Geekbench ML Score

8700
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date August 15 2024 07:20 PM
Views 1

System Information

System Information
Operating System iOS 17.6.1
Model iPad16,3
Model IDiPad16,3
Motherboard J717AP
CPU Information
Name ARM
Topology 1 Processor, 9 Cores
Identifier ARM
Base Frequency 4.41 GHz
Cluster 13 Cores
Cluster 26 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.28 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4136
774.0 IPS
 
Image Classification (F16)
100% 8364
1.57 KIPS
 
Image Classification (I8)
99% 8969
1.68 KIPS
 
Image Segmentation (F32)
100% 1750
29.2 IPS
 
Image Segmentation (F16)
100% 2263
37.8 IPS
 
Image Segmentation (I8)
100% 2263
37.8 IPS
 
Pose Estimation (F32)
100% 26544
32.1 IPS
 
Pose Estimation (F16)
100% 99412
120.4 IPS
 
Pose Estimation (I8)
100% 100743
122.0 IPS
 
Object Detection (F32)
100% 2752
205.5 IPS
 
Object Detection (F16)
100% 5495
410.2 IPS
 
Object Detection (I8)
97% 3126
233.4 IPS
 
Face Detection (F32)
100% 11294
134.3 IPS
 
Face Detection (F16)
97% 13817
164.3 IPS
 
Face Detection (I8)
96% 13562
161.3 IPS
 
Depth Estimation (F32)
100% 16607
128.8 IPS
 
Depth Estimation (F16)
100% 46395
359.8 IPS
 
Depth Estimation (I8)
37% 44345
343.9 IPS
 
Style Transfer (F32)
100% 53857
70.8 IPS
 
Style Transfer (F16)
100% 145732
191.7 IPS
 
Style Transfer (I8)
100% 155310
204.3 IPS
 
Image Super-Resolution (F32)
100% 7244
258.7 IPS
 
Image Super-Resolution (F16)
100% 20449
730.3 IPS
 
Image Super-Resolution (I8)
100% 21665
773.7 IPS
 
Text Classification (F32)
100% 1343
1.93 KIPS
 
Text Classification (F16)
100% 1172
1.68 KIPS
 
Text Classification (I8)
96% 1022
1.47 KIPS
 
Machine Translation (F32)
100% 696
12.8 IPS
 
Machine Translation (F16)
100% 1784
32.8 IPS
 
Machine Translation (I8)
99% 779
14.3 IPS
 

Compare

Set Baseline Geekbench 6 now available