Geekbench ML Score

1395
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date January 23 2024 11:33 PM
Views 1

System Information

System Information
Operating System iOS 17.3
Model iPad Pro 11-inch (2nd generation)
Model IDiPad8,9
Motherboard J417AP
CPU Information
Name Apple A12Z Bionic
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 2.49 GHz
Cluster 14 Cores
Cluster 24 Cores
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 5.56 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 846
158.3 IPS
 
Image Classification (F16)
100% 986
184.6 IPS
 
Image Classification (I8)
99% 955
178.7 IPS
 
Image Segmentation (F32)
100% 257
4.30 IPS
 
Image Segmentation (F16)
100% 263
4.39 IPS
 
Image Segmentation (I8)
100% 260
4.34 IPS
 
Pose Estimation (F32)
100% 3006
3.64 IPS
 
Pose Estimation (F16)
100% 4314
5.22 IPS
 
Pose Estimation (I8)
100% 4307
5.22 IPS
 
Object Detection (F32)
100% 900
67.2 IPS
 
Object Detection (F16)
100% 1158
86.5 IPS
 
Object Detection (I8)
97% 895
66.8 IPS
 
Face Detection (F32)
100% 3443
40.9 IPS
 
Face Detection (F16)
97% 3937
46.8 IPS
 
Face Detection (I8)
96% 3938
46.8 IPS
 
Depth Estimation (F32)
100% 3276
25.4 IPS
 
Depth Estimation (F16)
100% 4789
37.1 IPS
 
Depth Estimation (I8)
99% 4788
37.1 IPS
 
Style Transfer (F32)
24% 8526
11.2 IPS
 
Style Transfer (F16)
30% 12511
16.5 IPS
 
Style Transfer (I8)
30% 12418
16.3 IPS
 
Image Super-Resolution (F32)
100% 1740
62.2 IPS
 
Image Super-Resolution (F16)
100% 2333
83.3 IPS
 
Image Super-Resolution (I8)
100% 2259
80.7 IPS
 
Text Classification (F32)
100% 210
302.3 IPS
 
Text Classification (F16)
100% 252
361.7 IPS
 
Text Classification (I8)
96% 255
366.4 IPS
 
Machine Translation (F32)
100% 361
6.64 IPS
 
Machine Translation (F16)
100% 355
6.54 IPS
 
Machine Translation (I8)
99% 361
6.65 IPS
 

Compare

Set Baseline Geekbench 6 now available