Geekbench ML Score

3307
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date September 08 2024 04:48 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% 1420
265.7 IPS
 
Image Classification (F16)
100% 1850
346.2 IPS
 
Image Classification (I8)
99% 1848
345.8 IPS
 
Image Segmentation (F32)
100% 768
12.8 IPS
 
Image Segmentation (F16)
100% 543
9.07 IPS
 
Image Segmentation (I8)
100% 654
10.9 IPS
 
Pose Estimation (F32)
100% 5162
6.25 IPS
 
Pose Estimation (F16)
100% 13425
16.3 IPS
 
Pose Estimation (I8)
100% 13181
16.0 IPS
 
Object Detection (F32)
100% 1356
101.3 IPS
 
Object Detection (F16)
100% 1973
147.3 IPS
 
Object Detection (I8)
97% 1408
105.1 IPS
 
Face Detection (F32)
100% 2125
25.3 IPS
 
Face Detection (F16)
97% 3718
44.2 IPS
 
Face Detection (I8)
97% 3483
41.4 IPS
 
Depth Estimation (F32)
100% 5540
43.0 IPS
 
Depth Estimation (F16)
100% 8500
65.9 IPS
 
Depth Estimation (I8)
99% 8540
66.2 IPS
 
Style Transfer (F32)
100% 17385
22.9 IPS
 
Style Transfer (F16)
100% 26154
34.4 IPS
 
Style Transfer (I8)
100% 26092
34.3 IPS
 
Image Super-Resolution (F32)
100% 3973
141.9 IPS
 
Image Super-Resolution (F16)
100% 4873
174.0 IPS
 
Image Super-Resolution (I8)
100% 4869
173.9 IPS
 
Text Classification (F32)
100% 2363
3.40 KIPS
 
Text Classification (F16)
100% 3909
5.62 KIPS
 
Text Classification (I8)
96% 3947
5.67 KIPS
 
Machine Translation (F32)
100% 1240
22.8 IPS
 
Machine Translation (F16)
100% 1367
25.2 IPS
 
Machine Translation (I8)
99% 1107
20.4 IPS
 

Compare

Set Baseline Geekbench 6 now available