Geekbench ML Score

6750
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date June 17 2024 04:31 PM
Views 1

System Information

System Information
Operating System iOS 17.5.1
Model iPad16,5
Model IDiPad16,5
Motherboard J720AP
CPU Information
Name ARM
Topology 1 Processor, 10 Cores
Identifier ARM
Base Frequency 4.41 GHz
Cluster 14 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 15.05 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4218
789.2 IPS
 
Image Classification (F16)
100% 4454
833.4 IPS
 
Image Classification (I8)
99% 4095
766.3 IPS
 
Image Segmentation (F32)
100% 2001
33.4 IPS
 
Image Segmentation (F16)
100% 2268
37.9 IPS
 
Image Segmentation (I8)
100% 2223
37.1 IPS
 
Pose Estimation (F32)
100% 26869
32.5 IPS
 
Pose Estimation (F16)
100% 28918
35.0 IPS
 
Pose Estimation (I8)
100% 28084
34.0 IPS
 
Object Detection (F32)
100% 3305
246.8 IPS
 
Object Detection (F16)
100% 3930
293.4 IPS
 
Object Detection (I8)
97% 3361
251.0 IPS
 
Face Detection (F32)
100% 11431
135.9 IPS
 
Face Detection (F16)
98% 14127
168.0 IPS
 
Face Detection (I8)
97% 13743
163.4 IPS
 
Depth Estimation (F32)
100% 19640
152.3 IPS
 
Depth Estimation (F16)
100% 22059
171.1 IPS
 
Depth Estimation (I8)
37% 20072
155.7 IPS
 
Style Transfer (F32)
100% 55295
72.7 IPS
 
Style Transfer (F16)
100% 65353
86.0 IPS
 
Style Transfer (I8)
100% 64843
85.3 IPS
 
Image Super-Resolution (F32)
100% 9192
328.3 IPS
 
Image Super-Resolution (F16)
100% 9271
331.1 IPS
 
Image Super-Resolution (I8)
100% 8565
305.9 IPS
 
Text Classification (F32)
100% 1394
2.00 KIPS
 
Text Classification (F16)
100% 1535
2.21 KIPS
 
Text Classification (I8)
96% 1226
1.76 KIPS
 
Machine Translation (F32)
100% 1130
20.8 IPS
 
Machine Translation (F16)
100% 1146
21.1 IPS
 
Machine Translation (I8)
99% 916
16.9 IPS
 

Compare

Set Baseline Geekbench 6 now available