Geekbench ML Score

3190
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 26 2022 02:42 AM
Views 1

System Information

System Information
Operating System iOS 16.0.2
Model iPhone15,2
Model IDiPhone15,2
Motherboard D73AP
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 5.51 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 7293
781.4 IPS
 
Image Classification (F16)
100% 7288
780.9 IPS
 
Image Classification (I8)
81% 741
79.4 IPS
 
Image Segmentation (F32)
100% 2427
15.0 IPS
 
Image Segmentation (F16)
100% 2350
14.5 IPS
 
Image Segmentation (I8)
89% 1325
8.18 IPS
 
Pose Estimation (F32)
100% 26409
106.9 IPS
 
Pose Estimation (F16)
100% 25519
103.3 IPS
 
Pose Estimation (I8)
80% 257
1.04 IPS
 
Object Detection (F32)
100% 8917
312.9 IPS
 
Object Detection (F16)
100% 8940
313.8 IPS
 
Object Detection (I8)
52% 1054
37.0 IPS
 
Face Detection (F32)
100% 10461
120.2 IPS
 
Face Detection (F16)
100% 10482
120.4 IPS
 
Face Detection (I8)
75% 1013
11.6 IPS
 
Text Classification (F32)
100% 1232
487.4 IPS
 
Text Classification (F16)
100% 1261
498.8 IPS
 
Machine Translation (F32)
100% 2233
344.2 IPS
 
Machine Translation (F16)
100% 2245
346.0 IPS
 

Compare

Set Baseline Geekbench 6 now available