Geekbench ML Score

318
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date August 16 2024 06:28 PM
Views 1

System Information

System Information
Operating System iOS 17.6
Model iPad (6th generation)
Model IDiPad7,5
Motherboard J71bAP
CPU Information
Name Apple A10 Fusion
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.32 GHz
Cluster 12 Cores
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.93 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 197
36.8 IPS
 
Image Classification (F16)
100% 175
32.8 IPS
 
Image Classification (I8)
99% 173
32.3 IPS
 
Image Segmentation (F32)
100% 125
2.08 IPS
 
Image Segmentation (F16)
100% 128
2.13 IPS
 
Image Segmentation (I8)
100% 125
2.09 IPS
 
Pose Estimation (F32)
100% 972
1.18 IPS
 
Pose Estimation (F16)
100% 937
1.13 IPS
 
Pose Estimation (I8)
100% 917
1.11 IPS
 
Object Detection (F32)
100% 212
15.8 IPS
 
Object Detection (F16)
100% 186
13.9 IPS
 
Object Detection (I8)
97% 213
15.9 IPS
 
Face Detection (F32)
100% 387
4.60 IPS
 
Face Detection (F16)
100% 368
4.37 IPS
 
Face Detection (I8)
99% 384
4.57 IPS
 
Depth Estimation (F32)
100% 519
4.03 IPS
 
Depth Estimation (F16)
100% 493
3.83 IPS
 
Depth Estimation (I8)
99% 487
3.78 IPS
 
Style Transfer (F32)
100% 1460
1.92 IPS
 
Style Transfer (F16)
100% 1463
1.92 IPS
 
Style Transfer (I8)
100% 1446
1.90 IPS
 
Image Super-Resolution (F32)
100% 416
14.9 IPS
 
Image Super-Resolution (F16)
100% 415
14.8 IPS
 
Image Super-Resolution (I8)
100% 441
15.7 IPS
 
Text Classification (F32)
100% 180
258.2 IPS
 
Text Classification (F16)
100% 142
204.6 IPS
 
Text Classification (I8)
96% 140
201.9 IPS
 
Machine Translation (F32)
100% 143
2.64 IPS
 
Machine Translation (F16)
100% 124
2.29 IPS
 
Machine Translation (I8)
99% 139
2.56 IPS
 

Compare

Set Baseline Geekbench 6 now available