Geekbench ML Score

3709
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date August 23 2024 12:41 AM
Views 2

System Information

System Information
Operating System iOS 18.0
Model iPhone 13 Pro Max
Model IDiPhone14,3
Motherboard D64AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 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 5.51 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1337
250.2 IPS
 
Image Classification (F16)
100% 2311
432.4 IPS
 
Image Classification (I8)
99% 2317
433.6 IPS
 
Image Segmentation (F32)
100% 810
13.5 IPS
 
Image Segmentation (F16)
100% 1069
17.9 IPS
 
Image Segmentation (I8)
100% 1122
18.7 IPS
 
Pose Estimation (F32)
100% 6225
7.54 IPS
 
Pose Estimation (F16)
100% 13823
16.7 IPS
 
Pose Estimation (I8)
100% 13837
16.8 IPS
 
Object Detection (F32)
100% 1343
100.3 IPS
 
Object Detection (F16)
100% 2270
169.5 IPS
 
Object Detection (I8)
97% 1352
101.0 IPS
 
Face Detection (F32)
100% 2616
31.1 IPS
 
Face Detection (F16)
97% 5451
64.8 IPS
 
Face Detection (I8)
97% 5443
64.7 IPS
 
Depth Estimation (F32)
100% 5523
42.8 IPS
 
Depth Estimation (F16)
100% 11106
86.1 IPS
 
Depth Estimation (I8)
99% 11032
85.6 IPS
 
Style Transfer (F32)
100% 17455
23.0 IPS
 
Style Transfer (F16)
100% 26258
34.5 IPS
 
Style Transfer (I8)
100% 26477
34.8 IPS
 
Image Super-Resolution (F32)
100% 4151
148.3 IPS
 
Image Super-Resolution (F16)
100% 4856
173.4 IPS
 
Image Super-Resolution (I8)
100% 4917
175.6 IPS
 
Text Classification (F32)
100% 2149
3.09 KIPS
 
Text Classification (F16)
100% 3649
5.24 KIPS
 
Text Classification (I8)
96% 3633
5.22 KIPS
 
Machine Translation (F32)
100% 1207
22.2 IPS
 
Machine Translation (F16)
100% 1388
25.6 IPS
 
Machine Translation (I8)
99% 1171
21.5 IPS
 

Compare

Set Baseline Geekbench 6 now available