Geekbench ML Score

2588
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

User davidblue
Upload Date November 09 2022 02:29 AM
Views 7

System Information

System Information
Operating System iOS 16.2
Model iPhone 12 Pro Max
Model IDiPhone13,4
Motherboard D54pAP
CPU Information
Name Apple A14 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.99 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.54 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6188
663.1 IPS
 
Image Classification (F16)
100% 6280
672.8 IPS
 
Image Classification (I8)
81% 641
68.7 IPS
 
Image Segmentation (F32)
100% 1833
11.3 IPS
 
Image Segmentation (F16)
100% 1849
11.4 IPS
 
Image Segmentation (I8)
89% 1172
7.24 IPS
 
Pose Estimation (F32)
100% 18769
75.9 IPS
 
Pose Estimation (F16)
100% 18563
75.1 IPS
 
Pose Estimation (I8)
80% 224
0.91 IPS
 
Object Detection (F32)
100% 7289
255.8 IPS
 
Object Detection (F16)
100% 7428
260.7 IPS
 
Object Detection (I8)
52% 916
32.1 IPS
 
Face Detection (F32)
100% 7646
87.8 IPS
 
Face Detection (F16)
100% 7608
87.4 IPS
 
Face Detection (I8)
75% 898
10.3 IPS
 
Text Classification (F32)
100% 1104
436.5 IPS
 
Text Classification (F16)
100% 1090
431.0 IPS
 
Machine Translation (F32)
100% 1707
263.1 IPS
 
Machine Translation (F16)
100% 1711
263.8 IPS
 

Compare

Set Baseline Geekbench 6 now available