Geekbench ML Score

3192
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 26 2022 10:58 AM
Views 2

System Information

System Information
Operating System iOS 16.0
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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 7084
759.0 IPS
 
Image Classification (F16)
100% 7096
760.3 IPS
 
Image Classification (I8)
81% 745
79.8 IPS
 
Image Segmentation (F32)
100% 2420
14.9 IPS
 
Image Segmentation (F16)
100% 2390
14.8 IPS
 
Image Segmentation (I8)
89% 1342
8.29 IPS
 
Pose Estimation (F32)
100% 25709
104.0 IPS
 
Pose Estimation (F16)
100% 26366
106.7 IPS
 
Pose Estimation (I8)
80% 258
1.04 IPS
 
Object Detection (F32)
100% 8859
310.9 IPS
 
Object Detection (F16)
100% 8818
309.5 IPS
 
Object Detection (I8)
52% 1061
37.2 IPS
 
Face Detection (F32)
100% 10376
119.2 IPS
 
Face Detection (F16)
100% 10407
119.6 IPS
 
Face Detection (I8)
75% 1036
11.9 IPS
 
Text Classification (F32)
100% 1274
503.8 IPS
 
Text Classification (F16)
100% 1248
493.6 IPS
 
Machine Translation (F32)
100% 2251
347.0 IPS
 
Machine Translation (F16)
100% 2241
345.3 IPS
 

Compare

Set Baseline Geekbench 6 now available