Geekbench ML Score

1033
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 19 2022 05:50 PM
Views 7

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 CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 849
91.0 IPS
 
Image Classification (F16)
100% 826
88.5 IPS
 
Image Classification (I8)
81% 467
50.0 IPS
 
Image Segmentation (F32)
100% 1226
7.58 IPS
 
Image Segmentation (F16)
100% 1205
7.44 IPS
 
Image Segmentation (I8)
89% 1502
9.28 IPS
 
Pose Estimation (F32)
100% 460
1.86 IPS
 
Pose Estimation (F16)
100% 458
1.85 IPS
 
Pose Estimation (I8)
80% 536
2.17 IPS
 
Object Detection (F32)
100% 1201
42.1 IPS
 
Object Detection (F16)
100% 1202
42.2 IPS
 
Object Detection (I8)
52% 766
26.9 IPS
 
Face Detection (F32)
100% 1509
17.3 IPS
 
Face Detection (F16)
100% 1496
17.2 IPS
 
Face Detection (I8)
75% 861
9.90 IPS
 
Text Classification (F32)
100% 1421
562.1 IPS
 
Text Classification (F16)
100% 1438
568.8 IPS
 
Machine Translation (F32)
100% 2261
348.5 IPS
 
Machine Translation (F16)
100% 2281
351.5 IPS
 

Compare

Set Baseline