IDiPad7,4
Motherboard J208AP
CPU Information
Name Apple A10X Fusion
Topology 1 Processor, 3 Cores
Identifier ARM
Base Frequency 2.34 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache8.00 MB x 1
Memory Information
Size 3.91 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
0
 
Image Classification (F16)
100% 383
41.0 IPS
 
Image Classification (I8)
81% 328
35.1 IPS
 
Image Segmentation (F32)
100% 735
4.54 IPS
 
Image Segmentation (F16)
100% 734
4.54 IPS
 
Image Segmentation (I8)
89% 599
3.70 IPS
 
Pose Estimation (F32)
100% 304
1.23 IPS
 
Pose Estimation (F16)
100% 305
1.24 IPS
 
Pose Estimation (I8)
80% 128
0.52 IPS
 
Object Detection (F32)
100% 482
16.9 IPS
 
Object Detection (F16)
100% 481
16.9 IPS
 
Object Detection (I8)
52% 470
16.5 IPS
 
Face Detection (F32)
100% 832
9.56 IPS
 
Face Detection (F16)
100% 851
9.78 IPS
 
Face Detection (I8)
75% 433
4.98 IPS
 
Text Classification (F32)
98% 73
28.8 IPS
 
Text Classification (F16)
98% 79
31.2 IPS
 
Machine Translation (F32)
100% 734
113.1 IPS
 
Machine Translation (F16)
100% 733
113.0 IPS
 

Compare

Set Baseline Geekbench 6 now available