Geekbench ML Score

1388
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 10 2024 12:28 PM
Views 1

System Information

System Information
Operating System iOS 17.5
Model iPad Pro 11-inch (2nd generation)
Model IDiPad8,10
Motherboard J418AP
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% 889
166.4 IPS
 
Image Classification (F16)
100% 1071
200.4 IPS
 
Image Classification (I8)
99% 1048
196.1 IPS
 
Image Segmentation (F32)
100% 248
4.14 IPS
 
Image Segmentation (F16)
100% 260
4.33 IPS
 
Image Segmentation (I8)
100% 259
4.33 IPS
 
Pose Estimation (F32)
100% 3023
3.66 IPS
 
Pose Estimation (F16)
100% 4311
5.22 IPS
 
Pose Estimation (I8)
100% 4331
5.24 IPS
 
Object Detection (F32)
100% 893
66.7 IPS
 
Object Detection (F16)
100% 1143
85.3 IPS
 
Object Detection (I8)
97% 911
68.0 IPS
 
Face Detection (F32)
100% 3410
40.5 IPS
 
Face Detection (F16)
98% 3905
46.4 IPS
 
Face Detection (I8)
97% 3945
46.9 IPS
 
Depth Estimation (F32)
100% 3279
25.4 IPS
 
Depth Estimation (F16)
100% 4845
37.6 IPS
 
Depth Estimation (I8)
99% 4860
37.7 IPS
 
Style Transfer (F32)
100% 8709
11.5 IPS
 
Style Transfer (F16)
100% 10488
13.8 IPS
 
Style Transfer (I8)
100% 10396
13.7 IPS
 
Image Super-Resolution (F32)
100% 1678
59.9 IPS
 
Image Super-Resolution (F16)
100% 2319
82.8 IPS
 
Image Super-Resolution (I8)
100% 2438
87.1 IPS
 
Text Classification (F32)
100% 212
304.1 IPS
 
Text Classification (F16)
100% 244
350.5 IPS
 
Text Classification (I8)
96% 246
353.2 IPS
 
Machine Translation (F32)
100% 362
6.66 IPS
 
Machine Translation (F16)
100% 356
6.56 IPS
 
Machine Translation (I8)
99% 363
6.68 IPS
 

Compare

Set Baseline Geekbench 6 now available