Geekbench ML Score

1038
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 26 2024 05:46 PM
Views 1

System Information

System Information
Operating System iOS 17.5.1
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 CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 464
86.9 IPS
 
Image Classification (F16)
100% 667
124.8 IPS
 
Image Classification (I8)
99% 673
126.0 IPS
 
Image Segmentation (F32)
100% 296
4.95 IPS
 
Image Segmentation (F16)
100% 353
5.89 IPS
 
Image Segmentation (I8)
100% 359
6.00 IPS
 
Pose Estimation (F32)
100% 2498
3.02 IPS
 
Pose Estimation (F16)
100% 2230
2.70 IPS
 
Pose Estimation (I8)
100% 2261
2.74 IPS
 
Object Detection (F32)
100% 498
37.2 IPS
 
Object Detection (F16)
100% 777
58.0 IPS
 
Object Detection (I8)
97% 498
37.2 IPS
 
Face Detection (F32)
100% 1086
12.9 IPS
 
Face Detection (F16)
97% 1832
21.8 IPS
 
Face Detection (I8)
96% 1828
21.7 IPS
 
Depth Estimation (F32)
100% 1339
10.4 IPS
 
Depth Estimation (F16)
100% 2372
18.4 IPS
 
Depth Estimation (I8)
99% 2344
18.2 IPS
 
Style Transfer (F32)
100% 4770
6.27 IPS
 
Style Transfer (F16)
100% 7498
9.86 IPS
 
Style Transfer (I8)
100% 7548
9.93 IPS
 
Image Super-Resolution (F32)
100% 1222
43.6 IPS
 
Image Super-Resolution (F16)
100% 1456
52.0 IPS
 
Image Super-Resolution (I8)
100% 1454
51.9 IPS
 
Text Classification (F32)
100% 267
384.4 IPS
 
Text Classification (F16)
100% 521
748.4 IPS
 
Text Classification (I8)
96% 522
749.6 IPS
 
Machine Translation (F32)
100% 448
8.24 IPS
 
Machine Translation (F16)
100% 597
11.0 IPS
 
Machine Translation (I8)
99% 446
8.22 IPS
 

Compare

Set Baseline Geekbench 6 now available