Geekbench ML Score

941
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date May 14 2022 12:58 PM
Views 1

System Information

System Information
Operating System iOS 15.4.1
Model iPhone 13 Pro Max
Model IDiPhone14,3
Motherboard D64AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 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 CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 788
84.4 IPS
 
Image Classification (F16)
100% 763
81.8 IPS
 
Image Classification (I8)
81% 447
47.9 IPS
 
Image Segmentation (F32)
100% 1170
7.23 IPS
 
Image Segmentation (F16)
100% 1155
7.13 IPS
 
Image Segmentation (I8)
89% 1464
9.04 IPS
 
Pose Estimation (F32)
100% 444
1.80 IPS
 
Pose Estimation (F16)
100% 436
1.76 IPS
 
Pose Estimation (I8)
80% 509
2.06 IPS
 
Object Detection (F32)
100% 1137
39.9 IPS
 
Object Detection (F16)
100% 1144
40.1 IPS
 
Object Detection (I8)
52% 700
24.6 IPS
 
Face Detection (F32)
100% 1380
15.9 IPS
 
Face Detection (F16)
100% 1346
15.5 IPS
 
Face Detection (I8)
75% 841
9.66 IPS
 
Text Classification (F32)
100% 1017
402.2 IPS
 
Text Classification (F16)
100% 1073
424.2 IPS
 
Machine Translation (F32)
100% 1987
306.3 IPS
 
Machine Translation (F16)
100% 1959
301.9 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download