Geekbench ML Score

3197
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 06 2022 08:49 PM
Views 2

System Information

System Information
Operating System iOS 16.0.2
Model iPhone15,3
Model IDiPhone15,3
Motherboard D74AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.44 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 7225
774.1 IPS
 
Image Classification (F16)
100% 7227
774.3 IPS
 
Image Classification (I8)
81% 746
79.9 IPS
 
Image Segmentation (F32)
100% 2420
14.9 IPS
 
Image Segmentation (F16)
100% 2515
15.5 IPS
 
Image Segmentation (I8)
89% 1367
8.45 IPS
 
Pose Estimation (F32)
100% 24687
99.9 IPS
 
Pose Estimation (F16)
100% 26829
108.6 IPS
 
Pose Estimation (I8)
80% 258
1.05 IPS
 
Object Detection (F32)
100% 8720
306.0 IPS
 
Object Detection (F16)
100% 8761
307.5 IPS
 
Object Detection (I8)
52% 1061
37.2 IPS
 
Face Detection (F32)
100% 10388
119.3 IPS
 
Face Detection (F16)
100% 10415
119.7 IPS
 
Face Detection (I8)
75% 1050
12.1 IPS
 
Text Classification (F32)
100% 1237
489.4 IPS
 
Text Classification (F16)
100% 1234
488.1 IPS
 
Machine Translation (F32)
100% 2231
343.8 IPS
 
Machine Translation (F16)
100% 2241
345.4 IPS
 

Compare

Set Baseline Geekbench 6 now available