Geekbench ML Score

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

Result Information

Upload Date February 12 2024 06:05 PM
Views 1

System Information

System Information
Operating System iOS 17.3.1
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% 194
36.4 IPS
 
Image Classification (F16)
100% 177
33.1 IPS
 
Image Classification (I8)
99% 173
32.3 IPS
 
Image Segmentation (F32)
100% 127
2.11 IPS
 
Image Segmentation (F16)
100% 128
2.14 IPS
 
Image Segmentation (I8)
100% 127
2.13 IPS
 
Pose Estimation (F32)
100% 997
1.21 IPS
 
Pose Estimation (F16)
100% 944
1.14 IPS
 
Pose Estimation (I8)
100% 954
1.15 IPS
 
Object Detection (F32)
100% 206
15.4 IPS
 
Object Detection (F16)
100% 190
14.2 IPS
 
Object Detection (I8)
97% 212
15.9 IPS
 
Face Detection (F32)
100% 381
4.53 IPS
 
Face Detection (F16)
100% 384
4.56 IPS
 
Face Detection (I8)
99% 378
4.50 IPS
 
Depth Estimation (F32)
100% 508
3.94 IPS
 
Depth Estimation (F16)
100% 482
3.74 IPS
 
Depth Estimation (I8)
99% 476
3.70 IPS
 
Style Transfer (F32)
100% 1449
1.91 IPS
 
Style Transfer (F16)
100% 1482
1.95 IPS
 
Style Transfer (I8)
100% 1485
1.95 IPS
 
Image Super-Resolution (F32)
100% 439
15.7 IPS
 
Image Super-Resolution (F16)
100% 437
15.6 IPS
 
Image Super-Resolution (I8)
100% 452
16.2 IPS
 
Text Classification (F32)
100% 161
231.7 IPS
 
Text Classification (F16)
100% 121
173.8 IPS
 
Text Classification (I8)
96% 145
208.1 IPS
 
Machine Translation (F32)
100% 157
2.88 IPS
 
Machine Translation (F16)
100% 121
2.22 IPS
 
Machine Translation (I8)
99% 145
2.67 IPS
 

Compare

Set Baseline Geekbench 6 now available