Geekbench ML Score

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

Result Information

Upload Date September 30 2022 02:59 AM
Views 3

System Information

System Information
Operating System iOS 16.1
Model iPhone15,3
Model IDiPhone15,3
Motherboard D74AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.45 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

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 7426
795.7 IPS
 
Image Classification (F16)
100% 7244
776.2 IPS
 
Image Classification (I8)
81% 746
79.9 IPS
 
Image Segmentation (F32)
100% 2488
15.4 IPS
 
Image Segmentation (F16)
100% 2494
15.4 IPS
 
Image Segmentation (I8)
89% 1367
8.44 IPS
 
Pose Estimation (F32)
100% 25582
103.5 IPS
 
Pose Estimation (F16)
100% 25213
102.0 IPS
 
Pose Estimation (I8)
80% 258
1.04 IPS
 
Object Detection (F32)
100% 9046
317.5 IPS
 
Object Detection (F16)
100% 9117
320.0 IPS
 
Object Detection (I8)
52% 1066
37.4 IPS
 
Face Detection (F32)
100% 10309
118.4 IPS
 
Face Detection (F16)
100% 10451
120.1 IPS
 
Face Detection (I8)
75% 1048
12.0 IPS
 
Text Classification (F32)
100% 1202
475.4 IPS
 
Text Classification (F16)
100% 1210
478.7 IPS
 
Machine Translation (F32)
100% 2276
350.8 IPS
 
Machine Translation (F16)
100% 2260
348.4 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download