Geekbench ML Score

3371
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 08 2024 08:36 AM
Views 1

System Information

System Information
Operating System iOS 17.5
Model iPad Pro (12.9-inch 5th generation)
Model IDiPad13,8
Motherboard J522AP
CPU Information
Name Apple M1
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.19 GHz
Cluster 14 Cores
Cluster 24 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.31 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1697
317.5 IPS
 
Image Classification (F16)
100% 1160
217.0 IPS
 
Image Classification (I8)
99% 1240
232.1 IPS
 
Image Segmentation (F32)
100% 852
14.2 IPS
 
Image Segmentation (F16)
100% 848
14.2 IPS
 
Image Segmentation (I8)
100% 880
14.7 IPS
 
Pose Estimation (F32)
100% 16204
19.6 IPS
 
Pose Estimation (F16)
100% 17946
21.7 IPS
 
Pose Estimation (I8)
100% 17609
21.3 IPS
 
Object Detection (F32)
100% 1515
113.1 IPS
 
Object Detection (F16)
100% 1404
104.8 IPS
 
Object Detection (I8)
97% 1548
115.6 IPS
 
Face Detection (F32)
100% 5925
70.4 IPS
 
Face Detection (F16)
98% 7129
84.8 IPS
 
Face Detection (I8)
97% 7088
84.3 IPS
 
Depth Estimation (F32)
100% 11920
92.4 IPS
 
Depth Estimation (F16)
100% 13514
104.8 IPS
 
Depth Estimation (I8)
37% 12581
97.6 IPS
 
Style Transfer (F32)
100% 27380
36.0 IPS
 
Style Transfer (F16)
100% 32346
42.5 IPS
 
Style Transfer (I8)
100% 31832
41.9 IPS
 
Image Super-Resolution (F32)
100% 4989
178.2 IPS
 
Image Super-Resolution (F16)
100% 5378
192.1 IPS
 
Image Super-Resolution (I8)
100% 5456
194.9 IPS
 
Text Classification (F32)
100% 1175
1.69 KIPS
 
Text Classification (F16)
100% 763
1.10 KIPS
 
Text Classification (I8)
96% 764
1.10 KIPS
 
Machine Translation (F32)
100% 529
9.74 IPS
 
Machine Translation (F16)
100% 535
9.84 IPS
 
Machine Translation (I8)
99% 536
9.86 IPS
 

Compare

Set Baseline Geekbench 6 now available