Geekbench ML Score

3521
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date September 08 2024 04:41 AM
Views 1

System Information

System Information
Operating System iOS 17.5.1
Model iPhone 14 Pro Max
Model IDiPhone15,3
Motherboard D74AP
CPU Information
Name Apple A16 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.46 GHz
Cluster 12 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 5.48 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1437
269.0 IPS
 
Image Classification (F16)
100% 1880
351.8 IPS
 
Image Classification (I8)
99% 1862
348.5 IPS
 
Image Segmentation (F32)
100% 761
12.7 IPS
 
Image Segmentation (F16)
100% 767
12.8 IPS
 
Image Segmentation (I8)
100% 780
13.0 IPS
 
Pose Estimation (F32)
100% 6318
7.65 IPS
 
Pose Estimation (F16)
100% 14082
17.1 IPS
 
Pose Estimation (I8)
100% 14066
17.0 IPS
 
Object Detection (F32)
100% 1437
107.3 IPS
 
Object Detection (F16)
100% 1975
147.5 IPS
 
Object Detection (I8)
97% 1447
108.0 IPS
 
Face Detection (F32)
100% 2727
32.4 IPS
 
Face Detection (F16)
97% 4354
51.8 IPS
 
Face Detection (I8)
97% 4336
51.6 IPS
 
Depth Estimation (F32)
100% 5514
42.8 IPS
 
Depth Estimation (F16)
100% 8681
67.3 IPS
 
Depth Estimation (I8)
99% 8523
66.1 IPS
 
Style Transfer (F32)
100% 17149
22.6 IPS
 
Style Transfer (F16)
100% 26026
34.2 IPS
 
Style Transfer (I8)
100% 26633
35.0 IPS
 
Image Super-Resolution (F32)
100% 4041
144.3 IPS
 
Image Super-Resolution (F16)
100% 4925
175.9 IPS
 
Image Super-Resolution (I8)
100% 4994
178.4 IPS
 
Text Classification (F32)
100% 2381
3.42 KIPS
 
Text Classification (F16)
100% 3955
5.68 KIPS
 
Text Classification (I8)
96% 3986
5.73 KIPS
 
Machine Translation (F32)
100% 1226
22.6 IPS
 
Machine Translation (F16)
100% 1540
28.3 IPS
 
Machine Translation (I8)
99% 1221
22.5 IPS
 

Compare

Set Baseline Geekbench 6 now available