Geekbench ML Score

3210
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 05 2022 12:51 AM
Views 4

System Information

System Information
Operating System iOS 16.1
Model iPhone15,2
Model IDiPhone15,2
Motherboard D73AP
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 5.51 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 7224
774.1 IPS
 
Image Classification (F16)
100% 7216
773.1 IPS
 
Image Classification (I8)
81% 746
79.9 IPS
 
Image Segmentation (F32)
100% 2419
14.9 IPS
 
Image Segmentation (F16)
100% 2449
15.1 IPS
 
Image Segmentation (I8)
89% 1367
8.44 IPS
 
Pose Estimation (F32)
100% 25907
104.8 IPS
 
Pose Estimation (F16)
100% 25312
102.4 IPS
 
Pose Estimation (I8)
80% 259
1.05 IPS
 
Object Detection (F32)
100% 8908
312.6 IPS
 
Object Detection (F16)
100% 9061
318.0 IPS
 
Object Detection (I8)
52% 1065
37.4 IPS
 
Face Detection (F32)
100% 10415
119.7 IPS
 
Face Detection (F16)
100% 10580
121.5 IPS
 
Face Detection (I8)
75% 1050
12.1 IPS
 
Text Classification (F32)
100% 1225
484.7 IPS
 
Text Classification (F16)
100% 1234
488.2 IPS
 
Machine Translation (F32)
100% 2297
353.9 IPS
 
Machine Translation (F16)
100% 2288
352.6 IPS
 

Compare

Set Baseline Geekbench 6 now available